Context Engineering for Agents | Lance Martin, LangChain
The full conversation, including memory across sessions.
Open latent.space →
Building & Product
Podcast
Podcast
Podcast
Guide
Article
Article
Article
Article
Article
Guide
Article
Article
Article
Guide
Article
Article
Article
Article
How do I give my agent the right context and memory so it stops forgetting?
Agents fail less because the model is dumb and more because its context window is stuffed with the wrong things: performance measurably degrades as context grows (context rot). Context engineering is the fix: write important facts to external notes, select only what the current step needs, compress long histories into summaries, and isolate big sub-tasks into fresh contexts. Manus's production lesson adds a money angle: structure context so it caches well, because cache hits are 10x cheaper than fresh tokens.
Go deeper
18 resources.
Context Engineering for Agents (audio)
Same episode, playable on your commute.
Listen on Spotify open.spotify.com →Context Engineering Long-Horizon Agents | Harrison Chase
Why context, not model size, unlocks agents that work for hours.
Open sequoiacap.com →Effective context engineering for AI agents
The canonical guide: curation beats clever prompting for agents.
Open anthropic.com →Context Engineering for AI Agents: Lessons from Building Manus
Battle scars from a real production agent, including the KV-cache economics.
Open manus.im →Context Engineering for Agents
The write, select, compress, isolate framework every team now uses.
Open langchain.com →Context Engineering for Agents (original essay)
The post that coined the framing, with the LLM-as-CPU analogy.
Open rlancemartin.github.io →Context Engineering in Manus
An expert's teardown of how Manus applies the theory in production.
Open rlancemartin.github.io →Context Engineering for AI Agents: Part 2
Advanced patterns once the basics stop being enough.
Open philschmid.de →Context engineering in agents (docs)
The implementation reference when you actually build it.
Open docs.langchain.com →Fighting Context Rot
Explains why agents get dumber as conversations get longer, and what to do.
Open inkeep.com →Diagnosing and Mitigating Context Rot in Long-horizon Search
The research evidence that performance degrades with input length.
Open arxiv.org →Claude's Context Engineering Secrets: Best Practices from Anthropic
Reverse-engineers how Claude's own products manage context.
Open 01.me →Context Engineering: A Practical Guide for AI Agents
How a code-intelligence company feeds agents exactly the right slice of a codebase.
Open sourcegraph.com →AI Agent Harness, 3 Principles for Context Engineering, and the Bitter Lesson Revisited
Connects context engineering to harness design in three principles.
Open hugobowne.substack.com →Inside the LangChain x Manus Webinar on Context Engineering
Notes from the two leading teams comparing approaches live.
Open medium.com →Harrison Chase: 2026 ushers in long-horizon agents
Where memory and context management are heading next.
Open eu.36kr.com →Context Engineering for AI Agents: Key Lessons from Manus
A quick digest of the Manus lessons if you skip the original.
Open dev.to →More in AI Agents
- What actually is an AI agent, in plain language? 18 →
- Why would a founder use agents instead of a chatbot or automation? 18 →
- What real tasks are founders delegating to agents today? 20 →
- How do I build my first agent without being technical? 20 →
- Which platform or framework should I build my agents on? 18 →
- How much do AI agents cost to run, and how do I keep the bill under control? 18 →
- How do I test an AI agent and know when it's reliable enough to trust? 18 →
- What can go wrong when an agent acts on my behalf, and how do I keep it safe? 16 →
- What is MCP, and why does it matter for my agents? 18 →
- Should I build one agent or a team of agents working together? 18 →
- Can coding agents like Claude Code actually build my product? 18 →
- Is there a real startup opportunity in building vertical AI agents? 19 →
- How should I price a product built on AI agents? 18 →
- Why do most AI agent projects fail, and what do the winners do differently? 19 →
Also in Starting Up
The same ground, over in Build the product, our Starting Up track.
eChai Partner Brands
