Explorez tous les épisodes du podcast The AI Native Dev - from Copilot today to AI Native Software Development tomorrow
Plongez dans la liste complète des épisodes de The AI Native Dev - from Copilot today to AI Native Software Development tomorrow. Chaque épisode est catalogué accompagné de descriptions détaillées, ce qui facilite la recherche et l'exploration de sujets spécifiques. Suivez tous les épisodes de votre podcast préféré et ne manquez aucun contenu pertinent.
Rows per page:
50
1–50 of 129
Titre
Date
Durée
Legora CTO: Why AI Agents Need More Than a Chat Window
06 Oct 2026
00:44:22
AI coding agents now write almost all of Legora's code, with engineers running up to ten in parallel. Yet the CTO behind that shift thinks measuring adoption by tokens burned is a mistake. Jacob Lauritzen, CTO of Legora, joins Simon Maple to unpack what actually scales when agents do the typing, and where human judgment still has to stay in charge.
What we cover: – How Legora's engineers orchestrate many AI coding agents at once, from shared local dev resources to cloud agent setups – An agentic loop that reproduces, fixes and tests bugs straight from Slack – Why token maxing is a bad way to drive AI adoption, and what to measure instead – Agent evaluation: regression testing the harness as models and prompts change every week – Decision models, the verifier's rule, and where autonomy ends and human judgment begins – Why AI agents need more than a chat interface
Chapters: 00:00:00 - Introduction 00:01:47 - Legora's growth from $100M to $200M ARR 00:03:44 - Parallel coding agents and bug-fix loops 00:07:15 - Senior engineers vs AI-first engineers 00:10:10 - Why token maxing is the new lines of code 00:14:13 - What AI can and can't verify in legal work 00:17:30 - Decision models vs autoregressive LLMs 00:24:22 - Weekly model benchmarks and harness evals 00:26:58 - Why AI agents need more than a chat interface 00:35:03 - The verifier's rule and litigation strategy
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/lpg
🔔 Subscribe for weekly episodes on AI-native development
Is token count telling you anything real about how your team uses AI coding agents? Tell us in the comments.
Liz Fong-Jones: 2x the PRs, 1.5x the Incidents
29 Sep 2026
00:49:38
Honeycomb went from 30 to 70 merged pull requests a day in three months. The catch: automated code review, not code generation, became the real bottleneck of software automation. Liz Fong-Jones, Technical Fellow at Honeycomb, explains why incidents still rose 1.5x, how their internal bot Autobot now reviews every PR, and why AI amplifies whatever org you already have.
What we cover: – How automated code review lets humans focus on design, not trivial bugs – Using a decision model like Jev to decide which PRs are safe to auto-merge – What makes a codebase ready for AI coding agents – When to trust AI agents with production incidents, and when they're just throwing darts – Why "Claude did it" isn't an excuse, and what ownership means with AI – How open source maintainers can handle a flood of AI slop pull requests
Chapters: 00:00:00 - Introduction 00:06:41 - Why AI amplifies dysfunctional engineering orgs 00:10:45 - What makes a codebase AI ready 00:14:01 - Honeycomb's Autobot and automated code review 00:19:06 - Using Jev to decide which PRs are safe to merge 00:26:51 - Trusting AI agents during production incidents 00:30:40 - Least privilege and guardrails for coding agents 00:33:25 - If your name's on it, you own it 00:38:55 - AI slop pull requests and open source 00:45:56 - Will observability engineering survive as a role?
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/nlr
🔔 Subscribe for weekly episodes on AI-native development
Is your team's review capacity keeping up with your AI coding agents? Tell us in the comments.
Dexter Horthy: Why We Stopped Trusting AI to Write the Plan
22 Sep 2026
00:56:12
HumanLayer CEO Dexter Horthy on why his team's bet on spec driven development nearly wrecked their own codebase, and what changed his mind about reviewing AI-written code. Dexter walks through the "YOLO pull request" experiment that ran for months before the codebase became unusable, the "dumb zone" that limits how much context you can hand a model, and why he now believes there will always be alpha in reviewing something.
What we cover: – How HumanLayer's "read the plan, skip the code" experiment quietly broke their own codebase – Why context windows have a "dumb zone," and what that means for context engineering – Sean Grove's idea that specs, not code, are becoming the durable artifact – Building overnight agents that review and fix code before a human ever sees it – Why treating software development like a factory changes how bugs compound – What Dexter thinks his advice on reviewing AI-written code will look like in 12 months
Chapters: 00:00:00 - Introduction 00:02:15 - Meet Dexter Horthy, CEO of HumanLayer 00:06:03 - The "dumb zone": why more context makes models dumber 00:06:40 - Sean Grove's "the spec is the new code" 00:09:22 - The YOLO pull-request experiment that broke their codebase 00:11:09 - Letting the model own the architecture 00:17:03 - Planning as expected-pain management 00:28:15 - Slop Code Bench and the maintainability oracle problem 00:37:59 - Why software factories aren't like car factories 00:42:49 - "There will always be alpha in reviewing something"
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/4ep
🔔 Subscribe for weekly episodes on AI-native development
Where do you land on the determinism-to-adaptability slider — plan tightly, or let the agent run? Tell us in the comments.
AWS's Marc Brooker: Specs, Not Code, Are the Hard Part
16 Sep 2026
00:56:49
Spec-driven development is reshaping what software engineers actually do all day, and Marc Brooker, VP and Distinguished Engineer at AWS, has read 3,000 to 4,000 postmortems that convinced him the code was never the hard part. In this episode of The AI Native Dev, Marc explains why testing and specification are now the real engineering work, why metastable failures keep taking down systems that look perfectly healthy, and why he still won't let AI write a single word of his blog.
What we cover: – Why spec-driven development is turning testing into the hardest part of software – What metastable failures are, and why they keep taking healthy-looking systems down – How agentic coding tools can learn from postmortems and build their own memory – Why classic authorization breaks down once you're writing agentic policy – Why Marc won't let AI write his blog, but is fully comfortable with AI-generated code – What it takes to bring junior engineers up to speed in an AI-native industry
Chapters: 00:00:00 - Introduction 00:02:17 - Marc Brooker: 18 years at AWS building agentic dev tools 00:04:36 - Inside Strands, AWS's open source agent SDK 00:06:44 - Fifteen years on call, and what agents still can't debug 00:11:23 - Metastable failures and the humility of 4,000 postmortems 00:14:32 - Teaching agents to learn from postmortems and build their own memory 00:20:14 - Why agentic policy needs more than classic authorization 00:32:14 - The agentic software development hypothesis: spec-driven development, oracles, and testing 00:39:56 - Why Marc won't let AI write his blog (but will let it write code) 00:46:37 - Advice for leveling up junior engineers in the AI era
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/[SLUG]
🔔 Subscribe for weekly episodes on AI-native development
Do you trust an agent to run its own on-call rotation yet? Tell us in the comments.
