The AI Native Dev – from Copilot today to AI Native Software Development tomorrow

1. Edith Harbaugh: Code Is Cheap. The Last Mile Isn't.

   10 de noviembre de 202649 minTemporada 1 · Episodio 131A continuación

   Automated software delivery is moving faster than the people who used to approve every release. LaunchDarkly co-founder and CEO Edith Harbaugh tells Guy Podjarny why rollback should be autonomous, why one-shot …

   Notas del episodio

   Automated software delivery is moving faster than the people who used to approve every release. LaunchDarkly co-founder and CEO Edith Harbaugh tells Guy Podjarny why rollback should be autonomous, why one-shot coding agents fail, and why the bottleneck has moved to the last mile.
   
   What we cover:
   – How automated software delivery and autonomous rollback take humans out of the 2 a.m. incident
   – What makes a good feature flag, and when a homegrown system stops being enough
   – Why coding agents need an explicit definition of success before they write a line
   – Where release management fits in an AI software factory
   – Feature flags for AI agents: switching models and prompts at runtime
   – Running a company in the agentic coding era, and why teams should take dumb bets
   
   Chapters:
   00:00:00 - Introduction
   00:02:16 - From quarterly releases to 30,000 changes a day
   00:03:32 - Autonomous rollback and automated software delivery
   00:06:25 - What makes a good feature flag
   00:10:46 - Defining success for coding agents
   00:16:42 - Agent fleets and engineers as reviewers
   00:24:05 - Feature flags in the software factory
   00:29:02 - The bottleneck moves to the last mile
   00:39:24 - Runtime controls for AI agents
   00:44:26 - Running a company in the agentic coding era
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/e0p
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Where has the bottleneck moved in your team's automated software delivery? Tell us in the comments.

   Transcripción

2. Maggie Appleton: Agentic Coding Has Outgrown the Text Box

   3 de noviembre de 202652 minTemporada 1 · Episodio 130A continuación

   Agentic coding has outgrown the text box. Maggie Appleton, staff research engineer at GitHub Next, argues that walls of CLI output and AGENTS.md files serve coding agents far better than the humans steering …

   Notas del episodio

   Agentic coding has outgrown the text box. Maggie Appleton, staff research engineer at GitHub Next, argues that walls of CLI output and AGENTS.md files serve coding agents far better than the humans steering them. She walks through Chopin, the GitHub Next prototype where background agents turn a team's planning chat into a structured plan, and makes the case for agents that prompt you instead of waiting to be prompted.
   
   What we cover:
   – Why text-heavy agentic coding tools favor agents over humans
   – Boundary objects: what AGENTS.md, skill files and MCP servers get right and wrong
   – Multiplayer planning with coding agents in GitHub Next's Chopin
   – Human-to-agent handoffs, formal verification and spec-driven development
   – Why software quality is rising, not falling, with coding agents
   – Which roles still matter: PMs, designers and engineers
   
   Chapters:
   00:00:00 - Introduction
   00:02:14 - Inside GitHub Next and the Chopin project
   00:05:57 - Why solo agents break team alignment
   00:07:52 - Why coding agents struggle with design
   00:12:16 - Boundary objects: AGENTS.md, skills and MCP
   00:18:27 - Planning with coding agents as collaborators
   00:26:49 - Multiplayer planning with background agents
   00:31:57 - Agent handoffs and spec-driven development
   00:37:41 - Quality, craft and who decides what to build
   00:44:29 - Starting a career in agentic coding
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/j3d
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Should coding agents be prompting you more? Tell us in the comments how your team plans agentic coding work today.

   Transcripción

3. Caleb Sima: AI Attackers Move at Machine Speed

   27 de octubre de 202655 minTemporada 1 · Episodio 129A continuación

   AI attackers now move at machine speed, while most security teams still move at meeting speed. Former Robinhood CSO Caleb Sima has seen an AI attacker up close, and he argues the only way to keep up is to take …

   Notas del episodio

   AI attackers now move at machine speed, while most security teams still move at meeting speed. Former Robinhood CSO Caleb Sima has seen an AI attacker up close, and he argues the only way to keep up is to take humans out of the defense loop.
   
   Caleb joins Guy Podjarny to unpack what changes when the attacker is an agent: one that hits every surface at once, reverses open-source code to find a 0-day, and once inside, burns your own AI tokens to keep going.
   
