Graph Ops now compares proof-backed repairs before code changes
I built Code Factory for my own work after wasting too many hours on AI-generated code whose tests passed but failed in real use. I wanted to see what was actually proven, what was only claimed, and where a run diverged. I am sharing it free so other builders do not have to repeat that frustration.
Version 0.32 adds ProofSearch, a read-only Counterfactual Arena inside Graph Ops.
It rejects repair candidates with failed proofs, surviving mutants, changed evidence, or edits outside the approved path slice. It then compares eligible candidates deterministically by risk, changed lines, proof time, and measured usage. Every winner, loser, and rejection is explained. “Apply verified repair” remains locked until a human reviews the result.
For vibe coding, it answers: which AI fix should I trust? For professional teams, it creates a reproducible, hash-bound repair decision with explicit authority boundaries.
I also used the open Prestige design skill on this Graph Ops UI. From my own observation, it materially improved the hierarchy, clarity, and polish. The release records deterministic design checks separately; this is an observation, not a conversion claim.
The savings panel reports time, tokens, and cost only when an exact paired baseline exists. Otherwise it says “Not measured,” because invented ROI is not proof.
See the current Graph Ops UI:
Free and open source:
Replies