If cost reports cannot be tied to useful deliverables, start by preserving one representative example. It gives the investigation a concrete reference and makes the eventual correction easier to judge.
Find the likely cause
Usage is tracked without task identifiers.
Treat this as an explanation to verify against the actual work. Look at the input, the relevant decision, and the final result together. If the evidence does not support this diagnosis, investigate the mismatch before applying a convenient but unrelated fix.
Make the targeted correction
Associate usage and review effort with completed work.
Cost control should reduce wasted work while preserving the quality needed for the final use.
Check that the repair worked
Calculate cost per accepted item for representative task types.
Repeat the check on the final version that the reader or customer will encounter. An approved draft, a preview, and a published result can differ; the acceptance decision should concern the version people actually use.
Prevent the next related failure
A separate issue to watch for is this: aI costs rise because drafts are repeatedly regenerated. Classify the failure and revise the relevant instruction or input.
Monitor the useful outcome
Track total cost and human time per accepted item, including rework and failed attempts.
Keep a short record of the original symptom, the evidence behind the diagnosis, and the result of the acceptance check. That record makes the solution reusable when the same condition appears again, without assuming that every superficially similar problem has the same cause.