Tool Governance for Pydantic AI Agents
Revenue-intelligence system for industrial distribution: scores account-churn risk and runs a guarded Claude agent (Cue) whose tools are tiered into read / internal / approval, so destructive actions route through a human-in-the-loop queue. The model proposes; a person decides. Public, sanitized version on a synthetic tenant.
A Model Context Protocol (MCP) server in Go that provides a splunk_search tool, enabling LLMs to query Splunk instances via the REST API
File-watcher daemon that turns messy markdown meeting notes into clean, well-structured Linear issues. Anthropic forced tool use with a Pydantic-mirrored schema, idempotent batches via sidecar markers, and an eval harness with a no-op chitchat fixture as the hallucination regression catch. Built with the gstack workflow for Kalpi.
Add a description, image, and links to the llm-tool-use topic page so that developers can more easily learn about it.
To associate your repository with the llm-tool-use topic, visit your repo's landing page and select "manage topics."