   What we cover:
   – Why AI attackers outran the red teamers' predictions, including 400 Linux 0-days found at 2.5 hours each
   – Whether sandboxes can contain AI agents, and why external monitoring matters
   – Who is accountable when your AI agent hacks someone else
   – What actually changes when an AI attacker gets inside your company
   – Deception, digital twins and forensic-grade detection
   – Automating security: instant patching, one-way vs two-way doors, and security teams that ship the fix
   
   Chapters:
   00:00:00 - Introduction
   00:02:58 - AI security goes mainstream
   00:05:52 - Why AI attackers surprised the red teamers
   00:12:50 - Can sandboxes contain AI agents?
   00:18:03 - Security vs safety vs alignment
   00:22:18 - Who's accountable when your AI agent hacks?
   00:29:00 - What changes when an AI attacker hits you
   00:36:47 - Detection, forensics and deception
   00:44:10 - Machine speed vs meeting speed: automating defense
   00:48:53 - Security teams that ship the fix
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/9ja
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Are your defenses ready for AI attackers, or still running at meeting speed? Tell us in the comments.

   Transcripción

4. Your Coding Agent Should Never Hold a Credential

   22 de octubre de 202630 minTemporada 1 · Episodio 128ExtraA continuación

   Your coding agent should never hold a credential, and in a software factory that rule is only the start. Recorded live at the AI Security Summit in San Francisco, Simon Maple sits down with Eli Aleyner …

   Notas del episodio

   Your coding agent should never hold a credential, and in a software factory that rule is only the start. Recorded live at the AI Security Summit in San Francisco, Simon Maple sits down with Eli Aleyner (Docker), Marcelo Sousa (Snyk) and Ian Livingstone (Keycard), co-authors of Agent Baseline, a security reference architecture for the AI software factory.
   
   The panel unpacks why agents have to be treated as fundamentally unpredictable actors, why sandboxing alone is not enough when skills and MCP servers make the supply chain dynamic, and why approval prompts collapse into fatigue. Marcelo's verdict: sometimes these are kids with chainsaws.
   
   What we cover:
   – The three levels of autonomy, from coding agents to fully agent-directed workflows
   – Sandboxing coding agents and injecting secrets at the egress point
   – Why the agent supply chain is dynamic: skills, MCP servers and cloned repos
   – Prompt injection, least privilege and agents monitoring other agents in the harness
   – Approval fatigue: YOLO mode vs CYA mode
   – Where to start securing your software factory on Monday morning
   
   Chapters:
   00:00:00 - Introduction
   00:03:14 - What Agent Baseline is and who it's for
   00:04:17 - The three levels of software factory autonomy
   00:06:53 - Sandbox boundaries and manufacturing trust in agents
   00:09:22 - Why coding agents should never hold credentials
   00:11:44 - The dynamic agent supply chain: skills and MCP servers
   00:14:57 - Untrusted input, least privilege and agents watching agents
   00:18:02 - Approval fatigue: YOLO mode vs CYA mode
   00:20:22 - Are poisoned agent skills a supply chain problem?
   00:22:45 - Where the panel disagreed, and where to start Monday
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/gsh
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Which level of the software factory are you at today, and what are you locking down first? Tell us in the comments.

   Transcripción

5. Snyk's Manoj Nair: Skills and MCP Are the New npm

   20 de octubre de 202647 minTemporada 1 · Episodio 128A continuación

   Skills and MCP servers are the new npm, and AI coding agents are pulling them into enterprise codebases faster than security can keep up. Manoj Nair, Chief Innovation Officer at Snyk, joins Guy Podjarny at the …

   Notas del episodio

   Skills and MCP servers are the new npm, and AI coding agents are pulling them into enterprise codebases faster than security can keep up. Manoj Nair, Chief Innovation Officer at Snyk, joins Guy Podjarny at the Snyk AI Security Summit to map where enterprise agentic coding really stands.
   
   They get into why a 50,000-agent Claude Code rollout was pulled forward by weeks, why the autonomous attacker has some CISOs ready to accept an outage to patch faster, and how security is moving into the agent loop of the software factory.
   
