How Long Contexts Fail | Drew Breunig
Taking care of your context is the key to building successful agents. Just because there’s a 1 million token context window doesn’t mean you should fill it.
Jun 22, 2025 AGENTS LLM AI PROMPTING CONTEXT MANAGEMENT How Long Contexts Fail Managing Your Context is the Key to Successful Agents As frontier model context windows continue to grow 1 , with many supporting up to 1 million tokens, I see many excited discussions about how long context windows will unlock the agents of our dreams. After all, with a large enough window, you can simply throw everything into a prompt you might need – tools, documents, instructions, and more – and let the model take care of the rest. Long contexts kneecapped RAG enthusiasm (no need to find the best doc when you ca
saved by
related reading
- How to Fix Your Contextdbreunig.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Don’t Build Multi-Agents | Cognitioncognition.ai
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Multi-Agents: What's Actually Working | Cognitioncognition.ai
- Extending Context is Hard | kaiokendevkaiokendev.github.io
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Building Effective AI Agents \ Anthropicanthropic.com
- The huge potential implications of long-context inferenceepochai.substack.com
- Context Engineering for AI Agents: Lessons from Building Manusmanus.im
- Generalizing an LLM from 8k to 1M Context using Qwen-Agent | Qwenqwenlm.github.io