The harness behind two DOI-archived benchmark reports, and why a study premise can be killed in one working day

A benchmark that killed its own hypothesis: strong models re-derive what they can check, and a weak model trusts a stale note over the evidence in front of it

A reproducible benchmark: 42.7% to 98.7% on knowledge-trap questions, and a platform that learns from empty

An Apache-2.0 MCP server that gives frontier models access and grounded context to everything you built

I drove my own platform as a real client and told it to find every place a tool said one thing and did another. A case study in MCP SDLC.

An insight an analyst shares mid-session becomes a reviewed, signed-off change to the catalog rather than vanishing when the conversation ends.

Steering agents from the server middleware instead of the tool descriptions.

Compose mcp-trino, mcp-datahub, and mcp-s3 as Go libraries behind one endpoint, instead of running three servers that can't see each other.

An MCP server faces an agent on both sides. Go lets me leash the agent that writes it and harden the contract the agent reads.