   What we cover:
   – Why leadership and culture, not tooling, decide how fast enterprises adopt AI coding agents
   – The three risks of agentic coding: insecure output, the skills and MCP server supply chain, and agent behavior
   – Running coding agents locked down: sandboxes, agent identities and no open internet
   – Who owns the code an agent writes, and why AI-native organizations treat it as shared risk
   – Securing the software factory: security context in the agent loop and agentic remediation of the backlog
   – What still has to be solved before enterprises trust agents: identity, intent and behavior
   
   Chapters:
   00:00:00 - Introduction
   00:01:50 - The state of enterprise AI and agent adoption
   00:09:45 - Leadership, culture and a 50,000-agent rollout
   00:11:18 - Agentic coding risks: output, supply chain, behavior
   00:14:29 - Locked-down coding agents and the security trade-off
   00:18:01 - Who owns agent output? Compliance and accountability
   00:22:54 - The autonomous attacker and security technical debt
   00:27:56 - Securing the product vs securing the software factory
   00:33:00 - Agentic remediation and the security backlog
   00:40:18 - What enterprises need to trust AI coding agents
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/jw0
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Where is your organization on the path from copilot to AI coding agents? Tell us in the comments.

   Transcripción

6. Maria Gorinova: Feedback Loops That Fix Your Codebase

   13 de octubre de 202638 minTemporada 1 · Episodio 127A continuación

   Agent feedback loops are how a software factory maintains itself: agents mining their own session logs, PR comments and production signals, then fixing what they find. Maria Gorinova, member of technical staff …

   Notas del episodio

   Agent feedback loops are how a software factory maintains itself: agents mining their own session logs, PR comments and production signals, then fixing what they find. Maria Gorinova, member of technical staff at Tessl, explains how to build them, and why vague intent turns a loop into a mess.
   
   What we cover:
   – What a software factory is: repeatable workflows, a shared execution environment and agent feedback loops
   – Why agent context alone isn't enough, and where harness engineering comes in
   – The three stages of a feedback loop: analyze a data stream, find the problem, request the fix
   – Inner, middle and outer loops, from verifiers on every PR to self-healing in production
   – How Tessl's "comment diet" loop catches drift that no single PR causes
   – Operators and stewards: the human roles in a software factory
   
   Chapters:
   00:00:00 - Introduction
   00:02:36 - What is a software factory?
   00:05:38 - From agents to context to harness engineering
   00:09:15 - The three stages of an agent feedback loop
   00:13:16 - Inner, middle and outer feedback loops
   00:18:35 - Why vague intent breaks agent feedback loops
   00:21:50 - Comment bloat, drift and the rule of three
   00:25:48 - The software factory mindset
   00:27:45 - Loops, feedback loops and meta feedback loops
   00:32:45 - Operators, stewards and building your first loop
   
   Build your software factory, one workflow at a time, with Tessl:
   https://tessl.co/2uf
   
   🔔 Subscribe for weekly episodes on AI-native development
   
   Which agent feedback loop would you build first in your own software factory? Tell us in the comments.

   Capítulos (10)

   1. 0:00Introduction
   2. 2:36What is a software factory?
   3. 5:38From agents to context to harness engineering
   4. 9:15The three stages of an agent feedback loop
   5. 13:16Inner, middle and outer feedback loops
   6. 18:35Why vague intent breaks agent feedback loops
   7. 21:50Comment bloat, drift and the rule of three
   8. 25:48The software factory mindset
   9. 27:45Loops, feedback loops and meta feedback loops
   10. 32:45Operators, stewards and building your first loop

   Transcripción

7. Legora CTO: Why AI Agents Need More Than a Chat Window

   6 de octubre de 202644 minTemporada 1 · Episodio 126A continuación

   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 …

   Notas del episodio

   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.

   Capítulos

   Cargando capítulos…

   Transcripción

8. Liz Fong-Jones: 2x the PRs, 1.5x the Incidents

   29 de septiembre de 202650 minTemporada 1 · Episodio 125A continuación

   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 …

   Notas del episodio

   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.

   Capítulos

   Cargando capítulos…

   Transcripción

9. Dexter Horthy: Why We Stopped Trusting AI to Write the Plan

   22 de septiembre de 202656 minTemporada 1 · Episodio 124A continuación

   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 …

   Notas del episodio

   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.

