Daily Brief

Say what you want, not how to get it. The OpenProse team shows how to write multi-agent workflows as declarative contracts in plain markdown, which any harness (Claude Code, Codex and others) can compile and run. Demos include event-driven jobs triggered by webhooks and pull requests, a "grumpy senior" PR reviewer, and an end-to-end bank model-documentation workflow. They also discuss composing contracts, pinning a winning run into a reusable workflow, and how this compares to DSPy. Chapters: - 00:00 From prompt engineering to declaring intent - 05:40 What OpenProse is - 09:58 Agents, skills

Full episode: https://www.youtube.com/watch?v=f6cjAEr08qk Me on twitter: https://x.com/dwarkesh_sp

Ryan Ahern of Exa introduces Exa Snapshot, which lets agents search the web as it looked on any past date. He covers why search quality matters when agents broker most searches, how snapshot results compare to live results, and how teams use point-in-time search to build and test predictive signals without overfitting. Chapters: - 00:00 Intro - 02:14 Agents as the new searchers - 04:15 Exa's three core principles - 08:19 Snapshot vs live search - 12:45 From signals to predictions - 16:58 Backtesting without overfitting Ryan Ahern — https://exa.ai Join us in SF for the second annual AIE CODE

Deploying AI into real businesses is hard: org charts are messy, trust takes decades, and service firms don't scale like software. Prathik Naidu, founding partner at Long Lake, explains their strategy: acquire established service businesses, then transform them with AI from the inside. He covers how they choose companies and what changes once they own them, drawing on 40 businesses across residential services, architecture, HR and more. Chapters: - 00:00 Intro - 02:15 Why deploying AI into businesses is hard - 06:27 Why trust and brand win - 10:41 Software vs service economics - 12:42 The Lon

Benchmarks won't tell you how a model behaves in your app. Swapping it in and testing will. Pamela Fox, Principal Cloud Advocate at Microsoft, runs the same scenarios against GPT-5.5, Kimi K2.6, DeepSeek V4 Flash and Mistral Large 3 on Microsoft Foundry so you can see where models differ and what you can do about it. She works up from a letter-counting prompt to RAG groundedness, image input, multilingual pitfalls, tool calling, tool calling in a loop and a LangChain v1 travel agent, then moves to evaluation: string-check evals, LLM-as-a-judge, Microsoft's new ASSERT tool for generating test

David Silver on simple objectives in complex worlds: how evolution got all of life from a fitness signal, and how humans went from coordinating to communicating to trading to science. #ReinforcementLearning #AI #Emergence

Is the agent harness dead? Jediah Katz, Cursor's longest-tenured agent-harness engineer and now at SpaceX, explains why fancy harnesses no longer add coding intelligence: the data flywheel teaches models the skills harnesses used to patch in. He then argues why the harness matters more than ever. It opens new frontiers like Grokbot, and it owns what models can't absorb: infrastructure, trust and security, and efficiency. He closes with predictions, including that 90% of agent work runs off the laptop within six months. Chapters: - 00:00 Is the harness dead? - 01:09 From prompt engineer to har

Single-player Go would be the most boring game imaginable. David Silver on what happens the moment you add a second agent, and why simple environments can produce endless learning. #Go #AlphaGo #AI #ReinforcementLearning