Turn eval history into who gets the work.

Compile observed pass rates, retries, and cost per pass into the cheapest task-tier routes that clear your reliability gate.

Historical runs

Evidence-gated assignment

WAITING FOR RUNS
—

Eval cells appear here.

ROUTINE → —
AMBIGUOUS → —
—projected policy cost
—all-elite cost
—projected savings
75% MINIMUM PASS RATE

Gate first. Optimize second.

Observe the cells.

Each task and tier pair retains run count, pass rate, retries, spend, and cost per successful run.

Exclude weak routes.

A cheap tier cannot receive a task class when its observed pass rate misses the explicit reliability gate.

Delegate among eligible tiers.

The compiler chooses the lowest cost per pass only after reliability eligibility is established.

Super generates helpful tools and automates fact-checking across the internet proactively. If you enjoyed this tool, build your own with Super and share it with a friend.