You Don't Need Juniors to Code. Hire Them Anyway.
08 Sep 2026
00:52:22
Coding agent reliability isn't a model problem, it's a gates problem. Ran Aroussi, creator of yfinance and founder of Automaze, argues that an "agentic workflow" is a contradiction in terms, and that the only thing standing between you and full autonomy is deciding where a human still signs off. He also thinks you stopped needing junior developers for their coding skills about a year ago, and that hiring them anyway is the only way the industry gets its next generation of architects.
What we cover: – Why "agentic workflow" is a contradiction, and when agentic coding is the wrong tool for the job – Where a human still has to sign off, and what coding agent reliability actually depends on – What a software factory changed about delivery times, pricing and the client backlog – Why you no longer need juniors for their coding skills, and why you should hire them anyway – Teachable knowledge vs earned knowledge, and the experience agents cannot compress – The law firm model: why dev agencies may end up looking more like Kirkland & Ellis than a SaaS startup
Chapters: 00:00:00 - Introduction 00:03:05 - yfinance, open source and 30 million downloads a month 00:06:03 - Automaze and the MUXI agent application server 00:10:42 - Where to draw the line on agent autonomy 00:15:12 - Software factories and fully autonomous merges 00:22:25 - The architect archetype and the four-phase ladder 00:28:11 - Teachable knowledge vs earned knowledge 00:30:14 - What agents did to delivery times and pricing 00:37:03 - Why "agentic workflow" is an oxymoron 00:41:08 - Anthropic, OpenClaw and the end of flat subscriptions
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/vut
🔔 Subscribe for weekly episodes on AI-native development
Where's your gate? Tell us in the comments where you still refuse to let a coding agent merge without a human looking.
850 PRs a Week: How Tessl Runs a Software Factory
02 Sep 2026
00:51:17
The software factory that put up 850 pull requests in a week, with 85 to 90% of them handled by agents end to end. Tessl's Head of Product Dru Knox on how it actually got built, why it started with skills rather than automation, and the two things nobody expects a factory to change. Guy Podjarny digs into the skills-to-loops-to-factory path, and what breaks when you skip a step.
What we cover: – What a software factory actually is, and how it differs from a pile of disconnected automations – Loop engineering: turning a skill into something that gets better every time it runs – Why context engineering has to come before automation, and what stalls when it doesn't – The two gains nobody forecasts from extra agent capacity: quality and fungibility – Verifiers and evals, or how you enforce a standard that agents are free to ignore – Context-driven code review, and why a general-purpose reviewer plateaus
Chapters: 00:00:00 - Introduction 00:03:23 - Kikimora: Tessl's own dark factory 00:04:45 - Skills, loops and factories, defined 00:09:09 - 850 PRs a week, and the road to it 00:11:27 - The surprises: quality and fungibility 00:13:16 - Why a factory has to be context centric 00:16:40 - Context-driven code review and the wall teams hit 00:22:51 - Skills inventory across your whole code estate 00:28:38 - Verifiers, evals and enforcing what you wrote down 00:37:30 - Loops, automations and owning your software factory
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/coi
🔔 Subscribe for weekly episodes on AI-native development
If you've hit the plateau Dru describes, tell us where it stopped compounding for you.
Lada Kesseler: I Trust AI Tests Less Than AI Code
25 Aug 2026
00:45:50
Lada Kesseler's approach to loop engineering is brutally simple: give the agent one step, make it write the result to a file, then read it back and go again. She calls it a centrifuge. Spin fast enough and the stupid comes out.
The Logic20/20 principal engineer has spent the last year and a half building the ground rules, skills and refinement loops that fight the defaults coding agents ship with, starting with an instruction to stop trying to please her. Along the way she explains why she trusts AI-written tests less than AI-written code, why the description field in an agent skill was never meant for humans, and why most teams chasing a software factory are about to drown in garbage.
What we cover: – Why agent ground rules have to give the model a mission to disagree with you – The refinement loop that gets to quality when the first attempt never does – Why an agent harness only works if it does one thing at a time – Sketch prototypes: replacing your code with a markdown file and an agent – Why AI-generated tests are more dangerous than AI-generated code – Software factories, and what happens when you try to switch into one overnight
*AI DevCon is coming back to New York this November* Get 15% off your ticket with code POD15 https://tessl.io/devcon#tickets
Chapters: 00:00:00 - Introduction 00:03:38 - Using AI for everything, not just code 00:06:15 - Ground rules: fixing the defaults agents ship with 00:10:02 - Agent skills and why the description isn't for humans 00:13:09 - Loop engineering: how you actually get to quality 00:16:03 - The biggest misconception about coding agents 00:20:43 - Sketch prototypes and the limits of AI architecture 00:27:48 - Reverse direction: you are the decider 00:31:58 - Why she trusts AI tests less than AI code 00:35:00 - Software factories, or drowning in garbage
Build your software factory, one workflow at a time, with Tessl: https://tessl.co/k2t
🔔 Subscribe for weekly episodes on AI-native development
Where are you on the loop engineering curve, still hoping for a good first try or already spinning? Tell us in the comments.
Every Repo Is a Software Factory Now | Don Syme, GitHub
18 Aug 2026
01:04:35
Turning every repo into a software factory sounds like marketing until you see the machinery underneath. Don Syme, Principal Researcher at GitHub, breaks down continuous AI and GitHub Agentic Workflows, now in public preview. The short version: the agents are the easy part, the quality gates and guardrails are the work.
Watch Don's AI DevCon Talk here: https://youtu.be/kbvqRWY-bUs
What we cover: – What continuous AI is, and why it sits beside CI/CD rather than inside it – Why bounding the context is what stops automated agents going off the rails – Whether the repo is really the right unit for a software factory, and where monorepos break it – One workflow or an agent zoo? Cost control, scheduling and model exams – Quality gates, human review, and equipping the reviewer instead of drowning them
Chapters: 00:00:00 - Introduction 00:03:52 - What is continuous AI? 00:07:33 - From single player to multiplayer automation 00:09:42 - Bounding the context so agents don't go off the rails 00:12:57 - Software factories, loops and harnesses 00:18:44 - Inside GitHub Agentic Workflows 00:25:19 - Why the repo became the unit of production 00:37:11 - What belongs in the repo, and what doesn't 00:45:07 - One workflow or an agent zoo? Cost control in the factory 00:52:01 - Quality gates, human review and equipping the reviewer
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
If you're building a software factory of your own, tell us in the comments where your bottleneck actually sits.
