Back

Explore every episode of the podcast Build With AI

Dive into the complete episode list for Build With AI. Each episode is cataloged with detailed descriptions, making it easy to find and explore specific topics. Keep track of all episodes from your favorite podcast and never miss a moment of insightful content.

Rows per page:

1–50 of 64

TitlePub. DateDuration
How I'm finding all my AI services clients05 Jun 202600:14:55

In this solo episode, I walk through seven ways to land clients for your AI services business — starting with the method that personally got me seven qualified leads in about two hours of total effort. I cover everything from hosting a local AI meetup to knocking on doors to LinkedIn outreach to building agency partnerships, and I break down exactly what to say and do at each step. Every method ties back to one simple foot-in-the-door offer that converts cold strangers into paying clients. By the end, you'll know where to start, what to prioritize first, and how to stack these methods to build a real pipeline fast.

Join AI Operator Academy where we go even deeper on selling AI services, finding clients, and building an AI Operating System: https://aoa.community/

https://app.excalidraw.com/l/4z8Z2Lyybfg/jhXBCxthrX
 
Timestamps

00:00 – Intro
00:00 – Method 1: Host a local AI for small business meetup
02:24 – The follow-up that makes the meetup worth it
02:50 – Method 2: Door knocking local service businesses
04:47 – Method 3: LinkedIn outreach without being spammy
06:30 – Method 4: Free audits for people in your network
07:10 – Documenting wins and building early testimonials
08:10 – Method 5: Partnering with agencies, coaches, and consultants
09:35 – Method 6: Hosting AI office hours at a co-working space
11:56 – Method 7: Posting your wins on LinkedIn
13:30 – Where to start: the three methods to do first
 
Key Points
 
Hosting a local AI for small business meetup is the single best method to start with. Find a free venue (library, co-working space, or a realtor's office), set up an Eventbrite or Luma page, give a 20-minute talk on basic AI tools, and capture every name, phone number, and email at the door. The magic is in the follow-up within 24 hours.
 
The foot-in-the-door offer that powers every method on this list is a free 15-minute mini AI assessment. You're not selling anything upfront — you're prescribing one simple AI tool specific to their business. That assessment is what converts conversations into paying clients.
 
Door knocking local service businesses is the lowest-hanging fruit if you want a client today. One person went into 30 businesses, got five appointments, and landed two paying clients. If you do 10 walk-ins a week consistently, you will get clients.
 
Partnering with marketing agencies, coaches, and consultants is the highest long-term value method on the list. These partners already have your future clients as their clients, and most of them have no good answer when those clients ask about AI. You become their go-to AI resource and offer a cut of any work they send your way. One good partner can send you 50 to 100 leads over the course of a year.
 
Hosting AI office hours at a co-working space gives you free marketing and free exposure while positioning you as the local AI expert. You show up for two hours, answer member questions for free, and document every single question — those become your social media content and your client pipeline.
 
Every free audit, every question you answer, every text message that says "wow, I didn't know that" is an early win and an early testimonial. Screenshot all of it. These are your case studies for landing the next client and building toward charging $999 for a full paid assessment.
 
LinkedIn is the best platform for landing AI services clients. Post three to five times a week mixing wins, answers to common questions, and real education. Stay top of mind so that when someone needs an AI expert, you're the first person they call.
 
Luma - Event registration platform for hosting and promoting your AI meetup - https://lu.ma
 
Eventbrite - Free event pages to get attendees registered and confirmed - https://www.eventbrite.com

AI Operator Academy - https://www.skool.com/aioperatoracademy/about
 
FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim
 
 

How to build a $10K/month AI consulting business in 90 days (step-by-step)02 Jun 202600:15:22

In this solo episode, I walk through the exact offer I'm using to make over $1,000 an hour with AI consulting — the AI Concierge Offer — and break it down step by step so you can replicate it. I cover every piece of the infrastructure: the pre-call intake form I built in Jotform, the two 45-minute done-with-you strategy calls every month, the Voxer access setup with a real SLA, and the Notion documentation hub that tracks every automation we build together. I also show you how two Claude skills handle all my post-call follow-up in 30 seconds flat, and walk through exactly how I price this — from $1,000 a month to start, all the way up to where I'm at now at $2,000 a month with a 100% close rate. By the end of this episode, you'll have a complete blueprint to go build your own AI consulting business and land your first paying clients.

 
https://link.excalidraw.com/l/4z8Z2Lyybfg/8E8aGK6n25P

 Timestamps

00:00 – Making over $1,000/hour with the AI Concierge Offer

01:40 – The pre-call intake form built in Jotform

03:40 – The two 45-minute done-with-you strategy calls

04:30 – The AOA framework: Audit, Optimize, Automate

06:00 – Voxer access and the 12-hour SLA

08:00 – The Notion documentation hub walkthrough

09:56 – How two Claude skills automate post-call follow-up

12:15 – Pricing: from $1,000 to $2,000/month and when to raise rates

14:23 – How to get the full templates and business model

 

Key Points

 

The AI Concierge Offer is a done-with-you consulting engagement, not done-for-you. Two 45-minute strategy calls per month plus unlimited Voxer access — that's roughly 1.5 hours of your time per client at $1,500/month, which works out to $1,000 an hour.

 

The AOA framework — Audit, Optimize, Automate — is the operating system for every client engagement. You fix the process first before you ever touch automation, so you're not just automating broken workflows.

 

A pre-call Jotform intake questionnaire sent before the first paid call surfaces the client's biggest bottlenecks and makes the first session actually productive from minute one. If they haven't filled it out, reschedule — it's not optional.

 

The Notion documentation hub is the renewal mechanism. When clients can see a running quantified list of every skill, workflow, and automation you built together, the $1,500 or $2,000/month fee is easy for them to justify.

 

Two Claude skills handle all post-call admin in 30 seconds — one populates the Notion call log from the transcript, the other pulls out action items and drafts a follow-up email to the client. Build the infrastructure once and it runs itself.

 

When you're closing 100% of your sales calls, your price is too low. Start at $1,000/month, move to $1,500 once you have two clients, and keep raising until people push back. Corey is currently at $2,000/month and still closing every pitch.

 

Cap yourself at six clients. More than that and service quality degrades — and at $2,000/month, six clients is $12,000/month for roughly 9 hours of strategy call time.

 

Links Mentioned

 

AI Operator Academy — community with the full AI Concierge Offer business model, Jotform template, Notion hub template, and both Claude skills included: https://www.skool.com/aioperatoracademy/about

 

Voxer — walkie-talkie style async voice messaging app used for client communication between strategy calls: https://www.voxer.com

 

Jotform — form builder used to create the pre-call AI concierge intake questionnaire: https://www.jotform.com

 

FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

Build STUNNING Websites with Claude Code + Google Stitch (full walkthrough)17 Apr 202601:05:07

I sit down with Leon van Zyl, who ran a web design company for 10 years and now teaches over 700 people how to build real applications with coding agents. We walk through his exact workflow for building professional, client-ready websites using Google Stitch for the design system and Claude Code for the build — no coding skills required. Leon shows the difference between a one-shot AI-generated site and what you get when you front-load the design system before touching code. By the end, you'll have a repeatable workflow for going from design concept to finished website — including custom AI images that match your brand.

Links Mentioned:

Google Stitch: https://stitch.withgoogle.com

Claude Code: https://docs.anthropic.com/en/docs/claude-code

Cursor: https://www.cursor.com

Next.js: https://nextjs.org

Stitch MCP Server Docs: https://stitch.withgoogle.com/docs/mcp

Stitch Skills: https://stitch.withgoogle.com/docs/skills

Timestamps

00:00 – Intro

00:06 – What you'll learn: design systems for client-ready websites

02:04 – Jumping into the screen share

02:25 – The problem: one-shot AI websites look terrible

03:52 – The Stitch workflow result: side-by-side comparison

07:32 – Starting from a vanilla Next.js project

08:50 – What is Google Stitch and how to get started

10:00 – Prompting Stitch with brand details, fonts, and colors

13:00 – Why design systems matter for coding agents

16:00 – Iterating on the homepage before building more pages

17:44 – Sharing Stitch designs with clients for approval

21:23 – Setting up the Stitch MCP server in Claude Code

23:18 – What an MCP server actually is (simple explanation)

25:56 – Pulling the design system into your project

28:47 – Memory files: Claude.md vs Agents.md explained

33:24 – Converting the Stitch design into a working website

35:06 – Installing the Stitch React Components skill

41:11 – When to use this workflow: client work vs personal projects

44:27 – Viewing the finished website vs the Stitch mockup

48:27 – Downloading and converting images to WebP for performance

53:46 – Generating custom AI images with Nano Banana Pro

58:14 – Final result with branded AI-generated hero image

01:00:48 – Key takeaways and wrap-up

FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

FIND LEON ON SOCIAL

YouTube: https://www.youtube.com/@leonvanzyl

Claude Code Routines Clearly Explained (and why it matters)14 Apr 202600:05:11

Claude Code just dropped routines, and when I first saw the three options — routine, schedule, and loop — I had no idea when to use which. In this video, I break down all three modes in plain language and then demo building a routine from scratch using an X trend scanner I already had in my skill library. You'll see the full setup: GitHub connection, system prompt config, trigger options, and connector permissions. By the end, you'll know exactly which mode to use for any automation you want to build and how to get your first routine live.

Links Mentioned:
Claude Code Routines: https://claude.ai/code/routines
GitHub: https://github.com

Timestamps
00:00 – Intro: The confusion with Claude Code's new features
00:20 – The three modes: routine, schedule, and loop
00:50 – When to use each mode (simple breakdown)
01:10 – Using Claude Code to find a skill to demo
01:45 – Selecting the X scan routine
02:00 – GitHub requirement for routines explained
02:18 – Creating a new routine at claude.ai/code/routines
02:35 – Naming your routine and connecting your GitHub repo
02:50 – Dropping in your system prompt
03:05 – Setting the schedule trigger (10am Eastern daily)
03:20 – Configuring connectors and permission sets
03:40 – Running on demand and reviewing the output
04:10 – Full recap of all three modes

Key Points

* Claude Code has three automation modes — routine (runs on Anthropic's cloud, set it and forget it), schedule (needs local access, also available in Cowork), and loop (immediate execution in the CLI). Picking the wrong one means your automation won't work the way you expect.

* Routines require a GitHub repository. You can't create one without it, so get your repo connected before you start.

* The whole setup happens at claude.ai/code/routines — no coding required beyond having a system prompt in markdown format ready to paste in.

* Routines support three trigger types: time-based schedule, GitHub event, or API call. That gives you flexibility depending on whether you want it cron-based, push-based, or fired from another system.

* The X trend scanner ran automatically and surfaced several trending topic candidates with suggested content angles — zero manual research, just results ready to use.

FIND ME ON SOCIAL
X/Twitter: https://x.com/GanimCorey
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/

FIND NICK ON SOCIAL
X: https://x.com/NickSpisak_
LinkedIn: https://www.linkedin.com/in/nicholasspisak/
YouTube: https://www.youtube.com/@UCusMlMDWZS0uOlhgL0M_q-A

Claude Managed Agents Clearly Explained (and why it matters)10 Apr 202600:12:40

Grab the free Google Doc to build and deploy your first Claude Managed Agent in 60 seconds: https://return-my-time.kit.com/2872b904f5

I sit down with Nick Spisak, an AI agent builder who deployed his first Claude Managed Agent the same week Anthropic released the capability, to break down exactly what this platform is, who it's for, and when it makes financial sense to use it. We walk through the four user personas Claude Managed Agents is built for.