   Capítulos

   Cargando capítulos…

   Transcripción

10. AWS's Marc Brooker: Specs, Not Code, Are the Hard Part

    16 de septiembre de 202657 minTemporada 1 · Episodio 123A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

11. You Don't Need Juniors to Code. Hire Them Anyway.

    8 de septiembre de 202652 minTemporada 1 · Episodio 122A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

12. 850 PRs a Week: How Tessl Runs a Software Factory

    2 de septiembre de 202651 minTemporada 1 · Episodio 121A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

13. Lada Kesseler: I Trust AI Tests Less Than AI Code

    25 de agosto de 202646 minTemporada 1 · Episodio 120A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

14. Every Repo Is a Software Factory Now | Don Syme, GitHub

    18 de agosto de 20261 h 5 minTemporada 1 · Episodio 119A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

15. The Background Check You Can't Run on an AI Agent

    11 de agosto de 202648 minTemporada 1 · Episodio 118A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

16. Datadog Deleted All Its AI Context. It Worked.

    4 de agosto de 20261 h 1 minTemporada 1 · Episodio 117A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

17. Inside the Dark Factory: AI That Ships Code Solo

    28 de julio de 202659 minTemporada 1 · Episodio 116A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

18. BONUS: Snyk Found Malware Inside AI Agent Skills

    23 de julio de 202632 minTemporada 1ExtraA continuación

    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 …

    Notas del episodio

    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.

    Transcripción

19. From Living Room Hack to 30 AI Agents at Cyera

    21 de julio de 20261 h 6 minTemporada 1 · Episodio 115A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

20. Patrick Debois Maps the Patterns of AI-Native Dev

    14 de julio de 202648 minTemporada 1 · Episodio 114A continuación

    Con Patrick Debois

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

21. Inside Anthropic: How Claude Tag Is Changing Agentic Work

    7 de julio de 202658 minTemporada 1 · Episodio 113A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

22. The Tessl Agent: Build Your Software Factory on Autopilot

    30 de junio de 202653 minTemporada 1 · Episodio 112A continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

23. Why Agents Are Forcing Enterprises to Finally Fix Their Dev Process

    25 de junio de 20261 hTemporada 1 · Episodio 111A continuación

    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 …

    Notas del episodio

    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

    🌐 Tessl: https://tessl.io

    🔔 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.

    Transcripción

24. BONUS: DevCon London: Real Talk on AI ROI, Harnesses & Evals

    23 de junio de 202624 minTemporada 1ExtraA continuación

    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 …

    Notas del episodio

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

25. AI Security & the Agent-Ready Web: Experts Weigh In

    16 de junio de 20261 h 3 minTemporada 1 · Episodio 110A continuación

    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 …

    Notas del episodio

    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

    Capítulos

    Cargando capítulos…

    Transcripción

26. Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week

    9 de junio de 202655 minTemporada 1 · Episodio 109A continuación

    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 …

    Notas del episodio

    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.
    
    #HarnessEngineering #AINativeDev #SoftwareEngineering

    Capítulos

    Cargando capítulos…

    TranscripciónFragmento (0:45)

27. Why Developers Hit a Wall at 4 AI Agents

    2 de junio de 202648 minTemporada 1 · Episodio 108A continuación

    Con Nicholas Arcolano

    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 …

    Notas del episodio

    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

    Links:

    🌐 Tessl: https://tessl.io

    🔔 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.

    Capítulos

    Cargando capítulos…

    Transcripción

28. Don't Secure the Code. Secure the Coder.

    26 de mayo de 202640 minTemporada 1 · Episodio 107A continuación

    Con Brian Vermeer y Sam Stepanyan

    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 …

    Notas del episodio

    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

    Links: 🌐 Tessl: https://tessl.io

    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.

    Capítulos

    Cargando capítulos…

    Transcripción

29. The Hidden Security Risks of AI Coding Agents

    19 de mayo de 202641 minTemporada 1 · Episodio 106A continuación

    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 …

    Notas del episodio

    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

    
    

    Links:

    • 🌐 Tessl: https://tessl.io
    • 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?

    Capítulos

    Cargando capítulos…

    Transcripción

30. "AI Doesn't Stand for Artificial Intelligence" — Venkat Subramaniam's Take Will Change How You Think About It

    12 de mayo de 202653 minTemporada 1 · Episodio 105A continuación

    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 …

    Notas del episodio

    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

    Capítulos

    Cargando capítulos…

    Transcripción

Aquí están los 40 episodios más recientes de 135. Los anteriores están en el feed del podcast.