Caleb Sima: AI Attackers Move at Machine Speed

Ex-Robinhood CSO Caleb Sima on AI attackers that hit every surface at once, run on your own AI tokens, and why defense now means taking humans out of the loop.

27 Oct 2026 · 54 min 51 sec

Your Coding Agent Should Never Hold a Credential

Docker, Snyk and Keycard co-wrote Agent Baseline. Live in San Francisco, they explain why your coding agent should never hold a credential, and what to lock down first.

22 Oct 2026 · 29 min 51 sec

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

Snyk's Manoj Nair on why skills and MCP servers are the new npm, why CISOs are rethinking risk, and what enterprises need before they trust AI coding agents.

20 Oct 2026 · 46 min 31 sec

Maria Gorinova: Feedback Loops That Fix Your Codebase

Agents left alone write longer and longer comments. Tessl's Maria Gorinova explains the feedback loops that let a software factory catch drift and fix itself.

13 Oct 2026 · 37 min 56 sec

Jacob Lauritzen: Token Maxing Is the New Lines of Code

AI writes almost all of Legora's code. So why does its CTO think token maxing is a mistake, and why should litigation strategy stay a human call?

6 Oct 2026 · 44 min 21 sec

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

Honeycomb doubled its pull requests with AI and incidents rose 1.5x. Liz Fong-Jones on automated code review, owning AI output, and when agents can run production.

29 Sept 2026 · 49 min 37 sec · with Liz Fong-Jones

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

HumanLayer's Dexter Horthy staked his team's codebase on trust the plan, skip the code. Four months later it was unusable. Here's what changed his mind.

22 Sept 2026 · 56 min 10 sec

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

Marc Brooker (AWS) has read up to 4,000 postmortems and concluded code was never the hard part. He tells Simon why testing and specs are now the real work.

16 Sept 2026 · 56 min 48 sec · with Marc Brooker

850 PRs a Week: How Tessl Runs a Software Factory

Tessl's factory peaked at 850 PRs in a week, 85 to 90% of them agent-handled end to end. Dru Knox on why the two biggest changes weren't the speed anyone was chasing.

2 Sept 2026 · 51 min 17 sec

Lada Kesseler: I Trust AI Tests Less Than AI Code

Lada Kesseler trusts AI-written tests less than AI-written code, and thinks most teams chasing a software factory are about to drown in garbage.

25 Aug 2026 · 45 min 49 sec · with Lada Kesseler

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

Don Syme on why every repo is becoming a software factory, why guardrails let you run faster, and why no pull request should reach a human reviewer unless the quality gates have already earned its place.

18 Aug 2026 · 01 h 04 min · with Don Syme

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

Non-determinism is the feature and the bug. Keycard's Ian Livingstone on why agent identity breaks everything OAuth assumed, and the new layer that has to replace it: mission.

11 Aug 2026 · 47 min 44 sec