Links Mentioned:
Corey's X article: https://x.com/coreyganim/status/2042286607449874527
Nick's X article: https://x.com/NickSpisak_/status/2041949191887262164

Timestamps
00:00 – Intro
00:05 – What is Claude Managed Agents?
00:29 – Architecture: decoupling tools, sessions, and orchestration
01:15 – Who managed agents is and isn't for
01:33 – The four user personas breakdown
03:58 – Why AI Tinkerers should stick with Claude Code subscription
04:21 – Free Google Doc: build your first agent in 60 seconds
05:28 – Platform-as-a-service model explained
05:43 – Cost comparison: Managed Agents vs Agent SDK
06:09 – Live look inside platform.claude.com
06:23 – Workbench, sessions, and output walkthrough
08:16 – Sessions: tool calls vs. finished output explained
08:31 – Analytics dashboard and real cost breakdown
09:36 – When the ROI math works (and when it doesn't)
11:18 – Next steps: articles on X, how to get started
12:04 – Outro

Join the Build With AI community - weekly AI implementations, live coaching, and templates built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about

FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

FIND NICK ON SOCIAL

X: https://x.com/NickSpisak_

LinkedIn: https://www.linkedin.com/in/nicholasspisak/

YouTube: https://www.youtube.com/@nickspisak_

Build Karpathy's Second Brain With Obsidian + Claude Code07 Apr 202600:22:21

Download Nick's free second brain skill -- one-click install that sets up your entire Obsidian vault and ingestion workflow inside Claude Code: https://return-my-time.kit.com/286e11f7e6

I brought on Nick Spisak to build a complete second brain live -- start to finish, in under 20 minutes. By the end of this episode, you'll know exactly how to build your own second brain -- and you can grab Nick's free skill to do it in one click.

Timestamps

00:00 - Intro and Karpathy's viral second brain tweet

00:24 - What the second brain concept is

03:28 - Obsidian Web Clipper: scraping pages into your vault

04:41 - Nick's free skill: wizard, ingest, query, and lint commands

05:53 - Live demo: running the setup wizard in Claude Code

08:38 - How many vaults to manage: personal vs. business

10:30 - Opening the vault and exploring the file structure

12:21 - Graph view: seeing connections between your data

15:38 - Ingest command: raw data into organized wiki

16:29 - Automating ingestion on a cron schedule

19:12 - Compounding value and syncing the vault across devices

20:19 - Pruning the vault with the lint command

21:53 - Your data set as a moat in the AI age

Key Points

* Karpathy released a framework for building an LLM knowledge base. Nick turned it into a free Claude skill with a guided setup wizard, ingest, query, and lint commands -- works across Claude Code, Codex, Gemini CLI, and more. One-click install, no coding required.

* The system runs on three tiers: raw (brain dump), wiki (AI-organized knowledge base), and outputs (answers from querying). Drop files into raw, run ingest, and the AI maps everything into structured wiki entries with relationship graphs.

* You can automate ingestion using Claude Code's loop feature so the vault stays current without manual work. Pair with Obsidian's paid sync tier and a note captured on your phone is indexed before you're back at your desk.

* The lint command health-checks your wiki for outdated entries and missing connections -- and tells you exactly what to clip next to close the gaps. The wiki tells you what it doesn't know yet.

* Day zero this thing is basic. Day 90 it's a company asset no competitor can copy. Your private knowledge base is the foundation for every agent and skill you build -- and nobody else will have it.

Join the Build With AI community - weekly AI implementations, live coaching, and templates built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about

FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

FIND NICK ON SOCIAL

X: https://x.com/NickSpisak_

LinkedIn: https://www.linkedin.com/in/nicholasspisak/

YouTube: https://www.youtube.com/@nickspisak_

Perplexity Computer Masterclass for Beginners (full tutorial)03 Apr 202600:46:19

Eliot Prince is an SEO specialist with 10+ years of experience ranking businesses at the top of Google. He's now deep in the AI world, coaching businesses on how to do SEO faster and better using AI tools. In this episode, Eliot walks through how he's using Perplexity Computer to build repeatable SEO machines — systems that audit websites, generate deliverables, and even push changes live to WordPress, all from a single conversation.

We run a live audit on ReturnMyTime.com, watch three audit modules execute in parallel, and dig into the results — competitive analysis, keyword gaps, technical fixes, and auto-generated page copy. Eliot also demos a LinkedIn lead machine he built that reads DMs, scores leads, and drafts replies automatically using Perplexity's Linkup API connector.

The big takeaway: Perplexity Computer runs 19 LLM agents in the cloud simultaneously, meaning you can build systems that would traditionally take weeks of manual work or expensive SEO tool subscriptions - and you don't need to write a single line of code to do it.

Find Eliot YouTube's channel here:@princeeliot

Join the Build With AI community here: https://www.skool.com/buildwithai/about

I Replaced an 8-Person Marketing Team With Claude Code (full tutorial)01 Apr 202601:12:01

James Dickerson (AKA The Boring Marketer) has been consulting businesses on marketing and growth since 2012 — and he's now using Claude Code to do what used to require a $5-10K/month agency. In this episode, James goes screen-share and builds a complete marketing funnel live from scratch: a landing page, a quiz funnel, a 14-day email nurture sequence, and dozens of social and SEO content assets — all inside Claude Code with zero coding.

 

We break down the psychology behind high-converting email sequences (micro commitments, reciprocity, objection handling), how James's "skills" system encodes expert marketing knowledge into portable AI instruction files, and why anyone with these tools can immediately outperform 80% of marketers. If you've been procrastinating on Claude Code, this is your sign to just download an IDE and start.

X: https://x.com/BoringMarketer
Website: https://vibemarketer.com

Youtube: @theboringmarketer


How to Set Up OpenClaw in 7 Minutes (Step-by-Step Guide)27 Mar 202600:07:08

Grab the free one-page OpenClaw setup guide with every step and command listed out: https://corey-ganim.kit.com/c93f43577e

I walk through the complete OpenClaw setup process from zero to a working AI agent connected to Telegram — all in under seven minutes. You'll see every step: running the installer, configuring your Anthropic API key, creating a Telegram bot through BotFather, pairing it to your OpenClaw instance, and enabling web search with DuckDuckGo. One prerequisite, one terminal command, and you're live.

Key Takeaways:

  • OpenClaw installs with a single terminal command — the only prerequisite is having Node.js installed, which is also a one-command setup
  • The guided onboarding handles every configuration decision (model, API key, channel, search) through simple yes/no prompts — no manual config files
  • Creating a Telegram bot through BotFather takes about 60 seconds: message BotFather, run /newbot, choose a name ending in "bot," and copy the token
  • DuckDuckGo is the fastest search provider to start with because it requires zero additional API keys or setup
  • Skills and hooks can be added after the initial install — you don't need to configure everything before getting your agent running
  • The OpenClaw control panel gives you a browser-based chat window plus access to channels, sessions, usage stats, cron jobs, files, skills, and nodes

Timestamps:

00:00 - Introduction 

00:02 - Running the OpenClaw installer from the terminal 00:30 - Node.js prerequisite (quick install)

00:45 - Guided onboarding: Quick Start setup 

01:05 - Choosing Anthropic as your model provider 

01:20 - Entering your Anthropic API key 

01:35 - Selecting Claude Sonnet 4.6 

01:52 - Creating a Telegram bot with BotFather 

02:45 - Naming your bot and choosing a username 

03:15 - Connecting the bot token to OpenClaw 

03:30 - Enabling DuckDuckGo web search 

03:45 - Skipping skills and hooks (configurable later) 

04:06 - OpenClaw control panel overview 

04:30 - First chat with your bot in the browser 

05:15 - Pairing the bot with your Telegram account 

06:10 - First Telegram message confirmed 

06:30 - Setup complete — next steps for personalization

Links Mentioned:

Enjoyed this episode?

-> Subscribe and leave a review 

-> Join the community waitlist: https://return-my-time.kit.com/1bd2720397

Automate Social Media with AI: How I Post Content 100% On Autopilot (full guide)25 Mar 202600:30:49

What if you could describe an automation in plain English and get a fully functional web app back in 15 minutes? In this episode, Kevin Fernando walks through exactly how he built a daily social media post generator using a tool called Appy. The agent researches trending stories in your niche every morning at 7 AM, writes platform-specific posts in your voice (not generic AI slop), generates properly sized images for each platform, and emails you the drafts. Kevin built it live, deployed it to the web, and even had Corey sign up and generate posts in real time during the episode. If you've been building automations in Make.com or N8N, this is the next evolution.

Guest Introduction

Kevin Fernando a 20-year entrepreneur, former head of marketing for multiple SaaS companies, e-commerce store builder/seller, and former agency owner (six years). Kevin now runs the Solopreneur YouTube channel where he teaches entrepreneurs how to get more leverage from AI tools and software without needing a team.

Perplexity Computer vs. Manus: Which One's Actually Better?20 Mar 202600:15:13

Corey puts two leading agentic AI tools head-to-head in a real-world showdown. He tests Perplexity Computer ($200/month) against Manus ($20/month) across three practical use cases: multi-source research with website deployment, connected app integrations with Google Workspace, and data collection with visualization. You'll see exactly how each tool performs on speed, accuracy, output quality, and which one earns Corey's recommendation for 2026.

Join the Build With AI community waitlist: https://return-my-time.kit.com/1bd2720397

• Perplexity Computer completed tasks 5-10x faster than Manus across most tests — finishing in 60 seconds what took Manus 10 minutes 

• Both tools nailed data accuracy when researching AI startup funding, pulling identical figures from TechCrunch 

• Perplexity's Google Workspace integration produced cleaner, properly formatted deliverables (tables, headers, structured docs) while Manus output jumbled text

• For website deployment, Manus actually had slightly better UI design — but both successfully created shareable public URLs 

• When stuck, Perplexity self-corrected and found the data; it recovered gracefully from errors 

• ClickUp was recommended by both tools as best value for project management pricing ($12/user/month for Business plan) 

• Perplexity Computer wins overall for speed, output quality, and cleaner UI despite the 10x higher price tag

Timestamps:

00:00 - Introduction and test overview 

00:30 - Pricing comparison ($200 vs $20 plans) 

01:00 - Test 1: Multi-source research + website deployment

14:04 - Test 1 results: Speed comparison (2 min vs 10 min)

16:25 - Website design comparison

18:30 - Test 2: Gmail + Calendar + Google Docs integration

27:14 - Test 2 results: Output quality comparison 

29:40 - Perplexity's formatted table vs Manus' jumbled text 32:00 - Test 3: Data collection, analysis, and visualization 39:30 - Test 3 results: Bar charts and pricing spreadsheets 41:52 - Final verdict and recommendation

Links Mentioned:

• Perplexity Computer: https://perplexity.ai/

• Manus: https://manus.im/

I Built A $100K Research Assistant With Claude Code (for FREE)18 Mar 202600:53:39

What if you could go from a blank folder to a fully functional competitive research tool complete with scoring rubrics, interactive dashboards, and repeatable skills—in under an hour? In this episode, marketing veteran Adam Sandler (yes, that's his real name) shares his screen and builds the entire workflow live using a real-world use case: finding distressed wedding venues in North Carolina for a friend's acquisition business. No coding. No technical background. Just Claude Code, plain English, and a process that any knowledge worker can replicate.

