Podcast

Context Engineering Long-Horizon Agents | Harrison Chase

Sequoia Training Data (Harrison Chase) · sequoiacap.com

Why context, not model size, unlocks agents that work for hours.

Open on sequoiacap.com ↗

It answers 2 questions

  1. Prompt engineering, RAG, or fine-tuning: which one does my product actually need?
  2. How do I give my agent the right context and memory so it stops forgetting?

Read with it

  1. The canonical guide: curation beats clever prompting for agents. anthropic.com Guide Effective context engineering for AI agents Anthropic
  2. The write, select, compress, isolate framework every team now uses. langchain.com Article Context Engineering for Agents LangChain
  3. Battle scars from a real production agent, including the KV-cache economics. manus.im Article Context Engineering for AI Agents: Lessons from Building Manus Yichao 'Peak' Ji (Manus)
  4. The post that coined the framing, with the LLM-as-CPU analogy. rlancemartin.github.io Article Context Engineering for Agents (original essay) Lance Martin
  5. An expert's teardown of how Manus applies the theory in production. rlancemartin.github.io Article Context Engineering in Manus Lance Martin
  6. The full conversation, including memory across sessions. latent.space Podcast Context Engineering for Agents | Lance Martin, LangChain Latent Space (Lance Martin)
eChai Partner Brands The partnership →