The latest from the AI and MCP ecosystem, curated daily.
LangChain shares their internal methodology for building evals for Deep Agents — how they source data, design metrics, and run targeted experiments over time to make agents more accurate and reliable. The key principle: the best evals directly measure a specific agent behaviour you care about, not proxies. Practical guidance backed by LangChain's own production experience.
Today's stories:
LangChain shares their internal methodology for building evals for Deep Agents — how they source data, design metrics, and run targeted experiments over time to make agents more accurate and reliable. The key principle: the best evals directly measure a specific agent behaviour you care about, not proxies. Practical guidance backed by LangChain's own production experience.
Google launched Gemini 3.1 Flash Live and a Live API in Google AI Studio to power real-time voice and vision agents. This is significant for developers building conversational agents with low-latency audio/video streams and multi-modal state, enabling new live agent use cases like voice assistants and live vision-based workflows.
LangChain introduces Agent Middleware — a pattern for customising agent harnesses by injecting logic between the LLM and its environment without modifying core harness code. Covers the design pattern, use cases (logging, auth, rate limiting, retry logic), and how it enables teams to build application-specific harnesses on top of LangChain's Deep Agents framework.
Cursor applies online reinforcement learning to Composer — serving new model checkpoints to production and using real user interactions as reward signals to ship improved checkpoints multiple times per day. A practical account of how they close the loop between production usage and model training at high cadence. Fascinating engineering for anyone building RL-trained coding models.