Check Adam's youtube channel:https://www.youtube.com/@ViableEdge

I built an AI agent finance department (full build)27 May 202600:43:44
I brought on Mike Dion, a senior corporate finance professional who has helped automate more than 100,000 hours of work out of finance processes, to walk through how to build a fully functional AI agent finance department inside N8n — from scratch, with no coding background required. We build a CFO agent named Charles, give him a team of specialist sub-agents (FP&A, Accounting, and Treasury), and watch the delegation logic in action as Charles routes questions to the right specialist instead of answering everything himself. Mike also breaks down how to use ChatGPT to write your own system prompts, why you should give the CFO a reasoning model while using cheaper models for the sub-agents, and how to publish the finished chat so your whole team can access it. By the end of this episode, you'll have everything you need to replicate this AI finance department in under 45 minutes. Timestamps 00:00 – Intro 00:03 – What we're building: AI CFO inside N8n 00:23 – Mike's background and 100,000 hours of automation 00:52 – Why N8n over Make, Zapier, or Power Automate 02:00 – Setting up the chat trigger and naming the CFO 05:00 – Using ChatGPT to write the CFO system prompt 08:52 – Choosing the right AI model and saving on token costs 13:27 – Building the FP&A sub-agent (and what FP&A actually does) 16:36 – Adding the Accounting agent with code interpreter 19:25 – Building the Treasury agent 33:21 – Successful routing to FP&A and Treasury agents 38:19 – Publishing the chat and embedding it in Slack, Teams, or a website 39:22 – Mike's philosophy: train your team to build, don't just build for them 41:14 – Where to find Mike and his free Finance Automation Insider newsletter Key Points Using ChatGPT to write your own N8n system prompts is one of the fastest ways to get started — nothing knows ChatGPT better than ChatGPT itself, and what would have taken six hours of writing two years ago now takes minutes. The delegation logic is non-negotiable. If the CFO answers questions directly instead of routing them to a specialist, you lose access to any tools or context you've connected to those specialist agents — and you pay more for it. N8n can run completely free on a $4–5/month virtual private server, making this entire AI finance department buildable for nearly zero cost. You don't need a paid automation platform subscription. Setting the context window to 10 (five back-and-forth interactions) is a practical default — enough for most finance questions without ballooning your API costs on every run. You can publish the finished CFO chat and embed it directly in Slack, Microsoft Teams, or a company website. Your team sees a clean chat interface — all the N8n complexity stays invisible in the background. Links: F9 Finance YouTube channel — Mike's free weekly channel covering finance automation tools and builds: https://www.youtube.com/@F9Finance F9 Finance website — corporate automation training and the free Finance Automation Insider newsletter (includes 15 five-minute finance automations you can build with tools you already have): https://f9finance.com N8n — the free, self-hostable workflow automation tool used to build the AI CFO in this episode: https://n8n.io Join the Build With AI community — weekly AI implementations, live coaching, and no-fluff templates built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show. FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim FIND MIKE ON SOCIAL YouTube: https://www.youtube.com/@F9Finance Website: https://f9finance.com
OpenClaw Masterclass for Beginners (full tutorial)13 Mar 202600:32:25

Nick Spisak, a 15-year software veteran turned AI entrepreneur, walks through the complete OpenClaw setup for non-technical users. You'll learn how to install your first instance, give it skills that read documentation for you, and troubleshoot any issue using natural language. Nick even gives away his "OpenClaw Prime" skill that turns any coding agent into an OpenClaw expert, plus a visual step-by-step diagram.

• OpenClaw Prime Skill: https://corey-ganim.kit.com/f1f13dee60

• Excalidraw Setup Diagram: https://corey-ganim.kit.com/ab1cc7ab21

Key Takeaways:

• Build a skill that reads the docs so you don't have to. Nick's "OpenClaw Prime" skill makes Claude Code or Codex an instant OpenClaw expert.

• Troubleshooting works 100% of the time. Point your coding agent at your OpenClaw files, describe the issue in plain English, and let it fix itself.

• Skills are portable across models. Write it once for Codex, ask AI to convert it for Claude Code or Gemini.

• Spend 90% of your time in planning mode. Use Shift+Tab to enter plan mode and remove assumptions before execution.

• Real business use case: AI receptionist. Set up OpenClaw on WhatsApp to respond to leads while you're on a job site. One extra $10K roofing lead pays for the whole system.

• Telegram is the easiest platform to connect. Message the Bot Father, get your token, plug it into OpenClaw.

• Customize your agent's personality via the Soul file. Make it concise, opinionated, and aligned with how you work.

Timestamps:

00:00 - Introduction and what you'll learn

01:02 - Using Claude Cowork + Excalidraw for planning

03:46 - WhisperFlow: talk to your terminal with natural language

06:30 - OpenClaw Prime skill explained

08:41 - Why skills teach AI to "fish" (not just follow tutorials)

11:02 - Live troubleshooting demo: bringing Annie back online

13:44 - Claude Code vs Codex (skills are portable)

16:44 - Planning vs execution mode (the 90/10 rule)

19:21 - Real business use cases: AI receptionist for contractors

23:28 - 100% success rate troubleshooting (even with no code experience)

25:13 - Walkthrough of the Excalidraw setup diagram

27:16 - Setting up Telegram (easiest platform)

28:51 - Soul file and agent identity customization

30:26 - Wrap up and where to get free resources

Links & Resources Mentioned:

• OpenClaw Docs: https://docs.openclaw.ai

• Claude Cowork: https://claude.ai

• WhisperFlow: https://whisperflow.com

• Ghost TTY (Terminal): https://ghostty.org

Enjoyed this episode?

→ Subscribe and leave a review to help others discover the show

→ Join the Build with AI Community waitlist: https://return-my-time.kit.com/1bd2720397

Learn Zapier in 30 minutes: AI Agent Automation Tutorial For Beginners (2026)11 Mar 202600:30:53

Tom Nassr, co-founder and CEO of X-Ray, walks us through building a Zapier Agent from scratch in under 10 minutes. He demonstrates a practical use case: creating an AI agent that scans Gmail for specific emails and delivers a weekly summary to Slack. You'll learn the key difference between Zapier Agents and traditional Zaps, when to use each, and how to think about deterministic vs. non-deterministic automation.


Check Tom's youtube channel: https://youtube.com/@xrayautomation

Resources Mentioned:

• Zapier: https://zapier.com/

• X-Ray Website: https://xray.tech/

• X-Ray Search Tool (free): https://search.xray.tech/

Claude Cowork vs. Perplexity Computer - Which One's Actually Better?06 Mar 202600:18:08

In this episode I put two of the hottest AI agent tools head-to-head: Perplexity Computer ($200/mo) vs. Claude Cowork ($20/mo). After running both through three identical real-world tasks, he reveals which tool delivers better outputs, which one goes above and beyond, and whether the 10x price difference is actually justified. Spoiler: the winner might surprise you.

Grab the Google doc with the 3 test cases + full prompts here: https://return-my-time.kit.com/389d61df6a

Tools Mentioned:

• Perplexity Computer (Max plan): $200/mo - perplexity.ai

• Claude Cowork (Pro plan): $20/mo - claude.ai

• Zoho Invoice: zoho.com/invoice

• Invoice Ninja: invoiceninja.com

• Invoice Sherpa: invoicesherpa.com

How I Built An AI Marketing Team With Claude Code (full tutorial)04 Mar 202601:01:26

Craig Hewitt, founder of the 7-figure SaaS Castos, breaks down how he uses Claude Code to run his entire content marketing operation. Despite not being a developer, Craig built his first Claude Code project in 45 minutes while waiting outside his son's basketball practice. In this episode, he walks through the exact system he uses, demonstrates live builds, and shares his free, open-source SEO Machine project that anyone can download and use today.

YouTube: youtube.com/@thecraighewitt

Learn 80% of NotebookLM in 20 Minutes (Features Most People Miss)25 Feb 202600:37:29

Paul Noon ( aka The AI Professor) joins the show to give a full under-the-hood walkthrough of Google's NotebookLM.

 Paul's been using this tool daily in his business and personal life, and he breaks down exactly how it works, why it's different from ChatGPT or Gemini, and the real-world use cases that make it a must-have for any business owner. The best part? It's completely free.

This episode was inspired by Paul's viral "Top 25 NotebookLM Tips" video on YouTube — this is the deeper dive.

Check Paul’s YouTube channel: https://www.youtube.com/@TheProfessor-AI

How to Build a Website AI Agent That Books Demos While You Sleep (Free n8n Blueprint)18 Feb 202600:23:22

In this episode, Corey talks with AI automation strategist Ashley Gross about how businesses can build an AI agent that engages website visitors, answers questions, and books demos around the clock. Ashley walks through the workflow behind her own implementation — from capturing conversation data to syncing with CRM tools — and shares how automation helped her reclaim time and tie AI initiatives directly to revenue.

They discuss practical ways small business owners can start using AI, including training agents on SOPs, integrating with existing tech stacks, and focusing on high-impact use cases first. The conversation also explores common mistakes to avoid, such as overwhelming agents with too much data, and how AI insights can inform content and marketing strategy.

Grab Ashley's plug-and-play n8n blueprint free → https://return-my-time.kit.com/6e041f7506

The Only 6 AI Tools You Need In 2026 (Full Walkthrough)11 Feb 202600:28:25

Ryan Doser breaks down the AI tools he actually uses daily after testing hundreds of options. With 10+ years in marketing and 31,000+ YouTube subscribers, Ryan cuts through the noise to share what's worth your time and why 95% of AI tools are just white-labeled wrappers you don't need.

Check Ryan's you tube channel https://www.youtube.com/@RyanDoserAI

Claude Cowork Masteclass for Beginners (full tutorial)04 Feb 202600:42:23

Mark Kashef joins the show to demo Claude Cowork and break down how "skills" work compressed, reusable knowledge that Claude can invoke just-in-time without bloating your context window. We watch him build a PowerPoint presentation live using multiple AI agents and discuss how to get started with this powerful new tool.Mark Kashef joins the show to demo Claude Cowork and break down how "skills" work compressed, reusable knowledge that Claude can invoke just-in-time without bloating your context window. We watch him build a PowerPoint presentation live using multiple AI agents and discuss how to get started with this powerful new tool.

YouTube: @Mark_Kashef

How to Sell An AI App for $200K: 6 steps (full playbook)30 Jan 202600:34:05

 

In this conversation, Ritesh Verma shares his journey of building an AI app that garnered a $200,000 acquisition offer. He discusses his background in tech, the process of developing the app, understanding market needs, and the strategies he employed for customer acquisition and scaling the business. Ritesh emphasizes the importance of referrals, the app's value proposition for users, and provides insights into the acquisition process, highlighting the potential for lucrative outcomes in the software market.

Take a look at Ritesh’s YouTube channel here: https://www.youtube.com/@rkumarv

 

 

Manus AI: Build Your Automated Research Machine21 Jan 202600:35:17

Alex Cinovoj grew his LinkedIn following from 500 to 33,000 in under 10 months—not by posting more, but by building smarter systems. In this hands-on episode, Alex shares his screen and walks through the exact Manus workflow he uses to wake up every morning with a curated industry report ready to turn into content.

We also dig into his experience deploying 47 AI agents (half of which failed), why PDF-format content outperforms on LinkedIn, and his advice for overwhelmed business owners who don't know where to start with AI.

If you want to see how someone actually builds and tests AI solutions in production—not just talks about them—this episode is for you.

LinkedIn: Alex Cinovoj

 

AI agent focus groups are the future of marketing19 May 202600:50:24

I sat down with Justin Brooke, a 20-year advertising veteran who turned a $60 Google Ads campaign into a seven-figure agency — and then built an AI-powered prediction system that has since generated $260,000 for him personally. In this episode, Justin walks through his "predictive wear" framework: a multi-agent workflow that runs your ad copy and sales pages through a synthetic focus group of 13 detailed AI personas before a single dollar is spent on ads. We break down how the workflow is built in Mind Studio, why persona quality makes or breaks accuracy, and how Harvard, Stanford, and the New York Times have all validated this exact approach. By the end of this episode, you'll understand why running your marketing through a virtual focus group before it goes out the door may be the single highest-ROI move you can make right now.

Timestamps
03:29 – What "predictive wear" is and why Justin built it
05:00 – Why you need multiple personas, not just one
08:00 – How the 13-persona focus group workflow runs
09:00 – The prediction engine: picking the winning ad variation
10:00 – Harvard, Stanford, and the New York Times validate the method
13:15 – The ROI: $260K personally, 4 to 6X ROAS for clients
19:00 – What makes a persona accurate: the 1,400-word dossier
24:04 – The copywriter prompt and "embody" vs. "pretend to be"
33:00 – Sales page version: PDF upload and yes/no buyer scoring
41:00 – Why some personas are successful and others are struggling
45:00 – A $36,000 offer launched using this exact process
48:00 – Final advice: do the work on the persona quality

Key Points

The old way of advertising is learning by spending money — you write copy, run ads, and find out if it works after the budget is gone. Justin's predictive wear system flips this by running copy through a synthetic focus group of 13 AI personas before any ad spend, so you know what will convert before you go live.

Harvard, Stanford, and the New York Times have all independently validated this approach. The New York Times uses the same synthetic audience process to test headlines and found 92% accuracy compared to their human focus groups — meaning this is not a fringe experiment, it is becoming standard practice for major publishers and brands.

The cost is 13 to 20 cents per run. A top 1% copywriter charges $100 to $500 per ad. Justin's workflow produces three optimized variations in about 10 minutes for 13 cents, performs at or near the level of the best human copywriters for most use cases, and allows unlimited iteration — you run it until the copy converts.

