Tag: tool-use
All the articles with the tag "tool-use".
-
Inside Microsoft Agent Framework Harness Providers
Published: at 11:00 AMAn LLM in a loop is not enough for production work. This post breaks down the six problems every agent harness must solve — working memory, shared file access, plan/execute modes, task tracking, parallel sub-agents, and tool approval — and how the Microsoft Agents Framework implements them.
-
Inside the ReAct loop: how agents actually iterate
Published: at 11:00 AMWhat actually happens inside one iteration of the ReAct loop — why the model is stateless, how the transcript grows, when the loop exits, and why the harness around the model is where the engineering value lives.