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
saved by
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- Multi-Agents: What's Actually Working | Cognitioncognition.ai
- Building Effective AI Agents \ Anthropicanthropic.com
- Building reliable AI agents · parth sareenparthsareen.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Context Engineering for AI Agents: Lessons from Building Manusmanus.im
- How Long Contexts Faildbreunig.com
- Don't Sleep on Single-agent Systems | Sep 26, 2024all-hands.dev
- Why I'm Betting Against AI Agents in 2025 (Despite Building Them)utkarshkanwat.com
- Don’t Outsource Your Thinkingteltam.github.io