The system is also a copywriting trainer. Even with 20 years of experience, Justin says the feedback regularly surfaces blind spots and teaches him better approaches.


Anyone can use this, not just expert copywriters. Because the workflow takes whatever you input — even a bad ad — and improves it based on real persona feedback, non-copywriters like a front-desk employee or a local business owner can now produce top-10% ad copy without prior training.

Join the Build With AI community built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.

FIND ME ON SOCIAL
X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim

FIND JUSTIN ON SOCIAL
https://x.com/IMJustinBrooke
Website: https://adskills.com

How to Position Your Business to Be Discoverable by AI14 Jan 202600:40:06

Brien Gearin breaks down the fundamental shift happening in local search: it's no longer about optimizing for Google—it's about building credibility signals that AI can actually find and trust.

If your business isn't showing up when people ask ChatGPT or Claude for recommendations in your area, this episode explains exactly why (and what to do about it).

Check Brien Gearing LinkedIn: Brien Gearin | LinkedIn

How to turn Customers into zealots for your brand with AI + Primal Branding07 Jan 202600:42:50

Most entrepreneurs think branding is a logo and a website. They're wrong.

Patrick Hanlon, author of Primal Branding, breaks down the actual framework for building brands that create communities of fanatics—not just customers who'll ghost you for the next competitor.

This is the 20th anniversary of Primal Branding, and the framework is more relevant today than when it was first published in 2006. We dig into the seven pieces of primal code, why having haters is actually essential to your brand, and how AI amplifies (but can't replace) human creativity in branding.

If you're building something and want people who defend your brand instead of just buying from you, this conversation gives you the exact system.

Explore Patrick’s book here: https://www.amazon.com/dp/1451655312

 

Steve Rolle - From Military to $50M Soap Empire (And Why AI Changes Everything)31 Dec 202500:56:47

Steve Rolle went from civil engineering in the military to building a $50 million hospitality soap business—then sold it, became CEO of the merged company, and is now launching the next generation of hotel amenities with AI at the core. This conversation breaks down how he's using AI to disrupt an industry still running on fax machines, his framework for building businesses that operate without you, and his bold predictions about the future of work, robotics, and business margins.

Steve’s YouTube channel is @rollewithsteve.

this AI-powered marketing strategy to 10x your business in 202624 Dec 202500:29:27

In this episode, I'm pulling back the curtain on my entire 2026 marketing strategy—a flywheel system designed to ethically "steal" other people's audiences to grow your own. The best part? It runs on a stack of five completely free AI tools that automate most of the heavy lifting.

If you're a time-strapped solopreneur tired of shouting into the void on social media, this strategy will show you how to leverage collaboration and strategic partnerships to explode your reach and authority in your niche.

Test your AI knowledge in under 60 seconds — take the assessment at ReturnMyTime.com/quiz

 

STOP trying to automate everything...start here instead17 Dec 202500:26:26

In this episode, I breaks down a real AI Tools Assessment completed for a local realtor, revealing the exact decision-making framework I use to prescribe AI solutions that actually get used. This isn't another "top 10 AI tools" video - it's a deep dive into the judgment calls that separate successful AI implementation from expensive tech graveyard additions.

Vsit www.returnmytime.com/quiz to get a personalized AI action plan designed to level up your AI knowledge in as little as 60 seconds.

 

 

The 4 Levels of AI Mastery (And How to Reach Level 3 in 90 Days)10 Dec 202500:36:49

95% of entrepreneurs are stuck at level one of AI mastery. In this episode, I break down the four distinct levels of AI expertise and provides a practical 90-day roadmap to reach level three—even if you're starting from scratch. This isn't about theory or hype. It's about building real, valuable skills that separate you from your competition.

Build Your AI Brain in 15 Minutes (Claude Context Profiles Tutorial)03 Dec 202500:36:42

Tired of starting from scratch every time you use AI? In this episode, I walk you through exactly how to build a context profile—a structured knowledge package that teaches AI who you are, how you communicate, and the nuances of your work. No more generic outputs, no more repeating yourself. Just tailored responses every single time.

 

Download the free Context Profile Prompt in this link : https://corey-ganim.kit.com/7ae85c5bdf

 

 

The $50k/month passive income roadmap (4 pillars)26 Nov 202500:34:51

In this episode, I break down my complete strategy for achieving $50,000 per month in passive income by my 35th birthday (March 27, 2030).  I reveal my "Four Pillars" business ecosystem designed to make this astronomically ambitious goal not just possible, but extremely likely.

 

Grab the drawing shared in the screenshare here.

 

https://excalidraw.com/#json=y6K62GW7os9IqjxBo-JWO,1hW8aJ-yCAlKK_FcX2E3mA

3 ways to make recurring revenue with AI19 Nov 202500:33:41

W Gu est Nick Spisak shares his insights on automation, recurring revenue opportunities with AI, and how everyday entrepreneurs can get started without getting overwhelmed.

If you’re interested in the AI Assessment that Corey mentions, please email Corey@coreyganim.com

Follow Nick on X @NickSpisak_

AI Basics Masterclass | The Corey Ganim Show13 Nov 202501:11:59

In this special episode, Corey delivers an AI Basics Masterclass to Carl's mastermind group. This is a departure from the typical interview format, featuring Corey as the expert presenter teaching actionable AI implementation strategies for small business owners and entrepreneurs. The session covers everything from beginner-friendly tools to advanced automation workflows, with a focus on practical, immediately usable tactics.Download the presentation slides (mentioned in episode): Link: https://corey-ganim.kit.com/78de3e7562

 

Check out Karl's website: successwithkarl.com"

I BLEW UP Instagram With AI Content (4M Views in 30 Days)15 May 202600:32:44
I sat down with Nick Puru to break down the exact Claude Code setup he used to pull 4 million views and ~6,000 newsletter signups in the last 30-45 days for his AI consultancy. Nick walks through his short-form content factory inside Claude Code — the CLAUDE.md "brain," his ICP file (an avatar he calls Patrick), his foundations doc full of algorithm lessons like "negativity always wins," and the three skills he uses to write captions, generate scripts, and review them. We get into how he tests three hooks per video with Instagram trial reels, the humanizer skill from Bader on GitHub that strips out AI tells like em-dashes and "it's not X, it's Y," and why he treats every Claude project like onboarding a new employee. By the end of this episode, you'll have a clear blueprint for building your own short-form content system in Claude Code — starting from a single CLAUDE.md file and expanding from there. Timestamps 00:00 – Intro 00:37 – 4 million views in 30 days 01:53 – Reels to ManyChat to newsletter funnel 03:31 – Tour of the Claude Code folder structure 05:02 – How the write script command works 06:29 – Why human-in-the-loop matters for content 07:38 – Inside the CLAUDE.md brain file 08:11 – Meet Patrick, Nick's ICP avatar 10:04 – Foundations file and "negativity always wins" 13:43 – Live generating a Claude Cowork script 15:44 – Testing three hooks with Instagram trial reels 18:48 – Most bare-bones version to start with 22:36 – Why ICP and brand voice are foundational 24:28 – The humanizer skill from Bader on GitHub 27:01 – Treating AI like a new employee 29:35 – Context beats prompting in 2026 31:13 – Where to find Nick Key Points Nick's short-form system drove ~4M views in 30 days and ~6,000 newsletter signups in 45 days for his AI consultancy — every video CTA pushes a lead magnet via a ManyChat flow that collects emails and hands off to an appointment setter. The whole system lives inside Claude Code as three skills: one writes scripts, one reviews them against a quality checklist, and one generates captions. Trigger them by typing things like "write script" in the terminal. The CLAUDE.md file is the brain. It holds the output format, writing rules, key principles, and a pointer to an ICP file built around an avatar named Patrick — a small-to-mid market business owner ($few hundred K to $15M, 2-50 staff) who has tried ChatGPT once or twice but doesn't know Claude Code. One of Nick's foundations is "negativity always wins" — the algorithm rewards a stronger emotional charge, but he warns against using it on every video or audiences pick up on it. He calls it in only when the angle fits. He tests three different hooks on the same body and CTA using Instagram trial reels, treats it like A/B testing titles and thumbnails on YouTube, and feeds the winners back into the system as analytics context. To kill AI tells like em-dashes, bullet points, and "it's not X, it's Y," Nick runs scripts through Bader's humanizer skill from GitHub. Corey adds a similar instruction in his agents.md to never use dashes. Treat Claude like a new employee, not a magic box. You wouldn't expect a hire to crush it on day one — you'd give them SOPs, business context, your website, and an ICP. Same playbook for building any Claude project, whether it's short-form, long-form, or LinkedIn posts. Bader's humanizer skill on GitHub - https://github.com/bader-research ManyChat for Instagram DM automation - https://manychat.com FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim FIND NICK ON SOCIAL YouTube: https://www.youtube.com/@nickpuru X: https://x.com/nickpuru LinkedIn: https://www.linkedin.com/in/nicholas-puruczky-113818198/
How I Built an AI Voice Agent With Claude + Voiceflow (Zero Code)12 May 202600:59:14
Build your voice agent in 10 minutes (No code required) https://corey-ganim.kit.com/18da152cf4 In this episode, I sat down with Susan Westwater, co-founder of Pragmatic Digital and a conversational AI veteran since 2017, to build a working voice agent in Voiceflow live, with zero code. Susan walks through her exact prompt template for an appointment-scheduling agent, explains the difference between in-the-loop, on-the-loop, and fully autonomous agents, and shows how to separate your agent instructions from your knowledge base so you can update facts without breaking the whole build. We test the agent live (it called her cell phone mid-episode), connect it to a Google Sheet to capture customer intake, and talk about competitors like VAPI, ElevenLabs, and Voiceify. By the end, you'll have the exact playbook (and the template Susan is giving away) to spin up your own MVP voice agent in under an hour. Timestamps 03:42 – Inside Voiceflow and what makes it different 04:23 – Chatbot vs voice agent: listen, decide, act 05:30 – In the loop vs on the loop vs fully autonomous 09:09 – The system prompt: identity, purpose, and boundaries 11:54 – Voice, persona, and speech sculpting 13:22 – Separating agent instructions from knowledge base 17:14 – Stopping the agent from troubleshooting electrical issues 20:31 – Rules for collecting info one question at a time 23:21 – Pasting the prompt and one-shotting the build 26:34 – Voiceflow competitors: VAPI, ElevenLabs, Voiceify 30:22 – Connecting tools at each conversation step 33:13 – Why faster builds give up control 38:21 – Adding the knowledge base as a Word doc 43:13 – Sending customer intake to a Google Sheet 45:57 – Live phone call with the voice agent 50:09 – Branching, exit conditions, and iteration 54:52 – Custom voices, ElevenLabs integration, and voice security Key Points Keep two documents separate: agent instructions (how the agent behaves, its identity, persona, escalation rules) and knowledge base (the facts about your business). If pricing or hours change, you update one cell in your knowledge base instead of digging through a giant system prompt. The strength of a Voiceflow build lives in the prompt. Susan pastes her full instructions doc into the new project prompt and Voiceflow generates the entire conversation flow — greeting, qualification, intake, confirmation, escalation — with no coding. Be explicit about what the agent does NOT do. LLMs are trying to "win the game" (Susan's War Games analogy), so if you don't tell the electrical-appointment bot "do not troubleshoot," it will try to problem-solve its way out of every conversation. Collect intake one question at a time, use explicit confirmation on critical fields like callback numbers, and tell the agent to be empathetic but not apologetic — nobody wants a bot that says "I'm sorry" five times instead of solving the problem. Voiceflow — https://www.voiceflow.com Pragmatic Digital — Susan's agency helping brands operationalize conversational AI and applied AI for CX - https://www.pragmatic.digital VAPI — alternative voice agent platform - https://vapi.ai ElevenLabs - https://elevenlabs.io Voiceify — centralized library for chatbot, voice agent, and telephone deployments across web and mobile - https://voicify.com/ Twilio — phone number and telephony layer for connecting Voiceflow agents to real phone calls - https://www.twilio.com Make.com — automation platform that can connect to Voiceflow as a tool integration - https://www.make.com Robert Scoble on X https://x.com/Scobleizer Brian Roemmele on X https://x.com/BrianRoemmele FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim FIND SUSAN ON SOCIAL X: https://x.com/sjw75 Website: https://www.pragmatic.digital
I Built the ULTIMATE AI Second Brain (Karpathy's LLM Wiki Setup Guide)08 May 202600:18:41

🔗 Deploy your own Hermes agent on Hostinger -10% off any plan with code COREY10: http://hostinger.com/corey10 (use code COREY10)

Grab the free step-by-step Hermes Second Brain setup guide here: https://corey-ganim.kit.com/60fc0fe6d9


In this solo episode, I walk through exactly how I built the ultimate AI second brain using Hermes and its built-in LLM Wiki skill — inspired by Karpathy's wiki setup. I break down the three core operations of the Hermes agent (ingest, query, lint), the three layers of the knowledge base (raw sources, the wiki, schema/tags), and why I chose Hermes over Claude Code, OpenClaw, or Obsidian for this build. From there, I show the full one-click deploy on a Hostinger VPS, the OpenAI model setup, the Telegram bot integration via BotFather, and the Markdownload Chrome extension trick I use to feed any tweet, article, or webpage straight into the wiki. By the end of this episode, you'll have a clear, step-by-step path to deploy your own self-improving second brain that gets smarter the more you use it.

