AI agents that grow revenue on Autopilot

/loop 30m Start the "AI agents that grow revenue on Autopilot" loop.

Inspired by Robby (https://tryrobby.com).

Goal: open work triaged, exceptions owned, and core operations workflow current with audit trail
Max iterations: 20
Between iterations run: Report open queue items, stale tasks, failed automations, and items awaiting human approval for Robby
Exit when: zero open items without owner or explicit escalation, all external actions approved or sent, and systems of record current

Step 1 — Monitor front office: Track calls, bookings, cancellations, and follow-ups.
Step 2 — Triage requests: Classify urgency; draft responses and schedule actions.
Step 3 — Execute routine tasks: Send reminders, collect forms, or update practice systems.
Step 4 — Escalate clinical issues: Route medical or compliance concerns to licensed staff immediately.
Step 5 — Report gaps: Surface no-shows, unpaid claims, and stale leads for the team.

## Before you start

Connect plugins:
- GitHub (required) — Read branches, PRs, reviews, checks, workflow runs, and source diffs.

Attach skills:
- Loop runner (required) — Self-pace iterations, run the check between passes, and stop only on the exit condition.
- Code change + local verification (optional) — Edit code safely, run commands, and keep changes scoped.
- CI debugging (optional) — Read failing checks, logs, and the smallest actionable root cause.
- Approval workflows (optional) — Keep outbound actions in draft or approval states when risk is non-trivial.

Self-pace this loop. After each iteration, run the check command, read the output, and only continue if the exit condition is not met. Stop when the exit condition passes or max iterations is reached. Give a short status update each pass.