The Background Check You Can't Run on an AI Agent
11 Aug 2026
00:47:42
The thing that makes an agent useful is the exact thing that makes it dangerous. Keycard co-founder Ian Livingstone breaks down why non-determinism is both the feature and the bug, and why identity, not model quality, is what really gates how much autonomy you can hand an agent. If you have ever clicked "always allow" without reading it, this one is about you.
What we cover: – Why authentication was enough in the cloud era and stops being enough with agents – The background check you can't run on an agent, and what has to replace it – Mission identity: who is acting, on whose behalf, and for what purpose – Cross App Access, Agent Auth and the protocols trying to fix OAuth – Consent fatigue, LLM as a judge, and where hard boundaries still belong – Why MCP ships with an auth story and CLI tools don't
Chapters: 00:00:00 - Introduction 00:03:43 - Why every wave of computing rewrites identity 00:04:50 - The feature and the bug are the same thing 00:10:23 - Why shared secrets break for agents 00:13:36 - The background check you can't run on an agent 00:19:42 - Chargebacks, delegation and proving intent 00:22:16 - Mission identity: a new layer 00:28:07 - Cross App Access, Agent Auth and emerging protocols 00:33:02 - MCP vs CLI, and how Keycard works 00:43:22 - Identity three years from now
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
Where do you draw the hard line for your own agents? Tell us in the comments.
Datadog Deleted All Its AI Context. It Worked.
04 Aug 2026
01:01:23
Datadog's Language Foundations team deleted an entire folder of AI context files that had been carefully written and maintained for over a year, expecting a performance hit. Instead, their evals got better. Simon Boudrias, who runs Language Foundations at Datadog, walks Guy through what that taught his team about context rot, and the full journey of scaling AI coding agents to 4,000 engineers.
What we cover: – How Datadog scaled Cursor and Claude Code to 4,000 engineers in under a year – Why Datadog deleted all of its AI context files, and what happened to eval scores – Building an eval-driven code review system that replays old PRs to catch real incidents – Where open-weight models like GLM 5.2 stand against the frontier – Rethinking hiring and career ladders now that AI can run a real codebase interview
Chapters: 00:00:00 - Introduction 00:03:19 - Simon's role and Datadog's 4,000-engineer org 00:04:31 - The Cursor rollout that took off overnight 00:07:53 - How Claude Code entered the picture 00:10:51 - Building dedicated Signals and Flows teams 00:11:58 - Why Datadog bet early on evals 00:33:44 - Deleting all their AI context and getting better evals 00:47:51 - Where open-weight models stand today 00:51:45 - Rethinking hiring and career ladders for AI 00:59:24 - The real prize: better decisions, not just productivity
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
What's the oldest file in your AGENTS.md or CLAUDE.md that you're afraid to delete? Tell us in the comments.
Inside the Dark Factory: AI That Ships Code Solo
28 Jul 2026
00:58:38
At Tessl, 95% of the code shipped by their internal "Dark Factory" has never been looked at by a human, and the team still ships hundreds of pull requests a week, including through entire weekends. Rob Willoughby, who leads AI engineering at Tessl, joins Simon to open up the hood on how it actually works: the orchestrator, the verification layers, and the failures that forced the team to rebuild trust from scratch.
What we cover: – How Tessl routes 65-70% of its own pull requests through an autonomous "Dark Factory" – Why context in the repo matters more to output quality than which model you use – How natural language "verifiers" turn code review taste into fast, cheap checks agents can pass or fail – The queue bug that took dozens of pull requests to fix, and the from-scratch Elixir rewrite that stress-tested the whole system – How to start building your own software factory, one verification layer at a time
Chapters: 00:00:00 - Introduction 00:01:44 - Rob Willoughby joins: Tessl's PR numbers 00:04:01 - Live demo: kicking off two pull requests 00:14:03 - Building the Dark Factory: orchestrator vs. context 00:19:01 - Code review layers: Code Rabbit, Tessl Change Verify, and verifiers 00:29:58 - Earning trust: accountability in an autonomous system 00:33:20 - What broke: the queue bug and the Elixir rewrite experiment 00:39:56 - Onboarding new engineers into the factory 00:42:58 - Advice for teams starting their own software factory 00:52:03 - Back to the demo, and the road to 100% adoption
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
What would your own verification layer catch, and where would it break? Let us know in the comments.
BONUS: Snyk Found Malware Inside AI Agent Skills
23 Jul 2026
00:32:15
One Snyk developer's AI skill quietly handed their coding agent production credentials, and the security team found out the hard way. Krzysztof Huszcza, who leads AI security incubation at Snyk, joins this special Tessl and Snyk live stream to unpack the ToxicSkills research that uncovered 76 malicious agent skills in the wild, and what it actually takes to run coding agents safely at scale.
What we cover: – How Snyk's security team found 76 malicious skills hiding inside a popular open agent skill repository – Why skills have become the go-to way developers hand context to their coding agents – The internal incident at Snyk where a developer's skill exposed production credentials to an agent – How the Tessl and Snyk integration scans every skill and MCP server for risk before you install it – What's coming next with Snyk's new Evo product for governing coding agents at scale
Chapters: 00:00:00 - Introduction 00:01:33 - Chris's role: AI security incubation at Snyk 00:02:16 - Snyk's roots as a developer-first security company 00:03:58 - New security challenges from AI coding agents 00:06:26 - Skills: the new way to give agents context 00:07:35 - Inside Snyk's ToxicSkills research: malware and prompt injection 00:11:35 - How developers can vet skills before installing them 00:14:38 - A real incident: exposed production credentials at Snyk 00:17:45 - Building a secure-by-default agent stack 00:23:35 - What's next: Snyk's new coding agent security product
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
What's the riskiest skill you've installed without checking it first? Let us know in the comments.
From Living Room Hack to 30 AI Agents at Cyera
21 Jul 2026
01:06:03
An engineer builds an AI agent to manage his own life, decides an unrestricted "does everything" agent is too dangerous to trust, and ends up creating the internal agent platform that now runs 30 agents across his entire company.
Ori Shoshan, tech lead at Cyera, walks through the guardrails, citation system, and knowledge graph that turned "let the agent do anything" into "let the agent do exactly what it's supposed to, and nothing else."
What we cover: – Why one engineer built his own AI agent in his living room, and how it grew into Cyera's internal agent platform – Whitelisting tools instead of blacklisting them, plus the "escape hatch" that keeps agents honest – Backing every claim with a citation and using a second model to catch hallucinations before they reach a human – Trading RAG for a knowledge graph the agent can walk like a wiki – Turning "use this platform" into "build your own agent" to drive adoption across an entire engineering org – Running agents on confidential data that can investigate everything but can only ever say what's been cleared
Chapters: 00:00:00 - Introduction 00:02:04 - Meet Ori Shoshan and what Cyera does 00:06:50 - The living-room spark: why Ori built his own agent 00:11:09 - Whitelisting tools instead of blacklisting them 00:12:55 - Why every claim needs a citation 00:15:35 - Reducing hallucinations with clean-context verification 00:21:04 - Taking Borg to Slack: the first agents at work 00:25:33 - Why naming your agent drives adoption 00:39:53 - Knowledge graphs over RAG 00:52:00 - The AI Captains: scaling adoption with carrots, not sticks
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
Have you built guardrails like this into your own agents? Let us know what's worked (or blown up) for you in the comments.