Key Points

Hermes ships with a built-in LLM Wiki skill that handles the second brain function out of the box — your job is to curate sources, the agent's job is to summarize, tag, and file them away.

The knowledge base has exactly three layers: raw sources you give it (read-only), the agent-owned wiki of markdown files, and the schema/tags Hermes builds to make querying low-friction.

Run the Lint command roughly once a month — it audits your wiki for contradictions, sources older than 90 days, and oversized files that should be split for more accurate retrieval.

Deploy on a Hostinger VPS instead of locally — it's a one-click install with no terminal, cheaper than a Mac mini, always-on, and your data stays private.

The simplest workflow for feeding the wiki: use the Markdownload Chrome extension to clip any tweet, article, or webpage to markdown, drag it into your Telegram chat with Hermes, and tell it to add it to the wiki.

This is a compounding asset — on day 1 the knowledge base is the dumbest it'll ever be, but feed it consistently and by day 90 it becomes incredibly useful for retrieval.

Hermes agent VPS deployment on Hostinger (use code COREY10 for 10% off) - https://www.hostinger.com/vps/hermes-agent-hosting

Markdownload Chrome extension - https://chromewebstore.google.com/detail/markdownload-markdown-web/pcmpcfapbekmbjjkdalcgopdkipoggdi

Telegram BotFather - https://t.me/BotFather

OpenAI Codex - https://openai.com/codex

FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim


Cracking the X algorithm with Claude Code05 May 202600:57:29

Tom Crawshaw (8+ years in automations, $25M+ in attributed e-com revenue) cracks open the content system that's pulled him millions of views. We walk through the Claude Code skill he built that handles voice profile, copywriting principles, hook scoring, image prompts, and a humanizer pass from one slash command. He also surfaces a hidden Claude Code feature called /insights that audits your full usage history and tells you what to build next. You'll learn how to turn messy ChatGPT workflows into a real skill, why Whisperflow is non-negotiable, and the one slash command 99% of Claude Code users are sleeping on.

Timestamps

00:00 Intro

00:30 Tom's automation background

03:30 Skills vs. Projects on context

08:30 Auto-updating voice profile from X

11:00 Nano Banana plus Canva workflow

23:30 Live demo: a Whisperflow post

34:30 Hook scoring with copywriting principles

46:30 The hidden /insights command

54:30 Skills vs. n8n vs. Lovable

Key Points

Skills beat Claude Projects on context. Projects load every reference file on every message. A skill works like a book: Claude pulls only the chapter it needs, so a full pipeline runs in one chat.

Tom's skill auto-updates his voice profile weekly. The X API pulls his last 7 days of posts, ranks by engagement, and rewrites the profile so the skill keeps drifting toward what's working.

/insights is the most slept-on feature in Claude Code. It audits your full session history and hands back a real report: what's working, where you're breaking your own rules, skills to build, and prompts to run.

Image gen is 80% Nano Banana, 20% Canva. Generate fast in the AI tool, then finish in Canva with magic grab and magic erase.

Whisperflow changed how Tom and Corey think, not just type. Speaking forces tighter thinking and makes prompts richer because adding context costs almost nothing.

Links

Claude Code: https://www.anthropic.com/claude-code

Whisperflow: https://wisprflow.ai/

Nano Banana: https://gemini.google.com/

Canva: https://www.canva.com/

n8n: https://n8n.io/

Tom's site: https://learnn8nautomation.com/

Build With AI: https://www.skool.com/buildwithai/about

FIND ME ON SOCIAL

X: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

TOM ON SOCIAL

X: https://x.com/TomCrawshaw01

YouTube: https://www.youtube.com/@TheAIGrowthLab

Website: https://learnn8nautomation.com/

How I'm AI-maxxing boomer businesses to make f*ck you money29 Apr 202600:36:13
Free audit template Corey is giving away — https://audittemplate.ai In this episode, I sat down with Chris Koerner and outlined how I sell AI assessments to small businesses. Timestamps 00:00 – Intro 00:33 – The $1,000 AI audit pitch 01:10 – The lunch conversation that started it all 02:23 – Why 99 out of 100 owners need this 02:57 – Why Loom screen recording failed 04:25 – From Zoom calls to a voice agent 05:31 – Meet Annie, the AI interviewer 06:17 – Live demo of the voice agent 08:06 – How the voice agent was built (Retell + skills) 10:18 – Walking through a real assessment in Gamma 12:00 – The effort vs impact matrix 13:00 – Wedding venue saves 8 hours with Dash This 15:16 – Pricing journey: free to $1,000 17:30 – Why charging more makes upsells easier 18:02 – The full upsell menu breakdown 22:00 – Custom GPT knowledge system for a business broker 24:46 – Which industries this works best for 25:53 – Seven ways to find clients with no followers 26:39 – Hosting a local AI meetup 27:30 – Door-knocking businesses in 2026 29:25 – Using free audits to land warm contacts 30:30 – Running free AI office hours 31:30 – Hard-won lessons and the speed-to-lead upsell 34:36 – The simple Claude prompt that builds the audit 35:33 – Where to find Corey Key Points The business started from one lunch where a friend said he'd pay $1,000 just to be followed around for a day. After validating with 50–100 owners, Corey found 99 out of 100 small business owners need this — they just don't know which AI tools to use. The upsell menu is built into the report. Common follow-ons: process optimization ($3K–$5K), Zapier or Make automation builds ($1K–$3K), custom GPT knowledge systems, CRM setups (high-level CRM at $3K–$5K), and speed-to-lead AI agents tied directly to revenue. The seven-way client acquisition playbook works with zero followers: host a local AI meetup on Luma or Meetup.com, door-knock local businesses, run free audits for your network, host free AI office hours at coworking spaces or realtor offices, partner with well-connected locals, and lean on warm intros from your CEO peer group. You don't need to be an AI expert. As Corey puts it, you just need to be one step ahead of your average client — which is about seven days of studying. The realtor's office where he hosted his free AI meetup turned into paying assessment work. The Claude prompt to generate an audit is dead simple: attach the transcript, tell Claude to find off-the-shelf tools that fix the pain points, and point it at directories like Futurepedia or There's An AI For That. FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim
EASY Claude Cowork Setup (full beginner tutorial)23 Apr 202600:26:52

In this solo episode, I walk through the exact process of setting up Claude Cowork from scratch — the right way — using the free Cowork Onboarding plugin I built and made open source. I go step by step through the full onboarding flow, from picking your workspace folder and connecting tools, to building three core context files (About Me, Brand Voice, and Working Style), generating global instructions that tie everything together, setting up scheduled tasks like a daily morning briefing and quarterly context review, and running an optional security review to lock in sensible rules.

Timestamps

00:00 – Why Cowork is useless out of the box

02:22 – Starting the onboarding flow from scratch

03:30 – Choosing workspace folder and onboarding path

04:37 – Workspace structure and file access permissions

05:45 – Connecting Google Workspace tools (Gmail, Drive, Calendar)

06:56 – Building context files: About Me, Brand Voice, Working Style

10:58 – Linking existing brand materials from Google Drive

12:44 – Generating global instructions from your context files

15:00 – Skills and plugin recommendations from the marketplace

17:24 – Setting up scheduled tasks: morning briefing and quarterly review

19:46 – Running the optional security review

23:23 – Wrapping up: what we built and the two manual steps left

Key Points

  • Most people skip the onboarding and then wonder why Cowork feels generic. The entire point of setting it up properly — building context files and global instructions — is so Claude never has to ask who you are again. Every session loads with that context automatically.
  • The three context files (About Me, Brand Voice, Working Style) are the foundation of the whole setup. Without them, Cowork is writing responses for a stranger. With them, it knows your business, how you communicate, and how you like your deliverables structured.
  • Global instructions are the piece most people miss. Once you paste your generated global instructions into Cowork's settings, every single session loads that context from the start — no repeating yourself, no re-explaining your preferences.

Links Mentioned

Free Cowork Onboarding plugin — download it to run the full guided setup described in this episode: https://return-my-time.kit.com/f00d78554c

Build with AI community — get the full onboarding plugin including the self-assessment, workflow audit, and custom skill blueprints tailored to your business: https://www.skool.com/buildwithai/about

WisprFlow — the talk-to-text tool used during the onboarding to answer Claude's questions faster: https://wisprflow.ai

Find Me on Social

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

Building an SEO business with Claude Code09 Jun 202600:37:01

I brought on Ryan Doser — a non-technical marketer with over a decade of experience who built a real-world Claude Code SEO workflow that's generated $5,000 in passive revenue in under two months — to show exactly how this works, step by step. We walk through two full demos: how Ryan repurposes YouTube videos into SEO-optimized blog posts automatically via a WordPress MCP connection, and how he vibe-coded an entire local service business website from scratch using Claude Code, Astro, GitHub, and Cloudflare — no developer required. He also shows us how he's running the same WordPress workflow for a paying client that's now showing up number one in Google AI overviews for national keywords. By the end of this episode, you'll know exactly how to do this yourself, how to sell it as a service to local businesses, and where Ryan's $99 Claude Code Skill Stack fits into the equation.

Skool Community: https://www.skool.com/aioperatoracademy/about


Timestamps

00:00 – Intro and what you'll take away 
00:33 – Does this require coding knowledge? 
01:12 – Demo 1: WordPress Claude Code SEO workflow 
03:26 – Who to sell this to (creators vs. B2B clients) 
05:50 – How the blog post auto-publishes to WordPress 
07:15 – Google Search Console results and $5K in passive revenue 
09:38 – Breakdown of the revenue timeline and digital product 
11:42 – Real client example: MedX Dental IT 
13:34 – AI search results and ranking #1 in Google AI overviews 
14:50 – How to price this as a service and prove ROI 
16:42 – Demo 2: Local service businesses as the target niche 
19:47 – The fake septic tank site ranking on page one 
22:00 – Building and deploying with Astro, GitHub, and Cloudflare 
27:35 – Why this model beats time-saving automations 
31:23 – Why SEO is evergreen and the long-term pitch to clients 
33:00 – Live deploy: blog post goes from Claude Code to live site 
34:14 – Wrap-up and where to find Ryan


Key Points

Ryan is a non-technical marketer — no coding background. He built this entire workflow as a regular person figuring it out, which means anyone watching can do the same thing. If the barrier felt technical before, that framing matters.


The WordPress workflow is fully hands-off after one prompt. Claude Code scrapes a YouTube transcript, pulls screenshots from the video, compresses and uploads images to WordPress, writes the blog post with proper H2/H3 structure, assigns a category, sets the featured image, writes the meta description, and publishes a draft — all without touching the CMS.


Ryan made over $5,000 passively from a $99 digital product, with roughly 80% of that revenue attributed directly to blog traffic from AI-repurposed YouTube videos. He implemented this in late February and the traffic didn't even start building until mid-April - so the real window was about six weeks.


