Dynamic context discovery · Cursor
As models improve as agents, we've found success by providing fewer details up front, making it easier for the agent to pull relevant context on its own.
Blog / research Coding agents are quickly changing how software is built. Their rapid improvement comes from both improved agentic models and better context engineering to steer them. Cursor's agent harness, the instructions and tools we provide the model, is optimized individually for every new frontier model we support. However, there are context engineering improvements we can make, such as how we gather context and optimize token usage over a long trajectory, that apply to all models inside our harness. As models have become better as agents, we've found success by providing fewer details
saved by
related reading
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval | Cognitioncognition.ai
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Building reliable AI agents · parth sareenparthsareen.com
- How coding agents read your code (and how to write for them)modem.dev
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Continually improving our agent harness · Cursorcursor.com
- Context Engineering for Coding Agentsmartinfowler.com
- How Long Contexts Faildbreunig.com
- Arjun Virkarjunvirk.com
- Context Engineering for AI Agents: Lessons from Building Manusmanus.im
- Effective harnesses for long-running agents \ Anthropicanthropic.com