The humans in the system
People behind the loop
A small practice for making software workflows more observable, verifiable, and safe to run again.
We work across the boundary between a proposed change and the evidence that says whether it helped. These are the people you can call when the loop needs a better verdict, a safer deployment, or a sharper model.
3 people in the directory
- 01
Ada
Works on the Verdict plane side of the two-plane loop. Designs scoring rubrics, curates evaluation corpora, and reviews closure-test scorecards. Background in formal verification and property-based testing; came to autonomic software engineering by way of asking "who checks the checker?" one too many times.
Get called for
- verifier design and the closure test
- corpus curation and case authoring
- scoring rubric review
- 02
Grace
Works on the deployment side. Picks blast radii (L0 through L3) for live systems, designs the infrastructure reconciliation instantiation of the two-plane loop, and runs the cutovers when a system moves from L1 (Gated) to L2 (Unattended). Prefers boring solutions and finds them exciting; this is rarer than it sounds.
Get called for
- two-plane loop deployment on real workloads
- blast radius selection and L2+ rollout
- infrastructure reconciliation projects
- 03
Tim
Maintains agent-eval and the lab publication site. Works on autonomic software engineering, the two-plane loop blueprint, and the practice of putting a Verdict plane between a Proposer and the repository.
Get called for
- autonomic software engineering setup
- two-plane loop reference architecture
- verdict plane and corpus design
- evaluating AI agents at scale