The fake Des Moines Septic site - built in a single three-to-four-hour Claude Code session two weeks before recording - was already ranking on page one of Google, beating legitimate businesses, Better Business Bureau, and HomeAdvisor for "septic tank pumping near me." That's the case study you use to land clients.


The client pitch for boring local service businesses is not immediate ROI - it's long-term compounding. Work done today pays dividends in year one, year two, and year five, even after the retainer ends. Business owners who think long-term immediately get this, and they're exactly who you want as clients.


The whole stack is nearly free. GitHub is free. Cloudflare has a generous free tier. VS Code is free. Astro is free. All you need is a Claude subscription - $100 a month gets you real output capacity. The arbitrage between a $100/month subscription and two or three clients paying $2,000–$5,000 a month each is hard to argue with.


Ryan's approach to client acquisition for local businesses: go in person. With AI-generated spam calls and emails everywhere, walking into a business and talking to the owner directly cuts through the noise. Even as a mediocre salesperson, ten in-person conversations with decision-makers will close at least one client.


Links Mentioned

Ryan's Claude Code Skill Stack — 25–30 marketing and content skills including the WordPress repurposing workflow and the local service site builder — https://ryandoser.com/


Ryan Doser's YouTube channel — real-world Claude Code workflows for marketing and content, with full walkthroughs of everything shown in this episode — https://www.youtube.com/@RyanDoserAI


AI Marketing Insiders community — Ryan's 1,000+ member community for marketers using AI — https://www.skool.com/ai-marketing-insiders


FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim
Skool Community: https://www.skool.com/aioperatoracademy/about


FIND RYAN ON SOCIAL

YouTube: https://www.youtube.com/@RyanDoserAI
Website: https://ryandoser.com/
AI Marketing Insiders: https://www.skool.com/ai-marketing-insiders

How I convert free mini assessments into $999 AI audits12 Jun 202600:09:54

Grab the full mini assessment playbook in Notion for free, including the first-call script and the second-call prep checklist: https://corey-ganim.kit.com/0cea7ca381

In this solo episode, I hand over the complete free AI mini assessment framework I use to turn business owners into paid clients in two 15-minute calls. I walk through the three levers of ROI, the five questions to ask on the fact-finding call (including the ROI anchor and my favorite, the magic wand question), and how to pick the one bottleneck that sits at the intersection of high frequency and high friction. Then I break down the prescription tree, when to recommend an off-the-shelf tool, Claude Cowork, or a custom Claude skill, and the exact three things you bring to the follow-up call. By the end, you'll be able to run this assessment confidently in about 15 minutes and ask the money question that converts 30 to 50% of free assessments into paid work.

Join our AI Operator Academy Community: https://www.skool.com/aioperatoracademy/about


Timestamps

00:00 – Intro

00:14 – The lens: one bottleneck, one tool, one upsell

00:30 – The three levers of ROI

00:57 – Meeting one: the 15-minute fact-finding call

01:25 – The forking question

01:43 – The repetition question

01:58 – The friction question

02:10 – The ROI anchor question

02:45 – The magic wand question

03:35 – Closing call one and booking the follow-up

03:55 – Between meetings: frequency and friction research

04:43 – Meeting two: prescribing the one solution

05:15 – Finding off-the-shelf tools in AI directories

06:20 – Claude Cowork vs. a custom Claude skill

07:08 – The three things you bring to call two

07:40 – The money moment and the upsell question


Key Points


Every prescription has to pull one of three ROI levers: effectiveness (more revenue), efficiency (hours back in their week), or quality (happier customers). Let the owner pick the lever, then weight everything back to it.


Meeting one is pure discovery. Prescribe nothing. Ask the five questions, listen, and close by naming the one bottleneck with the highest opportunity back to them.


The ROI anchor: get the owner to quantify the pain in their own words. Two hours a week at $200 an hour is $400 a week they could get back, and that number does the selling for you.


The bottleneck worth fixing sits at the intersection of high frequency and high friction. That's the one you prescribe. Everything else stays in your back pocket.


The prescription tree: common tasks get an off-the-shelf tool, tasks involving judgment, writing, or research get Claude Cowork, and repeatable workflows unique to their business get a custom Claude skill.


When prescribing a custom Claude skill, tell them the what, not the how. That gap is your upsell.


Come to call two with three things, the name of the tool, what it costs, and the first step they could take this week, then ask the money question: hand it off, build it with you, or build it for you? 30 to 50% of the time, they say build it.


Free Notion template with the full mini assessment playbook, first-call script, and second-call prep checklist - [ADD NOTION TEMPLATE LINK]


There's An AI For That - AI tool directory searchable by industry to find off-the-shelf fixes - https://theresanaiforthat.com


Futurepedia - another AI tool directory for matching tools to client pain points - https://www.futurepedia.io


Claude Cowork - the prescription for tasks involving judgment, writing, or research - https://claude.com


FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

Click to enable keyboard move mode.


8 objections you'll get selling AI services (and how to destroy them)15 Jun 202600:11:53

Grab the free cheat sheet of all eight objections plus a how-to-use-them section - https://corey-ganim.kit.com/a2e17c90d1

In this solo episode, I break down the eight most common objections you'll hear when pitching AI services to business owners, and I show you exactly how to destroy each one. I cover the QuickBooks analogy that handles "can't I just use ChatGPT myself," why skeptics need one concrete win in days instead of more hype, and the ROI flip that makes "it's too expensive" the easiest objection on the list. I also walk through the effort versus impact matrix for owners who tried AI and got bad results, the five pillars that prove no business is too specialized, and the exact framing for "let me think about it." By the end of this episode, you'll have a ready response for every objection standing between you and your next closed AI deal.


Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business https://www.skool.com/aioperatoracademy/about

Timestamps

00:00 – Intro

00:14 – Objection 1: Can't I just use ChatGPT myself?

01:25 – Objection 2: AI feels overhyped

02:05 – Free cheat sheet of all eight objections

02:33 – Objection 3: It's too expensive

03:46 – Objection 4: I don't have time right now

04:55 – Objection 5: I tried AI and got bad results

05:40 – The effort versus impact matrix

06:30 – Objection 6: My business is too specialized

06:50 – The five pillars of an AI operating system

07:30 – Objection 7: I don't want to replace my people

09:00 – Objection 8: Let me think about it

09:45 – The $999 AI assessment close

10:25 – Recap and how to grab the cheat sheet


Key Points


You destroy "can't I just use ChatGPT myself?" with the QuickBooks analogy: you could do your own books, taxes, and insurance, but you pay an expert because they know what to do and you don't want to spend the time learning.


"It's too expensive" is the easiest objection to overcome because you can always flip it to ROI. If a few thousand dollars buys back five hours a week or unlocks more revenue, the expensive option is doing nothing.


"I don't have time" is the objection that proves the pitch. The owner has no time because they're buried in the exact day-to-day tasks you'd be automating.


Most owners who tried AI and got bad results jumped straight into tinkering. The right way is auditing existing workflows with an effort versus impact matrix and stack-ranking exactly where AI makes sense.


No business is too specialized for AI. Every business runs on follow-up, quoting, scheduling, and emails, and every business runs on the same five pillars: sales, marketing, finance, operations, and intelligence.


Frame AI as automating tasks, not roles. It pulls the grunt work off the team so they can do the job they were actually hired for, and you never lead with replacing people.


"Let me think about it" is usually a smokescreen. Reframe the real decision: every week of waiting is more hours lost to a task that could be automated, and the cost of staying stuck compounds.


ChatGPT - https://chatgpt.com


Claude - https://claude.ai


FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim

Instagram: https://www.instagram.com/coreyganim/

LinkedIn: https://www.linkedin.com/in/coreyganim/

YouTube: https://www.youtube.com/@coreyganim

The $5K AI offer that costs $9 to fulfill (how to build and sell it)18 Jun 202600:45:53

LIMITED bonus from Hyperagent: First 1,000 people get $1,000 in free Hyperagent credits. Claim yours: https://www.hyperagent.com/corey

I brought on Alex McDonnell from HyperAgent, which is the new agentic platform built by the team at Airtable, and we walked through a full business model for selling AI services to local brick-and-mortar businesses. The play is simple: use agents to find businesses with great reviews but terrible or nonexistent websites, have HyperAgent build them a new site automatically, then lead with that as a free tripwire offer. We go deep on the real upsell, which is revenue-driving systems like speed to quote tools for landscapers and mechanics that close deals faster. By the end of this episode, you'll have a complete offer structure you can take to any local business owner this week.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about


Timestamps

00:00 – Intro

00:43 – What HyperAgent is and the business model concept

02:19 – Why this outreach wasn't possible before AI agents

05:16 – The command center for managing agent-built prospects

07:59 – Website before and after: Veslo Family Restaurant

10:36 – How HyperAgent judges website quality on its own

15:10 – Speed to quote system for a landscaping business

19:53 – Why zero landscapers in your city have this yet

22:55 – Pricing the offer: $5-10K setup plus monthly retainer

26:14 – Live build: speed to quote for CS Automotive

27:35 – Plan mode vs execute mode in HyperAgent

30:39 – Running agents on a Kanban board in Airtable

33:30 – Selling the agent itself as the product

37:03 – Agent marketplace and the compute markup model

38:05 – Live result: the CS Automotive quote tool finishes

42:20 – Static artifacts as lead gen, always-on agents as the upsell


Key Points

The tripwire offer model works because agents can now build a full website for a local business in under an hour for about nine dollars in compute, turning what used to be a paid deliverable into a free lead gen tool.

HyperAgent doesn't just find businesses without websites. It has the judgment to recognize that a business has a website but it's bad, which is a much harder problem that most agentic tools couldn't solve even a few months ago.


The real money is not in the website. It's in upselling always-on revenue systems like speed to quote tools that help businesses close deals faster, priced as a $5-10K setup fee plus a monthly retainer of $200-1,000.

The landscaping speed to quote example is the standout: a customer submits a photo of their yard and gets back three design variations with toggleable features, live pricing, and financing options, all generated by an agent.

Every skill Alex builds for HyperAgent demos gets published for free on X and GitHub, so you can grab the landscaping build, install it, and take it to a client without building from scratch.

HyperAgent's long-term vision includes an agent marketplace where creators publish agents and earn a markup on compute costs, making distribution feel free to the end user while the builder still gets paid.


Airtable - System of record for managing agent workflows via Kanban boards - https://www.airtable.com

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.

FIND ME ON SOCIAL

X/Twitter: https://x.com/coreyganim 
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/ 
YouTube: https://www.youtube.com/@coreyganim

FIND ALEX ON SOCIAL

X/Twitter:  @hyperagentapp 


Building a one-person AI agent business that makes $50K/month22 Jun 202600:47:50

Grab Nick's exact blueprint for scaling a managed AI agent business to $50k/month: https://corey-ganim.kit.com/5e8c982461

Use code COREY to get your first 3 days of Orgo.ai free then 20% off your first 3 months: https://www.orgo.ai/?r=COREY

I brought on Nick Vasilescu, co-founder of Orgo, and we built out the complete blueprint for a one-person managed AI agent business that can hit $50K a month in recurring revenue. The model is straightforward: charge $5K per month per client for unlimited agents, unlimited tokens, and unlimited infrastructure. You handle everything so the business owner never has to think about what a token is or how to set up Hermes. We walk through the full stack, the offer, how to find and close clients, how to onboard them using an effort versus impact matrix, and how to deploy and manage agent fleets on Orgo. Nick even sets up a Hermes agent from scratch in twenty-six seconds live on screen. If you want a business you can start this week with skills you already have, this episode gives you the whole thing.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about

Timestamps


00:00
– Intro and what you'll walk away with

01:14 – The $5K per month per client blueprint overview


01:46
– The biggest arbitrage: most businesses don't know what agents can do


03:11
– The offer: unlimited tokens, agents, and infrastructure


05:08
– Best industries for managed agents and how to pick a niche


06:07
– Go broad first, let the market pull you into a niche

08:06 – How to find clients: content, Upwork, and free work for case studies


09:43
– Why your first clients should be free


11:06
– Onboarding: voice recorder to workflow map to effort versus impact matrix


12:32
– The audit as a foot-in-the-door offer


14:49
– Steal this flow: free mini audit into paid audit into managed service

16:00 – The agent stack: Hermes, Composio, and Orgo


17:51
– Composio for one-click tool connections

19:53 – Orgo walkthrough: spinning up workspaces and agent computers

21:02 – How workspaces map to clients


22:25
– The client never sees Orgo, it's your operator layer

24:38 – Troubleshooting client agents from your phone


26:49
– Building industry-specific productized agent apps


27:59
– From audit transcript to deployed skill in ten minutes

28:36 – Orgo discount code for the audience


29:47
– Windows computers on Orgo: managing Codex and Claude Code for clients


32:35
– Cloning agent templates for instant productization

33:50 – Twenty-six second Hermes installation live on screen

37:16 – The full stack: Hermes, Composio, Orgo, Agent Mail

38:08 – Watchdogs: get alerted before your client notices a problem

39:31 – Why being a good communicator is your biggest edge


41:28
– Token cost management with Codex subscriptions

41:36 – The math: ten clients equals $50K MRR at 85% margins


43:04
– Why most people still won't take action

45:00 – Thinking long term: the cost of intelligence is going to zero


Key Points


The core offer is simple: unlimited tokens, unlimited agents, unlimited infrastructure for $5K a month. Business owners do not care about the technical details. They want their problem solved, and your job is to remove all complexity.


