Cognition | Don’t Build Multi-Agents
Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.
Principles of Context Engineering We’ll work our way up to the following principles: Share context Actions carry implicit decisions Why think about principles? HTML was introduced in 1993. In 2013, Facebook released React to the world. It is now 2025 and React (and its descendants) dominates the way developers build sites and apps. Why? Because React is not just a scaffold for writing code. It is a philosophy. By using React, you embrace building applications with a pattern of reactivity and modularity, which people now accept to be a standard requirement, but this was not always obvious to ea
Explore this link on the map →saved by
related reading
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Building Effective AI Agents \ Anthropicanthropic.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Context Engineering for AI Agents: Lessons from Building Manusmanus.im
- Multi-Agents: What's Actually Working | Cognitioncognition.ai
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Towards self-driving codebases · Cursorcursor.com
- How Long Contexts Faildbreunig.com
- Building reliable AI agents · parth sareenparthsareen.com
- How we built our multi-agent research system \ Anthropicanthropic.com