Patrick Debois Maps the Patterns of AI-Native Dev
14 Jul 2026
00:47:38
After DevOps, Patrick Debois has a new map. The godfather of DevOps returns to walk through his AI patterns research: how he tracks where AI-native development is heading by mining social signals instead of surveys, why the stack is settling into patterns worth learning, and why your AI budget problem is really an optimization problem.
What we cover: – Inside the AI patterns site at Tessl.io/patterns and how it's auto-generated – The four layers of AI enablement: agent, team, platform, and organization – Solo, shared, and multiplayer modes: the compounding effect of shared context – Managing agent costs: budgets as a forcing function for optimization – Scaling adoption: find the success story, don't fight the skeptics – Hiring system thinkers instead of elegant coders
Chapters: 00:00:00 - Introduction 00:02:28 - Why AI grips Patrick Debois 00:04:33 - Agent, team, platform and org enablement 00:06:36 - Is AI-native development maturing? 00:11:19 - Inside the AI patterns site 00:18:14 - Quality, security and the IDE as review interface 00:22:45 - Changing roles and harness engineering 00:26:32 - Hiring in the AI era 00:30:31 - Scaling adoption across the org 00:42:03 - Cost management and ROI
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
Where is your organization on the maturity curve? Drop your take in the comments.
Inside Anthropic: How Claude Tag Is Changing Agentic Work
07 Jul 2026
00:57:31
Six people reacted to Boris's side-project Slack post. A year later, Claude Code is ubiquitous, and the company just launched its next evolution: Claude Tag, an AI teammate that lives in Slack.
Lamis Mukta, Member of Technical Staff at Anthropic, joins Simon Maple to unpack how Claude Tag works, why Anthropic built it, and what it took internally to go from a scrappy side project to a company-wide habit.
What we cover: – What Claude Tag actually is, and how it differs from Claude Code and Cowork – Why trust in AI agents is really a function of model capability, not just comfort – The internal "dogfooding" culture that shaped Claude Code and Claude Tag – How Anthropic secures multiplayer AI with agent identities and channel-level permissioning – Where Claude and Claude Tag show up outside of engineering at Anthropic – Dreaming: how Anthropic's managed agents continually improve their own memory
Watch Lamis' talk from AI Native DevCon London 2026 here: https://youtu.be/tTcxVv8HHNw
Chapters: 00:00:00 - Introduction 00:01:46 - Meet Lamis Mukta from Anthropic 00:02:56 - What is Claude Tag? 00:10:07 - From single-player to multiplayer agentic coding 00:15:50 - Trust, capability, and the METR chart 00:21:02 - How the industry is really using Claude Code 00:26:33 - The Claude Code origin story 00:33:47 - Agent identities and permissioning at scale 00:40:23 - Claude beyond engineering at Anthropic 00:48:16 - Dreaming and practical tips for rolling out Claude Tag
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
What's the one thing your team would delegate to an AI teammate first? Let us know in the comments.
The Tessl Agent: Build Your Software Factory on Autopilot
30 Jun 2026
00:52:52
What if the whole point of your AI agent was to eventually make itself redundant? Dru Knox, Head of Product at Tessl, introduces the Tessl agent — a new interface built not just for AI-assisted coding, but for building the software factory that keeps improving without constant human input.
This is a conversation about loop engineering: how to set up automated feedback cycles so your agents get smarter, your code review gets tighter, and your team ships more without adding more toil.
What we cover: – What the Tessl agent is and how it fits into the broader Tessl platform – Loop engineering: why building automated feedback loops is the right place to start – How the agent sets up and continuously improves agentic code review – Why optimising your AI agent costs is usually the wrong lever to pull – The case for open, modular software factories — and the risk of vendor lock-in – UX expectations in the AI era: why outcome-oriented interfaces are now the baseline
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
What's your approach to building feedback loops into your agent workflows? Drop a comment — we'd love to hear how teams are thinking about this.
Why Agents Are Forcing Enterprises to Finally Fix Their Dev Process
25 Jun 2026
01:00:10
Enterprises are finally being forced to care about their software development lifecycle — not because anyone suddenly got disciplined, but because agents cost money and the waste is now visible. When it was humans, it was "Timmy's just lazy." Now it's a line item.
Simon Maple sat down with Patrick Debois (the godfather of DevOps, now DevRel at Tessl), Tammuz Dubnov (co-founder and CEO of Autonomy AI), and Daniel Jones (Head of Product at re:cinq) at AI Native DevCon London for a wide-ranging panel on AI enablement — who owns it, what's breaking, and what the organisations getting it right are actually doing differently.
What we cover:
– Who should own agentic coding adoption inside an enterprise, and why platform teams are already filling the vacuum
– The "Timmy's lazy" problem: why agent cost visibility is forcing process discipline that humans never got
– Why PR-based workflows are an anti-pattern inside enterprises once you're moving at agent speed
– The PUMP framework (Plan, merge, polish): how one team is shipping features with developers, PMs, and designers all opening PRs –
Rethinking what a "test" is in an agentic world — and why feedback loops matter more than first-pass correctness
– The biggest mistake enterprises are making right now: piecemeal adoption with no mandate and no shared tooling
🔔 Subscribe for weekly episodes on AI-native development
What's your team's approach to AI enablement — central mandate or letting individuals find their own way? Drop it in the comments.
BONUS: DevCon London: Real Talk on AI ROI, Harnesses & Evals
23 Jun 2026
00:23:40
From the expo floor of AI Native DevCon London, Simon Maple went straight to the developers — speakers, attendees, and sponsors — to ask what's actually working with AI in 2026. The verdict? Outcomes beat outputs every time, 4,000-hour workloads are collapsing to 20 minutes, and the real bottleneck isn't code.
This is a conference floor walkthrough: honest, unscripted takes on harness engineering, evals, AI adoption mindsets, and the change management challenge that nobody talks about enough.
