New here?

Start with these five

Chain of Thought is a show for engineers, founders, and operators shipping AI in production. These five episodes cover the threads that run through everything else — agents, evals, memory, infrastructure, and what real products demand. Read the transcript or press play.

  1. 1 EP 61 53 min Transcript The AI Framework Era Is Over: Why Context Is the Moat | Jerry Liu Jerry Liu, LlamaIndex LlamaIndex founder Jerry Liu on why context — not the framework — is where the real leverage moved. The cleanest entry into how we think about agents.
  2. 2 EP 57 43 min Transcript Every AI Agent Has an Evaluation Gap | Alex Ratner, Snorkel AI Alex Ratner, Snorkel AI Snorkel AI’s Alex Ratner on the evaluation gap every team hits the moment an agent leaves the demo. Evals are the show’s recurring through-line.
  3. 3 EP 53 59 min Transcript Agent Memory: The Last Battleground in the AI Stack | Richmond Alake, Oracle Richmond Alake, Oracle Richmond Alake on why memory is the layer that decides whether an agent actually works across sessions — the part most teams under-build.
  4. 4 EP 47 51 min Transcript Gemini 3 & Robot Dogs: Inside Google DeepMind's AI Experiments | Paige Bailey Paige Bailey, Google DeepMind Google DeepMind’s Paige Bailey on what a frontier lab is actually shipping — models, tooling, and the experiments behind them. A look at the leading edge.
  5. 5 EP 18 42 min Transcript AI Won't Solve Your Toughest Engineering Problems | Honeycomb’s Charity Majors Charity Majors, Honeycomb Honeycomb’s Charity Majors on why AI won’t solve your hardest engineering problems — the production-reliability reality check every team needs.

Then explore by topic

All topics →

Best-of collections → Browse all episodes → Get the newsletter →