FediPilotSelf-repair & feedback
AI usage per job
Track AI usage for each request and see what a client job used.
The problem it solves
Practices want to know what each client job cost in AI usage.
How it works
- Run a job.
- Usage is tracked per request.
- Ask for the usage.
What your practice gets
- Cost visibility.
- Per job.
- Better pricing decisions.
Questions accountants ask
Where does usage come from?
Your AI account usage per request.
Can I see it per client?
Yes, per job.
Does Fedix charge for it?
AI runs on your own subscription.
Related features
Features that work alongside ai usage per job.
Assistant status in plain words
See in plain words whether the assistant is working properly, with the technical log behind a button.
Real failures recorded once
When a connected service genuinely fails, FediPilot records one incident, not one per retry.
Self-repair
When FediPilot detects a failure, it reproduces it, prepares a fix and validates it before offering it.
Workflow repairs
When a workflow goes wrong, FediPilot can correct the workflow skill rather than needing a code change.
Defects reach developers with evidence
Code defects are packaged with what is needed to reproduce them and sent to the development team.
Feedback on or off
Turn feedback sending on or off and see what happened to your feedback.
See it working in your practice.
Once your 14-day trial has started, you can download FediPilot for Windows from your Fedix dashboard and sign in with your Fedix account. FediPilot runs on your own ChatGPT or Claude account, which Fedix does not supply. Training sessions are included and can be booked at any time; they are not a precondition.
14-day free trial. A payment method is required to start. Your paid subscription starts automatically when the 14 days end; cancel during the trial and you pay nothing. After the trial, a 6-month minimum term applies, then month-to-month. Commit to 12 months up front and the monthly price is 20% lower. See pricing.