What we cover: – Why measuring token usage, code commits, and outputs will lead your team astray – How NearForm cut a 4,000-hour AML backlog to 20 minutes using agents – Harness engineering and evals as the developer skills that matter most in 2026 – Why change management — not tooling — is the missing ingredient for real AI ROI – How AutonomyAI is letting PMs and designers ship directly to production
Chapters: 00:00:00 - Welcome to AI Native DevCon London 00:01:03 - Chris Baty: Outcomes Over Outputs 00:05:15 - Martin: How Tooling Changed Everything 00:07:21 - Ryan: Harnesses, Evals and Skills 00:08:50 - Manny Saka: Plan Before You Prompt 00:11:58 - Cian O Maidin, NearForm: Real AI ROI 00:15:21 - Snyk: Building Trust at Scale 00:17:01 - AutonomyAI: Shipping Without Engineering 00:21:35 - Tessl Agent: Harness Engineering 00:22:41 - Closing Thoughts
🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development
Whether you're cautious or YOLOing it with AI — drop where you land in the comments.
AI Security & the Agent-Ready Web: Experts Weigh In
16 Jun 2026
01:02:55
What does it mean to build securely when agents can negotiate their own guardrails? And what happens to the web — CLIs, frameworks, even the browser itself — when the primary user is no longer human? At AI Native DevCon London, Simon Maple sat down with two panels of experts to find out.
First: a security roundtable with Joseph Katsioloudes from GitHub, Liran Tal from Snyk, and John Groetzinger from Cisco.
Then: a web AI conversation with Dana Lawson from Netlify, Maximiliano Firtman from codemia, and James Moss from Tessl.
What we cover:
– Why 83% of enterprises plan to deploy AI but only 29% feel ready to do so securely
– Prompt injection as a risk you have to accept — and how least privilege and sandboxing are your real defences
– The "agent experience" concept: why systems built for human eyes fail at machine scale
– Whether fundamentals like HTTP, semantic HTML, and accessibility still matter when agents do the heavy lifting
– How WebMCP lets websites expose tools directly to agents
— and why blocking them is like trying to turn off the sun
Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week
09 Jun 2026
00:55:28
Most engineering teams are still arguing about whether to use AI coding agents.
Ryan Lopopolo's team at OpenAI shipped an entire product with no human-written code — and onboarding a new engineer made the team faster within two weeks.
That outcome didn't come from better prompts. It came from what Ryan calls Harness Engineering: the systems, constraints, and feedback loops that sit around the agent — the context it sees, the tools it can call, the tests and linters that close the loop, and the asynchronous CI jobs that catch slop before it compounds.
We sat down with Ryan at AI Native DevCon London 2026, and he got into the specifics: how his team went from 3.5 PRs per engineer per week to 70, why he inverts spec-driven development (build the code first, distill the spec second), and what he means when he says it's "borderline negligent" not to use a billion tokens a day.
It's one of the most grounded, production-focused conversations we've had on The AI Native Dev. The trailer is live now — and the full episode drops this week.
Engineering teams are shipping twice as many pull requests with AI — but merge rates on AI-generated PRs have dropped from 80% to 60%.
Nick Arcolano, Head of AI & Research at Jellyfish, sits on one of the most comprehensive datasets in the industry: 250,000 developers, 40 million data points, monthly benchmarks on real agentic coding adoption across enterprise companies. What he's seeing in that data is both more promising and more complicated than the headlines suggest.
What we cover:
Why experienced engineers hit a hard ceiling at 4 concurrent agents, and what it would take to break through it
The 80/20 vs 60/40 merge rate gap between human and AI-generated pull requests — and what's actually causing it
How AI adoption reached 71% weekly active usage across 250K developers, and what "depth of use" really means
Why 2026 is the year the CFO gets involved — and how engineering leaders should prepare to show their receipts
The biggest misconception engineering leads have about what it takes to get to true AI-native development
Why companies have jet engines but are still building cars, and what the real architectural changes look like
🔔 Subscribe for weekly episodes on AI-native development
If you're an engineering leader trying to make sense of the gap between the AI hype and what's actually showing up in production, drop your take in the comments.
Don't Secure the Code. Secure the Coder.
26 May 2026
00:40:01
AI agents don't just write insecure code — they can escape their sandboxes, delete files, and do whatever it takes to complete a task. The security mental model that served us through the cloud era isn't enough anymore. Guy Podjarny, founder of Snyk and CEO of Tessl, made the case at London's AI Security Summit: it's time to stop securing the code and start securing the coder.
Recorded live at the AI Security Summit in London, this episode features conversations with Brian Vermeer (Snyk), Sam Stepanyan (OWASP London), and a full recording of Guy's keynote on why agentic development demands a fundamentally different approach to security.
What we cover:
Why shadow AI is the new shadow IT — and why CISOs can't secure what they can't see
Skills as a new supply chain attack surface (malicious, vulnerable, and negligent skills)
Why more context is not always better — and what the data says about focused skill design
The OWASP Top Ten for Agentic AI and what it means for teams building today
Why security must become agentic to keep up with the attackers who already are
The Context Development Lifecycle (CDLC) and how leading orgs are using it
Subscribe for weekly episodes on AI-native development
What's the biggest security risk your team isn't talking about when it comes to agentic development? Drop it in the comments.
The Hidden Security Risks of AI Coding Agents
19 May 2026
00:41:10
Your AI coding agent has access to your secrets, pulls in content from the outside world, and can run shell commands. According to Joe Holdcroft, that combination makes you one prompt injection away from a very bad time. The tools haven't changed the fundamentals of security — they've just made every existing risk move faster, and introduced a few genuinely new ones. What we cover:
Why the "lethal trifecta" of agent capabilities creates a novel threat surface
How text and markdown files have become a new class of vulnerability
Slop squatting: the attack vector created by agents hallucinating package names
The context supply chain — and why it mirrors the early days of npm security
What a "CBOM" (context bill of materials) might look like and why we may need one
How to think about agent trust using the contractor mental model
Chapters:
00:00 Introduction
01:40 The Lethal Trifecta: why agents are inherently risky
03:23 Same hygiene, higher stakes
04:08 Text as a vulnerability: markdown as a security risk
06:08 Do AI tools make you more or less secure?
08:09 Snyk + Tessl: scanning skills in the registry
10:10 The context supply chain problem
14:28 The CBOM: do we need a context bill of materials?
17:35 Secrets, credentials, and principle of least privilege
22:25 Balancing security with developer velocity
36:54 One piece of advice for CTOs going all-in on AI
Subscribe for weekly episodes on AI-native development
If you're thinking about AI governance in your team, drop a comment — how are you handling context supply chain today?
"AI Doesn't Stand for Artificial Intelligence" — Venkat Subramaniam's Take Will Change How You Think About It
12 May 2026
00:52:45
Is AI actually intelligent — or just very fast at guessing based on bad data?
Venkat Subramaniam, 40-year programming veteran, educator, and co-founder of Arc of AI, joins the AI Native Dev Podcast to share a perspective that cuts through the hype: AI stands for Accelerated Inference — not Artificial Intelligence. And that reframe changes everything about how developers should use it.
