Run waste analysis

The idea

When a run ends, the platform analyses its steps and requests for repeats, missed fusions, context growth, large outputs and long logs. It estimates the tokens each mechanism would save.

The problem
Token waste stayed hidden until the bill came.
Why it matters
Each run shows its share of waste, and oversight warns about large wasteful runs.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • Ranked ways to cut spend

    From its own records, Crewshal ranks where an organization can spend less: harness settings that are off, low-cost work that ran on expensive models, and failed calls. Each saving has a monthly estimate, the control to change and a prompt to copy.

  • Keep-or-discard harness loop

    A harness change is kept only if the declared capability metrics stay within tolerance, one efficiency metric improves by the minimum, and frozen held-out cases confirm it. Campaigns count every attempt.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.