Observing Codex MCP Tool Calls with Langfuse
A practical local setup for tracing Codex MCP requests, tool execution, and evaluation without sending application data to the cloud.
Read storypgvector and RAG, Explained Through a Real Knowledge Workflow
A plain-English walkthrough of how Markdown knowledge pages become searchable AI context using embeddings, pgvector, HNSW, and evaluation checks.
Read storyMCP as a Safe AI Integration Boundary
How I think about model tools as narrow product interfaces instead of hidden access to an application.
Read storyVercel AI SDK with Explicit Tool Boundaries
Why AI tools need schemas, permissions, confirmation, and audit trails before they change product data.
Read story