In this episode, Venkat unpacks why the speed of AI generation has outpaced our ability to review it, why you can delegate work to AI but never your reputation, and tells the story of a $2 million feature that got cancelled with one simple question: "Why are we building this?"
🔑 Topics covered:
— Why "Accelerated Inference" is a more honest name for AI
— The code quality crisis AI has inherited from decades of bad human code
— Accountability, lawsuits, and professional responsibility in the AI era
— What makes a senior developer
— and why AI widens that gap
— The one question that should precede every feature decision
— Why vibe coding is the most overrated AI trend right now
🎙️ Guest: Venkat Subramaniam — author, educator, and co-creator of Arc of AI
🎙️ Host: Simon Maple
📅 Recorded live at Arc of AI, Austin
🔔 Subscribe for weekly conversations with practitioners (not vendors) building with AI.
🎧 Listen on Spotify / Apple Podcasts — search "AI Native Dev"
🌐 Community & events: tessl.io/community
The Creator of Spring Thinks You Can't Code Serious Software With AI
05 May 2026
00:56:36
Rod Johnson — the creator of Spring Framework and founder of Embabel — joins Simon Maple on the AI Native Dev Podcast to share his unfiltered take on where enterprise AI is actually heading.
In this episode, Rod breaks down why enterprises are making a huge mistake rewriting Java apps in Python, why vibe coding will destroy your codebase if left unchecked, and why this might be the last generation of frameworks that developers ever choose for themselves.
Rod also pulls back the curtain on Embabel — the new JVM-native agentic framework he's building — including how it borrows its planning algorithm from NPC AI in video games, why he's skeptical of MCP despite its hype, and the AI failure pattern he keeps seeing in large enterprises.
Whether you're a Java developer navigating the AI wave or a tech lead trying to figure out where to actually invest, this is essential listening.
Topics covered: 0:00 Intro — Rod Johnson, Spring creator, returns to building 5:16 PhD in 19th century Parisian piano music (yes, really) 6:15 What made Rod come back and build Embabel 7:36 "The universe would end before Python could execute inference" 13:08 The #1 enterprise AI failure pattern Rod keeps seeing 16:23 "You cannot vibe code serious software" 19:37 Why Embabel uses a video game NPC planning algorithm 27:47 Why Rod is an MCP skeptic 53:54 "This is the last wave of frameworks chosen by people"
Links: 🔗 Embabel: https://embabel.com
🎟 AI Native Dev London (June 1–2): https://ainativedev.io — use code POD30 for 30% off.
Subscribe for weekly conversations with the engineers and founders building the future of AI-native development.
What OpenAI, Stripe & ElevenLabs Devs Do Differently Now | AI Native Dev
28 Apr 2026
01:05:51
How aligned are teams at Google DeepMind, OpenAI, Stripe, and ElevenLabs on what’s changing in software development?
At AI Engineer London, with 100+ speakers and 1000+ engineers in the room, Simon Maple pulls together perspectives from across the ecosystem to understand where AI-native development is heading.
• why traditional CI/CD “is dead” • the growing need for automated code review and guardrails • the move from more context is better to right context at the right time • the difference between general-purpose models vs specialized domain models
Logan Kilpatrick on Who Ships AGI, DeepMind and the Problem With More Software
21 Apr 2026
00:38:16
"If you could have a system that could build anything with code, humans can't compete on the same level. That's narrow superintelligence, and we're close."
In this episode of AI Native Dev, Simon Maple sits down with Logan Kilpatrick, who spent years at OpenAI working alongside Sam Altman before moving to Google DeepMind as Group Product Manager.
They get into:
There will be 100x more developers in the world because of AI
AGI will be a product, not a model
The way you used AI tools three months ago is already wrong
What's actually changing inside the Gemini team and why it matters for developers building with it today
The developers who win won't be the ones who mastered today's tools. They'll be the ones who never stopped learning the new ones.
Everything 100 Episodes Revealed About AI Native Dev
14 Apr 2026
00:56:32
When did writing code stop being the job and start being the hobby?
One hundred episodes in, Guy Podjarny and Simon Maple pull the clips, check the predictions, and trace the through line across conversations with guests from Datadog, ElevenLabs, GitHub, and more.
They get into:
The move from spec-driven to context-driven development
Why humans become the bottleneck in code review
What changes when agents run the SDLC end-to-end
Adoption across orgs vs depth of actual usage
Thanks to every guest and every listener who made this possible. On to the next hundred.
Want to have these conversations in person? AI DevCon is coming to London on 1st and 2nd June, 2026.
How DeepSeek leveraged Qwen and Llama to build its model in $5M
07 Apr 2026
00:39:30
Meta’s Llama might not actually be open source AI, and the developers building on it have no idea.
In this episode of AI Native Dev, Simon Maple sits down with Amanda Brock, CEO of OpenUK, to break down what open source actually means in the age of AI and why most of the industry is getting it wrong.
They get into:
what open washing is and why it is happening across major models right now
how DeepSeek built a frontier model for $5 million instead of $100 million
why Chinese developers are already on Kimi and the west is sleeping on it
what the west needs to learn from China's open source strategy before it is too late
Eight companies already control the world's digital infrastructure. We cannot let that happen again with AI.
Why Every Developer needs to know about WebMCP Now
31 Mar 2026
01:00:24
An agent cannot read your website. And that needs to change.
In this episode of AI Native Dev, Guy Podjarny sits down with Maximiliano Firtman, 30-year web developer and author of 14 books, to talk about what building for the web looks like when traffic comes from agents and humans both.
They get into:
why AI agents taking screenshots of your website is inefficient and expensive
what Web MCP is and how it gives agents a direct API into your website
how a 200MB Apple model running offline is opening up a whole new category of web apps
why every vibe coded app is a web app and what that means for the future of the web
Your next visitor might not be human. Are you ready for that?
"The code that we have is a liability. The system is the asset we're building."
Chad Fowler, VC at Blue Yard Capital and former CTO at Wunderlist, sits down with Guy Podjarny to discuss the Phoenix Architecture: software designed to be replaced rather than maintained.
In this episode: • why was the code written by Chad never longer than a page • how he replaced 70% of a codebase in 3 months and cut costs by 75% • shipping AI code no human ever reviewed, and how to make it safe • the shadow specs your agents are making without you • why your system should work with the worst LLM, not just the best
If you're still thinking about your codebase the old way, this one will change that.
We Scanned 3,984 Skills — 1 in 7 Can Hack Your Machine
17 Mar 2026
00:34:43
Most developers install skills without reading what's inside them. But that's exactly what attackers are counting on.
Simon Maple sits down with Brian Vermeer from Snyk at DevNexus to get into the security risk hiding inside the skills and MCPs running on your local machine. They scanned over 4,000 skills and found that 1 in 7 had at least one critical security vulnerability.