The best sales flow is a three-step funnel: a free mini audit that uncovers one pain point, a paid full audit for $1,000 that maps five to seven workflow opportunities, and then a $5K per month managed service where you credit the audit fee toward the first month.

The effort versus impact matrix is the key to onboarding. After the first call, you map every workflow the client mentions, plot them by value versus effort, and start with the ones in the high-value low-effort quadrant. That first win is the hook.

Orgo lets you manage fleets of agent computers across all your clients from one dashboard. Each client gets their own workspace. You can spin up a Hermes agent from a template in twenty-six seconds and clone golden snapshots to productize your setup across multiple clients in the same niche.

Composio solves the biggest fulfillment bottleneck in managed agents: connecting all of a client's tools. The client connects their apps in one place, gives you the API key, and your agent has access to everything.


The math works even with conservative assumptions. One new client every six weeks gets you to ten clients and $600K ARR in a year. Token costs per client run about $200 a month via a Codex subscription, leaving you with 85 percent or higher gross margins.


Nick's long-term thesis: the cost of intelligence is going to zero. Even if you lose money on tokens in month one, the spread will widen every month as models get cheaper. Think about where the puck is going.
 Hermes Agent: https://www.hermes.agent Agent Mail: https://agentmail.to Excalidraw business blueprint diagram: [placeholder - link to diagram]

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.


FIND ME ON SOCIAL


 X/Twitter: https://x.com/coreyganim

 Instagram: https://www.instagram.com/coreyganim/

 LinkedIn: https://www.linkedin.com/in/coreyganim/ 


YouTube: https://www.youtube.com/@coreyganim


FIND NICK ON SOCIAL

 X: https://x.com/nickvasiles

YouTube:@nickvasiles

Orgo: https://www.orgo.ai


How I sell AI second brains for $5K each (full blueprint)25 Jun 202600:53:22


 Grab Adam's free build guide for building, packaging, and selling your first AI knowledge base: https://corey-ganim.kit.com/a49b7bd19d

Adam Sandler from Viable Edge is back on the pod, and this time he walks through the full blueprint for selling AI-powered knowledge bases as a service. The pitch to clients is simple: I will clean up all of your company knowledge, organize it, structure it, and turn it into a living asset that powers every AI tool you use going forward. No Obsidian, no RAG, no vectors. Just markdown files on a local machine. Adam builds the whole thing live on screen using Claude Code with a fictional company, shows the seven note types every knowledge base needs, and breaks down the pricing tiers from a $750 audit to a $4,700 premium build. The real insight is that the knowledge base is not the end product. It is the foundation that opens the door to every future engagement with that client.


Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about


Timestamps 

  • 01:18 – Why Adam leads with the knowledge base on every engagement
  • 02:55 – Knowledge base as a tripwire offer, same concept as the AI audit
  • 04:12 – The pitch: clean up your company knowledge and make it a living asset
  • 04:57 – You don't need Obsidian or RAG to start, markdown files are enough
  • 06:12 – Why a provider-agnostic knowledge base protects clients from platform risk
  • 07:00 – Token cost savings as a selling point for teams and enterprise
  • 08:45 – Anthropic enterprise going to pay-as-you-go and why that matters
  • 09:34 – The seven durable note types every knowledge base needs
  • 13:19 – How the seven types simplify the what do I include question
  • 14:13 – The spine concept: one foundational schema everything ladders up to
  • 15:58 – Module-by-module walkthrough of Adam's mini course
  • 16:58 – No client needs to touch Claude Code, this works in Cowork
  • 18:06 – Coaching moments as value-adds during the build
  • 18:29 – Live build: establishing the foundation with discovery prompts
  • 20:16 – The discovery questions mapped to the seven note types
  • 22:00 – Applying structure: from raw answers to schema
  • 25:31 – Summary of the build process so far
  • 27:01 – How to maintain the knowledge base after the initial build
  • 27:38 – Pricing: audit, core build, and premium build tiers
  • 29:09 – The knowledge audit as a foot-in-the-door offer
  • 30:10 – Positioning options: department-by-department builds for larger clients
  • 30:52 – The first knowledge base files and the index file
  • 34:50 – Three layers of context: hot, durable, and disposable
  • 35:47 – Setting up Cowork global instructions to recognize the knowledge base
  • 38:33 – The ingest skill: automating information intake from multiple sources
  • 39:47 – The curate skill: weekly health checks on the vault
  • 41:26 – Provider portability as a major selling point
  • 42:18 – Handling sensitive client information
  • 43:41 – Upselling from the knowledge base: let the data tell you what to build next
  • 46:16 – Light bulb moment: the knowledge base recommends its own next project
  • 47:08 – Value-add opportunities: competitive insights, call transcript analysis
  • 48:25 – Why solo practitioners can compete with startups in this space
  • 50:09 – Second brain as a service is going to be one of the hottest AI offers
  • 51:58 – Where to find Adam and the free guide


Key Points

The knowledge base solves the foundational problem every AI engagement runs into: where is the client's information and how is it organized? Starting here sets up every future project to succeed and gives you a reason to keep working with the client.

There are seven durable note types that form the starting schema for any client: snapshot, people and contacts, ongoing conversations, preferences and rules, project history, decisions and rationale, and open loops. This framework answers the question of what to include and what to leave out.

The spine is the one foundational piece of data everything else ladders up to. For most clients, it is their annual goals or objectives. Every other note in the knowledge base should be traceable back to it.

No fancy technology is required to start. The entire build runs on markdown files. No Obsidian, no RAG, no vector databases. You can add sophistication later, but a simple implementation still delivers massive value and is easy to sell because there is zero technical friction for the client.

The sales flow mirrors the AI audit model: a $750 knowledge audit maps where the client's information lives and what the schema should look like, then upsells into a $3,500 core build or $4,700 premium build. The audit fee gets credited toward the build.


Two skills keep the knowledge base alive after the initial build. The ingest skill automatically processes new information from sources like Gmail, calendar, and an inbox folder. The curate skill runs weekly to flag stale notes, contradictions, open items, and gaps.


The biggest upsell comes from the knowledge base itself. Once all of a client's context is in one place, you can query it for the top opportunities to implement AI next, and the client does not need to be sold because the data is making the case.

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.


FIND ME ON SOCIAL

 X/Twitter: https://x.com/coreyganim
 Instagram: https://www.instagram.com/coreyganim/ 
LinkedIn: https://www.linkedin.com/in/coreyganim/ 
YouTube: https://www.youtube.com/@coreyganim


FIND ADAM ON SOCIAL

 YouTube: https://www.youtube.com/@viableedge

How I run an $8K/month AI business in 5 minutes a day (full breakdown)29 Jun 202600:20:45


Grab the free AI Concierge playbook including the full offer and fulfillment process:
https://corey-ganim.kit.com/cde665995b 

This is the full AI concierge business model broken down step by step. You are going to see everything from the intake form to the Notion hub to the Claude skills that handle all the follow-up work in thirty seconds. I walk through the exact process I use with real clients: how to onboard them, how to run the first call, how to automate the entire back end, and how to earn the renewal without ever having to sell them again. Outside the calls themselves, I spend less than five minutes per client. This is the full playbook.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about

Timestamps
 

  • 00:30 – Step 1: land the client from the AI assessment upsell
  • 01:00 – Step 2: send the JotForm intake form before the first call
  • 02:17 – The tool stack and team questions
  • 03:00 – The outcomes section: what does winning look like in 90 days
  • 04:00 – No form, no call: why the intake form is non-negotiable
  • 04:36 – Step 3: the Notion hub walkthrough
  • 06:00 – Open action items and the call log
  • 07:00 – Tools and skills built on this call: the most important section
  • 08:00 – How this works section and the 12-hour Voxer SLA
  • 09:05 – Step 4: conducting the first strategy call
  • 09:30 – Track 1: onboarding clients to Claude Cowork with the plugin
  • 11:29 – Track 2: running AOA on the biggest bottleneck
  • 12:00 – AOA framework: audit, optimize, automate
  • 13:55 – Step 5: running the back-end skills in thirty seconds
  • 14:30 – AI Concierge Follow-Up Email skill
  • 15:00 – AI Concierge Call Update skill for Notion
  • 15:30 – AI Concierge Post-Call orchestrator skill
  • 16:14 – The follow-up email draft and one-click send
  • 17:00 – Less than five minutes of post-call admin work
  • 17:30 – Step 6: mind the gap, Voxer between calls
  • 18:00 – Step 7: call two and beyond, stacking the build list
  • 18:33 – Doubling the price for weekly call cadence
  • 19:00 – Step 8: earning the renewal, the ledger does the talking
  • 19:30 – The free checklist and AI Operator Academy

Key Points

The AI concierge model starts with a $999 AI assessment that upsells into an ongoing retainer. The intake form in JotForm acts as a mini audit so you arrive at the first call with a game plan instead of spending thirty minutes figuring out where to start.

The Notion hub is the single source of truth for every client engagement. After each call, a Claude skill automatically fills in the top three takeaways, action items, and a detailed list of every tool and skill built on that call. That build log is the most important retention mechanism in the entire model.


The AOA framework drives every strategy call: audit the process by having the client share their screen and show you the manual workflow, optimize by cutting unnecessary steps, then automate by turning it into a Claude skill or handing it to Cowork. Most clients hit their 90-day goal by call two or three.

Three Claude skills handle the entire back end. AI Concierge Follow-Up Email drafts a recap email to the client. AI Concierge Call Update fills out the Notion hub from the call transcript. AI Concierge Post-Call runs both in parallel. Total time after each call is less than five minutes.

The renewal sells itself. The build log inside Notion shows the client in unmistakable detail what they got for their money. You never have to pitch the renewal because the ledger does the talking.

Between calls, Voxer is the async communication tool with a 12-hour SLA. Responding faster than promised is the easiest way to over-deliver and keep clients feeling supported.


Links Mentioned: JotForm: https://www.jotform.com Notion: https://www.notion.so Fathom: https://fathom.video Voxer: https://www.voxer.com

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.


