Best Chain of Thought Episodes on AI Coding Agents
What changes downstream when agents write most of the code.
Whether an agent can write the code is settled. What’s still open is what happens downstream: the review queue, and the parts of the job that quietly assumed a human typed it. None of this is a prediction. Each guest ran it on their own team and came back with numbers.
- 1 250,000 Lines of Code/Week: Inside an AMD VP's Agent-First Workflow | Anush Elangovan Anush Elangovan, AMD Anush Elangovan runs 10–12 Claude Code agents across three machines and burns 6.5 billion tokens a week. The line that stuck with me: the test harness is the new code review.
- 2 After Code Gen: What Graphite Is Building for the Post-AI Dev Stack | Greg Foster Greg Foster, Graphite Graphite’s Greg Foster on the bottleneck moving from writing code to reviewing it, once agents start opening pull requests in the background faster than humans can merge them.
- 3 I Built an AI Coworker That Runs 90% of My Day Sterling Chin, Postman Sterling Chin onboarded an assistant built on Claude Code the way you would onboard a junior employee, and forty days later it was handling 90% of his workday. Live demos, not a thought experiment.
- 4 First Code, Then AGI: Software’s Event Horizon with Poolside Founders Jason Warner & Eiso Kant Jason Warner & Eiso Kant Jason Warner and Eiso Kant on why Poolside trains for code specifically instead of general capability, and what reinforcement learning against real execution feedback buys a model.
- 5 Using AI to Modernize Your Legacy Applications | MongoDB’s Rachelle Palmer Rachelle Palmer, MongoDB MongoDB’s Rachelle Palmer on pointing AI at legacy codebases — the least glamorous use of coding agents, and one of the few with an obvious payback measured in years off a timeline.
- Best Chain of Thought Episodes for AI Founders Building an AI company — defensibility, GTM, and the market reality.
- Best Chain of Thought Episodes for Engineers Shipping with AI — the craft, the workflow, and the reality checks.
- Best Chain of Thought Episodes on AI Agents How agents actually work — architecture, memory, context, frameworks.
- Best Chain of Thought Episodes on AI Evaluation Measuring whether AI actually works — evals, reliability, trust.
- Best Chain of Thought Episodes on Agent Memory How agents remember — memory stores, context engineering, and what breaks without them.
- Best Chain of Thought Episodes on Multi-Agent Systems Many agents, one system — orchestration patterns, protocols, and the overhead they add.
- Best Chain of Thought Episodes on Open Source AI Open weights, open ecosystems, and what they actually cost in production.
- Best Chain of Thought Episodes for Enterprise AI Leaders Getting AI past the pilot — ROI, rollout, and the data underneath it.
- Best Chain of Thought Episodes on AI Security Attacking agents, defending them, and the part software cannot cover.
- Best Chain of Thought Episodes on RAG & Retrieval Getting the right context to the model: chunking, vectors, graphs, and what breaks at scale.