Here’s what you need to know:
Why prompting your agent to write secure code doesn't make it secure
How a trusted skill can update silently and start offloading your credentials
What prompt injection actually looks like inside a skill file
Why vibe coding makes the attack surface bigger, not smaller
How the Snyk agent scan catches what you'd never spot manually
Every skill on the Tessl registry now has a Snyk security scan attached. Check before you install.
The Greatest Time to Build a Startup (The AI-Native Advantage)
10 Mar 2026
01:01:23
The best agentic developers throw away their agent's work without guilt, run three agents at once and only use one, and treat their AI like a junior developer they genuinely dislike. It sounds wrong. It works.
Daniel Jones, Head of Product at re:cinq, has upskilled hundreds of developers across Northern Europe's largest enterprises. In this episode he joins Simon Maple to share the counterintuitive habits, hard data, and practical frameworks behind high-performing agentic development teams.
On the docket:
Why bad engineering practices get worse, not better, with AI agents
The exact conditions that make your agent hallucinate every time
Why your AGENTS.md is quietly working against you
How to manage context before it kills your productivity
What enterprise AI rollout actually looks like at scale
Why the worst managers get the most out of agentic coding
If your team is adding AI and wondering why things aren't getting faster, this episode is for you.
Richmond Alake, Director of AI Developer Experience at Oracle, joins Simon Maple to make the case that most agent failures come down to one thing: memory. Not the model, not the infrastructure. Memory.
On the docket:
why skills are just SOPs your organisation already has written down
the job title that is replacing prompt engineers
file systems vs databases for agent memory (and why one gets you hacked)
the memory trick that makes agents feel actually intelligent
why the agent loop and training loop are about to become one
The developers who figure this out first are going to be very hard to compete with.
Cisco Principal Engineer's Fix for AI Code Security
25 Feb 2026
00:33:28
Your AI coding agent learned from millions of lines of code, including insecure ones. That means by default, it can write vulnerable code too.
So how do you fix that?
John Groetzinger, Principal Engineer at Cisco, built CodeGuard, a security skills layer that teaches coding agents how to write and review code securely. He tested it against real scenarios.
The result: 84% success rate vs 47% baseline. Nearly 2× improvement.
In this episode we get into:
how CodeGuard works
why Cisco open sourced it
the surprisingly simple method that gets agents to fix their own mistakes
Try CodeGuard: cisco/software-security on the Tessl registry.
Connect with us here: John Groetzinger: https://www.linkedin.com/in/john-groetzinger/ Cisco: https://www.linkedin.com/company/cisco/ Simon Maple: https://www.linkedin.com/in/simonmaple/ Tessl: https://www.linkedin.com/company/tesslio/
Why Context Beats Every Prompt You'll Ever Write
17 Feb 2026
00:30:35
Most teams think agentic dev is about writing better prompts. It's not.
Guy Podjarny and Simon Maple explain why managing context, not crafting prompts, is what separates teams that scale with agents from teams that don't. They walk through a practical framework for building, evaluating, and distributing the context your agents actually need.
In this episode: • Why agents fail without structured context about your internal platform • The 3 context layers: policies, platform docs, and application context • How to build regression evals and torture tests for your agents • The Context Development Lifecycle (CDLC) - a new loop for agentic dev
Your agents are only as good as the context you give them.
From IBM Acquisition to AI-Native Observability | Dash0 CEO
10 Feb 2026
00:55:56
"Charts are good for users, not good for agents. Agents look at the underlying data and do deep analysis."
Mirko Novakovic built Instana, sold it to IBM, and now he's building Dash0, rethinking observability for agents, not humans.
In conversation with Guy Podjarny, he explains: • why OpenTelemetry turned out to be perfect for AI • how UX changes when agents are your primary users • why interactive collaboration beats static chat outputs • the survival question for observability vendors in the AI era
Only 2-3 people in most companies can truly debug production. That knowledge lives in their heads and disappears when they leave. Mirko's betting agents will change that.
One skill took coding success from 28% to 71%. Another made things worse.
Guy Podjarny and Simon Maple tested 1000+ agent skills and reveal which ones actually work, which hurt performance, and why anecdotal evidence isn't enough anymore.
Tessl Skills Registry is the first package manager for agent skills with built-in evaluations, versioning, and lifecycle management. Explore tested skills and see real performance data: https://tessl.io/registry
On the docket: • Claude roasted Anthropic's own skill with a 27% score ("monolithic wall of text") • Why some popular skills actually decrease agent performance • How Tessl is bringing package managers and evals to agent skills
Whether you're creating your first skill or managing them across your dev team, this is your roadmap for making agent skills actually work.
The Developer Skills That Will Actually Survive AI
27 Jan 2026
00:56:05
“You have to prioritize between the thing you want to do and the thing that actually is driving the business, that’s what really big companies are fighting every single day.”
As former CEO of GitHub and now a startup founder again, Thomas Dohmke brings a rare, inside-out perspective on innovation across both worlds.
In conversation with Guy Podjarny, he explains: • why startups and incumbents fight in different weight classes • why humans shouldn’t sit in every feedback loop as agents scale • the importance of learning as a core skill for future developers
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
How Too Much Information Destroys Agent Performance
20 Jan 2026
00:20:18
Most AI agents fail because you're using them wrong. Here’s what actually works in production.
In this episode, Simon Maple sits down with Itamar Friedman (CEO of Qodo) and Robert Brennan (CEO of OpenHands) at QCon AI. They pull back the curtain on why agents hallucinate, provide inconsistent answers, and ship low-quality code.
On the docket: • Why a third of developer-reported AI output is incorrect • Why you must separate creative coding agents from structured review agents • How excessive information destroys agent performance • Parallelizing agents across 1,000+ repositories to resolve CVEs and legacy debt
Recorded live at QCon, this one's straight from architects building the future of the AI-native dev cycle.
In this special milestone episode, Simon Maple and Guy Podjarny celebrate 1 million views by looking back at the chaos of 2025 and forecasting the high-stakes reality of 2026.
On the docket: • Why appearing on this show has become a leading indicator for getting acquired or raising billions (and whether Simon should start charging a 2% carry). • The end of prompt engineering and the rise of context as the ultimate competitive advantage. • Our boldest 2026 predictions, including open models taking enterprise share and AI coding going truly multiplayer.
Whether you're building a solo unicorn or leading an enterprise team, this is your roadmap for staying ahead of the 2026 AI curve.
What AI Engineering Looks Like at Meta, Coinbase, ServiceTitan and ThoughtWorks
06 Jan 2026
01:12:37
What does it take to make AI work inside engineering teams?