FIND ME ON SOCIAL:
X/Twitter: https://x.com/coreyganim 
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/ 
YouTube: https://www.youtube.com/@coreyganim

Charge $999 to audit businesses with AI02 Jul 202600:13:30

Grab the exact template I use to deliver the $999 AI audits here (free): https://corey-ganim.kit.com/fd0829de10

This is the actual AI tools assessment template that we deliver to clients after a $999 audit. Nine slides, built from scratch in Claude Design, walked through one by one so you can see exactly what goes on every slide and why. I cover the effort versus impact matrix, the tool stack recommendations, the four-day quick wins plan that gets clients to implement at least half the report in under a week, and the financial impact slide that shows them their monthly ROI in dollars. I also show you exactly how the assessment sets up the upsell into bigger projects, and at the end I give you the actual template file so you can duplicate it in Claude Design and start using it with your own clients.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about


Timestamps

00:00 – Intro: The real AI tools assessment template


00:30
– Building the template in Claude Design and why we canceled Gamma


01:00
– How to auto-fill the template by dropping in a client transcript

01:30 – Slide 1: Title slide and the tweaks menu in Claude Design

02:00 – Slide 2: Executive summary with primary pain point and outcome

02:24 – The three levers of ROI: Effectiveness, efficiency, and quality

02:50 – Slide 3: The effort versus impact matrix


03:30
– Quick wins, fill-ins, major projects, and what to ignore

04:44 – Slide 4: Quick wins summary with pain point to tool mapping


05:30
– Slide 5: The full tool stack with cost, setup time, and time saved


06:30
– Slide 6: The four-day quick wins plan

07:02 – Why the four-day plan prevents implementation paralysis

07:30 – Slide 7: What comes after quick wins and the major projects upsell

08:30 – How to tee up the upsell on the review call


09:00
– Slide 8: Financial impact and the monthly net ROI calculation

09:20 – The ROI formula: Weekly Hours Returned × Hourly Rate − Tool Cost


10:30
– Slide 9: Next steps and the review call booking

11:00 – Three questions that close 50 percent of upsells on the review call


11:43
– How to duplicate the template in Claude Design using the HTML file


12:30
– Sixty seconds to a fully imported template


Key Points


The assessment template is nine slides built in Claude Design. You can drag and drop a client transcript into the Claude Design chat and it will auto-fill the entire template for you, making this nearly plug and play.

The effort versus impact matrix is the light bulb moment for clients. It sorts all recommendations into four quadrants: quick wins that are high impact and low effort, fill-ins, things to ignore, and major projects that become your upsell opportunities.

The tool stack slide is where you spend most of the review call. Each recommendation shows the pain point, the tool, a brief description, the monthly cost, setup complexity, and estimated weekly time saved.

The four-day quick wins plan prevents implementation paralysis. Instead of overwhelming clients with six recommendations, you give them four things to do in four days that capture at least fifty percent of the report's value.

The financial impact slide makes the ROI undeniable. Take the weekly hours returned times the client's self-reported hourly rate times four, then subtract the total monthly tool cost. A typical result: five hours per week at a hundred dollars per hour minus fifty dollars in tools equals $1,950 per month in net ROI from a $999 assessment.


The major projects slide is the upsell. High impact, high effort solutions that need custom builds like Zapier automations, AI agents, or knowledge bases. On the review call, three simple questions close over fifty percent of clients: do you want my help implementing these, which will you tackle first, and how urgent is it.


Links Mentioned: Claude Design: https://claude.ai SanBox: https://www.sanebox.com Fathom: https://fathom.video


If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.


FIND ME ON SOCIAL


X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/ 
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim

Don't start an AI automation agency in 2026 (do this instead)06 Jul 202600:24:58


Grab the assessment report template I use to deliver $999 AI assessments (free): https://audittemplate.ai/

Grab the full Excalidraw diagram I show in this video depicting the AI Offer Ladder: https://app.excalidraw.com/l/4z8Z2Lyybfg/8FAvEjYbuGc 

This is the full AI offer ladder that I use to sell AI services, from a free mini assessment all the way up to a two thousand dollar per month concierge retainer and beyond. I walk through all three tiers of the ladder step by step: the free mini assessment that converts thirty to fifty percent of the time, the paid assessment that we charge $999 for, and the AI concierge model that is my primary income source right now. I also cover four à la carte builds you can sell on top of the ladder, with real examples and exact pricing from engagements we have actually closed. If you want theof this offer ladder plus the assessment report template, both are linked below for free.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about


Timestamps 

  • 00:00 – Intro: The three components of the AI offer ladder
  • 00:30 – The free mini assessment: What it is and how it works
  • 01:00 – Three levers of ROI: Effectiveness, efficiency, and quality
  • 01:30 – Meeting one: Discovery call and the magic wand question
  • 02:00 – Meeting two: Prescribing the fix
  • 02:21 – Download the Excalidraw diagram for free
  • 03:00 – Off-the-shelf tool vs. Claude Cowork vs. Claude skill: When to prescribe each
  • 04:00 – Closing the free assessment: Gauging appetite for paid help
  • 04:30 – Conversion data: 30 to 50 percent of free assessments convert to paid
  • 04:44Step Two: The paid assessment at $999
  • 05:30 – Annie: The voice agent that conducts the 45-minute interview
  • 06:30 – Building the report in Claude Design
  • 07:06 – Six parts of the paid assessment report
  • 07:30 – The effort versus impact matrix and quick wins
  • 08:30 – Quantifying ROI: Hourly Rate × Hours Saved − Tool Cost
  • 09:29 – The 30-minute walkthrough call and the upsell moment
  • 10:00 – Pricing progression: Free to $200 to $500 to $1,000
  • 10:30Step Three: The AI concierge retainer
  • 11:57 – Effective hourly rate: At $1,500/month is $1,000/hour
  • 12:30 – JotForm intake as a hard requirement before call one
  • 13:30 – Framework: AOA (Audit, Optimize, Automate)
  • 14:06 – The call cadence and Voxer between sessions
  • 15:30 – The Notion Hub as a renewal mechanism
  • 16:26 – Two Claude skills that fill out Notion and draft follow-up emails in 30 seconds
  • 17:00 – Concierge pricing: $1,000 to $2,000/month, capping at six clients
  • 18:00À La Carte Build 1: Process optimization at $3,000 to $5,000
  • 19:30À La Carte Build 2: Zapier or Make automation at $1,000 to $5,000
  • 20:00À La Carte Build 3: Knowledge system or custom GPT at $3,000
  • 21:00 – Case Study: Business broker custom GPT that cut 400 emails to 10
  • 22:00À La Carte Build 4: Speed to lead agent
  • 23:36 – Wrap-up and where to get the diagram and template



Key Points

The offer ladder has three tiers that build on each other. A free fifteen-minute mini assessment identifies one pain point and prescribes one tool. Thirty to fifty percent of those convert into a paid assessment at $999 that uncovers three to seven opportunities and delivers a full report. From there, clients can upsell into AI concierge at one to two thousand dollars a month.

The free mini assessment is a two-meeting process. Meeting one is pure discovery for fifteen minutes. Between calls you research the bottleneck and find a tool. Meeting two you prescribe the fix and gauge appetite for paid help with three simple questions.

The paid assessment report has six parts: executive summary, effort versus impact matrix, recommended tool stack, four-day quick wins plan, upsell opportunities for heavier builds, and a financial ROI slide that quantifies their monthly savings in dollars.

The AI concierge model is two 45-minute calls per month where you run the AOA framework on every bottleneck: audit the manual process, optimize by cutting unnecessary steps, automate with a Claude skill. Two Claude skills handle the entire back end in thirty seconds.

The math on concierge is compelling. At $1,500 per month for ninety minutes of call time, the effective hourly rate is $1,000 per hour. Capping at six clients means the maximum workload is nine hours of calls per month.

Four à la carte builds can stack on top of the ladder: process optimization at three to five thousand dollars, Zapier or Make automation at one to five thousand, knowledge system or custom GPT at three thousand, and speed to lead agents that drive revenue directly.


Links Mentioned

Futurepedia: https://www.futurepedia.io
There's an AI for That: https://theresanaiforthat.com 
JotForm: https://www.jotform.com 
Voxer: https://www.voxer.com
Fathom: https://fathom.video


If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.


FIND ME ON SOCIAL:
X/Twitter: https://x.com/coreyganim 
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/ 
YouTube: https://www.youtube.com/@coreyganim


The AI Operating System that sells itself (zero delivery work)09 Jul 202600:33:49


Justin Brooke from Agent Skills is back on the podcast, and this time he walks us through the full business model behind selling AI systems as zip files with zero delivery work. His system is called CMO HQ, a marketing and sales operating system built entirely out of folders and markdown files that works with any AI, whether it is Claude, ChatGPT, Hermes, Codex, or anything else. The delivery model is dead simple: the customer buys from a sales page, receives a zip file with an operations manual and an installer dot MD file, hands that file to their AI of choice, and the AI builds out the entire system for them. No onboarding calls, no Loom walkthroughs, no custom setup. Justin shows us the full folder structure, the finance layer, a live content pipeline, and the actual installer file on screen.

Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about

Timestamps

00:00 - Intro: Justin Brooke is back


00:23
- What CMO HQ is and why it works with any AI


01:23
- The folder structure: HQ, brands, finance, shared

03:30 - Brands folder: one per brand with intelligence, departments, and metrics


04:10
- The finance folder and why it matters for true marketing metrics


05:14
- The installer.md file that builds the whole system

05:45 - Why this is the simplest marketing OS out there


05:50
- Inside the finance folder: revenue, expenses, economics, reporting


06:48
- Connecting Google Ads, Kit, Thrivecart, and Xeny for full-picture data


07:56
- Building in iCloud for access from any device


09:27
- Marketing departments: paid, earned, and owned channels


10:00
- The sacred pipeline: active to review to publish

11:06 - Live example: faith-based niche site blog post end to end

13:30 - Automated performance reporting via MCP connections


15:18
- Why Justin does everything in Claude Cowork, not Claude Code

15:45 - How to sell any AI-generated asset to clients

16:25 - The delivery problem and why folders and files solve it

17:24 - The two-file delivery: operations manual plus installer.md


19:13
- Session transfer documents and how the system started


20:19
- Changelog.md for tracking business decisions


20:46
- The jobs to be done framework for building any system

22:01 - Jobs equal folders, instructions equal markdown files, which equal skills


23:26
- Why the nerds who want to build it themselves are not your customers

24:33 - Step one: jobs to be done, then vibe with Claude to build folders


26:00
- Three things every agent needs: memory, instructions, tools


26:18
- Why you should use a slide deck on every sales call


28:25
- The installer file walkthrough on screen

30:27 - Why this means zero delivery work


31:14
- Where to find Justin and Build Club


32:22
- Justin hangs out mostly on Twitter


Key Points

The entire system is folders and markdown files. No code, no complex frameworks, no platform lock-in. It works with Claude, ChatGPT, Hermes, Codex, or any other AI because all of them can read folders and files.


The delivery model eliminates all fulfillment work. Customers buy from a sales page, receive a zip file containing an operations manual and an installer dot MD file, hand that installer to their AI, and the AI builds out the entire system. No calls, no custom setup, no support tickets.

The installer dot MD file is the key innovation. It contains a greeting, an interview section that asks the customer about their business, and then the full folder structure with instructions. The AI reads it and builds everything automatically in one session.

CMO HQ has four main sections: an HQ folder for personal and business identity, a brands folder with one subfolder per brand containing intelligence, departments, and metrics, a finance folder that connects to accounting and ad platforms for real financial reporting, and a shared folder for team collaboration.

The jobs to be done framework is how you replicate this for any niche. Figure out what jobs need to be done in a business, make a folder for each job, put instructions in each folder, and you have a sellable system. Dentists, lawyers, agencies, any vertical works the same way.


Three things every agent needs: memory so it knows what happened, instructions so it knows what to do, and tools so it can do the work. If you have those three things in folders and files, you can handle any job.


The sales advice is simple and powerful: stop doing calls on the fly and use a slide deck for every sales call. It keeps you on pace, makes every call uniformly good by the fifth or sixth time, and becomes the training material when you hire a salesperson.


Links Mentioned


 Agent Skills / Build Club: https://agentskills.ai Jake Van Cleef (ICM system and folders-and-files research): mentioned, search YouTube Ghost CMS: https://ghost.org 11 Labs: https://elevenlabs.io

If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.

FIND ME ON SOCIAL


 X/Twitter: https://x.com/coreyganim

 Instagram: https://www.instagram.com/coreyganim/


 LinkedIn: https://www.linkedin.com/in/coreyganim/ 


YouTube: https://www.youtube.com/@coreyganim


FIND JUSTIN ON SOCIAL

 X/Twitter: https://x.com/agentskills_ai
                  https://x.com/IMJustinBrooke


Agent Skills: https://agentskills.ai

© My Podcast Data · Independent project · Data from Apple & Spotify