Get the latest tech news
Context Engineering for AI Agents: Lessons
This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.
Additionally, if you're self-hosting models using frameworks like vLLM, make sure prefix/prompt caching is enabled, and that you're using techniques like session IDs to route requests consistently across distributed workers. In practice, most model providers and inference frameworks support some form of response prefill, which allows you to constrain the action space without modifying the tool definitions. Manus introduces small amounts of structured variation in actions and observations—different serialization templates, alternate phrasing, minor noise in order or formatting.
Or read this on Hacker News