← All talks

Editorial provenance

Review ledger.

Every transcript and overview begins as derived content. This ledger reports what AI Engineer has—and has not—reviewed. A terminology correction is not a line-by-line editorial review.

TalkTranscript statusKnown issues
Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, AnthropicSystematic correction applied; full review pendingA systematic Cloud-to-Claude terminology correction was applied; the remaining transcript is not fully reviewed.
Full Walkthrough: Workflow for AI Coding — Matt PocockFull editorial review pendingSpeaker diarization includes `Mike` and `Guest`, which are not corroborated by canonical speaker metadata; their attribution remains unreviewed.
"Software Fundamentals Matter More Than Ever" — Matt PocockFull editorial review pendingSpeaker diarization includes `Guest`, which is not a resolved person and remains unreviewed.
The New Code — Sean Grove, OpenAISystematic correction applied; full review pendingChecksum-pinned corrections normalize GPT-4o, sycophancy, and muscle-memory terminology; the remaining transcript is not fully reviewed.
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayerFull editorial review pendingSpeaker diarization includes `Guest`, which is not a resolved person and remains unreviewed.
How We Build Effective Agents: Barry Zhang, AnthropicFull editorial review pendingNo issue recorded; review still pending.
Building pi in a World of Slop — Mario ZechnerSystematic correction applied; full review pendingA systematic Cloud-to-Claude terminology correction was applied; the remaining transcript is not fully reviewed.
Building Production-Ready RAG Applications: Jerry LiuFull editorial review pendingNo issue recorded; review still pending.
The Infinite Software Crisis – Jake Nations, NetflixFull editorial review pendingThe generated summary's 1968 date was absent from committed transcript text and was removed; the video slides were not independently checked.
Building Agents with Model Context Protocol - Full Workshop with Mahesh Murag of AnthropicFull editorial review pendingSpeaker diarization includes `Guest`, which is not a resolved person and remains unreviewed.
Does AI Actually Boost Developer Productivity? (100k Devs Study) - Yegor Denisov-Blanch, StanfordFull editorial review pendingNo issue recorded; review still pending.
Why Agentic Systems Need Ontologies — Frank Coyle, UC BerkeleyFull editorial review pendingNo issue recorded; review still pending.
12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayerFull editorial review pendingSpeaker diarization includes `Guest`, which is not a resolved person and remains unreviewed.
GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil EifremFull editorial review pendingSpeaker diarization includes `Host`, which is not a resolved person and remains unreviewed.
Harnesses in AI: A Deep Dive — Tejas Kumar, IBMFull editorial review pendingSpeaker diarization includes `Guest`, which is not a resolved person and remains unreviewed.
Building and evaluating AI Agents — Sayash Kapoor, AI Snake OilFull editorial review pendingNo issue recorded; review still pending.
Pydantic is all you need: Jason LiuFull editorial review pendingNo issue recorded; review still pending.
The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, FactoryFull editorial review pendingNo issue recorded; review still pending.
Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAIFull editorial review pendingNo issue recorded; review still pending.
RAG Agents in Prod: 10 Lessons We Learned — Douwe Kiela, creator of RAGFull editorial review pendingNo issue recorded; review still pending.
2025 in LLMs so far, illustrated by Pelicans on Bicycles — Simon WillisonFull editorial review pendingNo issue recorded; review still pending.
Field Guide to Fable — Thariq Shihipar, AnthropicFull editorial review pendingNo issue recorded; review still pending.
[Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel HanFull editorial review pendingNo issue recorded; review still pending.
Claude Agent SDK [Full Workshop] — Thariq Shihipar, AnthropicFull editorial review pendingNo issue recorded; review still pending.
Beyond Components: Designing Generative UI for MCP Apps — Ruben Casas, PostmanFull editorial review pendingNo issue recorded; review still pending.
State of the Claw — Peter SteinbergerFull editorial review pendingNo issue recorded; review still pending.
The Future of MCP — David Soria Parra, AnthropicFull editorial review pendingNo issue recorded; review still pending.
The Future of Knowledge Assistants: Jerry LiuFull editorial review pendingNo issue recorded; review still pending.
How I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOSFull editorial review pendingNo issue recorded; review still pending.
Building Great Agent Skills: The Missing ManualFull editorial review pendingNo issue recorded; review still pending.