blastproof
Only what changed
AI agents
Compared
Does it fit?
Benchmarks
Notes
GitHub
v0.27.0
Notes
Notes from
building it.
What we measured, what we got wrong, and what changed because of it.
2026-10-17
updated
2026-10-18
Should a decision model judge your tests first?
I put two new decision models in front of the LLM that judges every step in blastproof, and measured accuracy, cost and time. One of them is now my pick.