This high-stakes compilation episode with Ian Thomas (Meta), Wesley Reisz (ThoughtWorks), Sepehr Khosravi (Coinbase), and David Stein (ServiceTitan) goes inside the engineering rooms of the world's most sophisticated tech organisations to uncover how they're moving past AI hype into AI-native production.
On the docket: • How Meta achieved 80% weekly AI adoption through grassroots community building instead of top-down mandates • Why ThoughtWorks uses the RIPPER-5 framework to structure AI workflows and prevent agents from jumping straight to code • When Coinbase engineers use Cursor versus Claude Code and why sub-agents are critical for managing context without bloat • How ServiceTitan migrated 247 legacy metrics in three weeks using self-healing validation loops and standardized agent tasks
If you're trying to make AI useful inside your team, this episode shows exactly what matters.
What Developers Need To Know About Agents Before 2026
30 Dec 2025
00:46:45
2025 changed what it means to be a developer.
And 2026 is about to change even more.
This Tessl episode brings a year-end reflection on how agents reshaped software development and what developers need to unlearn next, featuring Reuven Cohen, Founder of the Agentic Foundation, Maor Shlomo, Founder of Base44, and Maksim Shaposhnikov, Technical Member at Tessl.
On the docket: • Reuven Cohen on why most agent systems fail and what agentic engineering demands • Maor Shlomo on where vibe coding works, where it breaks, and how guardrails protect long-term software • Maksim Shaposhnikov on developer autonomy, IDE vs terminal agents, and designing for delegation
This episode looks ahead to 2026 and examines the systems developers will be responsible for next.
Why Faster AI Development Often Increases Rework | Cian Clarke
23 Dec 2025
00:54:02
Vibe coding is only good at creating a sense of progress for devs.
In this episode of AI Native Dev, Cian Clarke, head of AI at Nearform, joins Simon Maple to talk about BMAD, their spec-driven approach that prioritizes clarity before code over prompt first development.
They also get into: • speed upfront vs. maintainability over time • why senior engineers gain leverage as junior pathways narrow • the cultural shift needed to scale AI-generated software beyond solo builders
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Building an AI Agent in 100 Lines of Code | Yaniv Aknin
16 Dec 2025
00:42:40
Before you add context, understand the context that’s already there.
In this episode, Yaniv Aknin, founding engineer at Tessl, explains the built in instructions that precede every user prompt, and why acknowledging that hidden layer is critical.
On the docket: • why tool design matters more than raw reasoning ability • how Codex does more with fewer tools • how subagents let Claude stay flexible under context pressure • why generalist models may adapt better to unfamiliar tools
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here: 1. Yaniv Aknin- https://www.linkedin.com/in/yanivaknin/ 2. Simon Maple- https://www.linkedin.com/in/simonmaple/ 3. Tessl- https://www.linkedin.com/company/tesslio/ 4. AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/
How New Libraries Saw a 50% Improvement | Maria Gorinova
09 Dec 2025
00:40:56
We’re holding probabilistic systems to deterministic standards.
In this episode of AI Native Dev, Simon Maple talks with Maria Gorinova, Member of Technical Staff at Tessl, about the mismatch between how developers expect software to behave, and how agents actually do. • how structured context improves abstraction use • why agent reliability can only be demonstrated through measurement • how Tessl’s tiles improve reliability without bloating context
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Check out the article - https://tessl.io/blog/proposed-evaluation-framework-for-coding-agents/
Connect with us here: 1. Maria Gorinova- https://www.linkedin.com/in/mariagorinova/ 2. Simon Maple- https://www.linkedin.com/in/simonmaple/ 3. Tessl- https://www.linkedin.com/company/tesslio/ 4. AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/
Agent Experience Is the New Developer Experience | Sean Roberts
03 Dec 2025
00:30:00
Your codebase already has AI contributors. If they don’t understand it, that’s on you.
In this segment from AI Native DevCon, Sean Roberts, VP of Applied AI at Netlify, explains why agent experience is, in fact, an extension of developer experience.
He also shares:
why hallucinations are what inference looks like when context is missing.
why knowledge graphs matter for large codebases.
using feedback loops to help agents learn from real deployments.
the downside of standardising on a single agent
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
What Holds Devs Back From Multi-Agent Thinking | Guy Podjarny
26 Nov 2025
00:33:16
LLMs don’t get smarter when you dump everything into context, they get distracted.
At AI-Native DevCon, Guy Podjarny unpacks the evolution of AI augmented development, and how devs can get the most from current tools.
On the docket: • how to help agents close the capability-reliability gap • why 'context engineering is basically the same as specs.' • why statistical measurement is the only meaningful way to judge agent reliability. • how ‘tiles’ level inconsistent documentation across old and new libraries.
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here: 1. Guy Podjarny- https://www.linkedin.com/in/guypo/ 2. Simon Maple- https://www.linkedin.com/in/simonmaple/ 3. Tessl- https://www.linkedin.com/company/tesslio/ 4. AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/
Join our AI Native Dev Community: https://discord.com/invite/jbb2vHnHZQ?utm_source=footer&utm_medium=tessl+website&utm_campaign=community
The Hidden Vulnerabilities Behind AI Code | René Brandel
18 Nov 2025
01:01:02
If software can improve autonomously, why shouldn’t security?
On this episode of AI Native Dev, René Brandel, founder and CEO of Casco, explores how upfront specs enable reliable agent generated software, and how that same discipline drives Casco’s autonomous, continuously improving security.
On the docket: • how small teams with self-improving agents can outperform large security orgs. • why vibe coding is ideal for rapid prototyping and live customer iteration. • what a practical, scalable specification format must solve for in real workflows.
Connect with us here: 1. René Brandel - https://www.linkedin.com/in/renebrandel/ 2. Simon Maple - https://www.linkedin.com/in/simonmaple/ 3. Tessl - https://www.linkedin.com/company/tesslio/
What Developers Can Build Next With AI
12 Nov 2025
01:09:13
In this compilation, Simon Maple brings together Baruch Sadogursky (TuxCare), Liran Tal (Snyk), Alex Gavrilescu (Greentube), and Josh Long (Broadcom) to break down where AI-assisted development fails, and what teams must do to keep it reliable.
On the docket: • why spec-compiled tests must come before letting AI generate code • the uncertainty around what “AI security engineering” actually means today • how Backlog.md stays minimal so agents can split work autonomously • how Spring shows AI plugging straight into the business logic companies already run on Spring microservices
Connect with us here: Baruch Sadogursky- https://www.linkedin.com/in/jbaruch/ Liran Tal- https://www.linkedin.com/in/talliran/ Alex Gavrilescu- https://www.linkedin.com/in/alexandrugavrilescu/ Josh Long- https://www.linkedin.com/in/joshlong/ Simon Maple - https://www.linkedin.com/in/simonmaple/ Tessl - https://www.linkedin.com/company/tesslio/