Bounded MCP service
Prototype one small, auditable MR BIG capability with FastMCP and measure integration effort, permissions, and client compatibility.
Lab notebook
Questions worth testing.
These are experiment directions, not released products or verified production capabilities.
Repository context quality
Compare graph-backed code context with an existing workflow, tracking retrieval recall, stale-index behavior, and review usefulness.
Agent-assisted security review
Evaluate Deepsec in a sandbox alongside static analysis and human review, measuring validated findings and false positives.
Terminal coding agent
Evaluate Qwen Code on a non-sensitive test repository using a governed model configuration and explicit tool-safety boundaries.
Experiment standard: define the question, isolate the system, record the inputs, preserve the evidence, and publish limitations alongside results.