The tiny computer built for on Autopilot
Inspired by Button Computer β The tiny computer built for voice AI.. Loop until the workflow is current, exceptions are owned, and human sign-off is captured where required.
Inspired by Button Computer
by Trooper
/loop 30m Start the "The tiny computer built for on Autopilot" loop. Inspired by Button Computer (https://buttoncomputer.com). Goal: open work triaged, exceptions owned, and core design 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 Button Computer Exit when: zero open items without owner or explicit escalation, all external actions approved or sent, and systems of record current Step 1 β Intake demand: Collect specs, quantities, lead times, and vendor constraints. Step 2 β Source and compare: Rank suppliers or components by spec, cost, and availability. Step 3 β Draft orders: Prepare POs or build configs with cited BOM lines. Step 4 β Human approval: Require sign-off before spend or manufacturing commits. Step 5 β Track fulfillment: Monitor delivery, QA, and exception handling to close. ## Before you start Connect plugins: - GitHub (required) β Read branches, PRs, reviews, checks, workflow runs, and source diffs. - Figma (required) β Inspect designs, dimensions, assets, and handoff notes. - Browser / Web access (required) β Open pages, inspect live state, collect evidence, and verify changes. Attach skills: - Loop runner (required) β Self-pace iterations, run the check between passes, and stop only on the exit condition. - Code change + local verification (optional) β Edit code safely, run commands, and keep changes scoped. - CI debugging (optional) β Read failing checks, logs, and the smallest actionable root cause. - Approval workflows (optional) β Keep outbound actions in draft or approval states when risk is non-trivial. - Visual design QA (optional) β Compare implementation against visual expectations and capture regressions. - Browser QA (optional) β Exercise product flows, capture visual evidence, and verify fixes in-browser. 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.
Paste the kickoff prompt into Cursor, Claude Code, or Codex. Deeplinks do not install hook files.
1. Intake demand
Collect specs, quantities, lead times, and vendor constraints.
2. Source and compare
Rank suppliers or components by spec, cost, and availability.
3. Draft orders
Prepare POs or build configs with cited BOM lines.
4. Human approval
Require sign-off before spend or manufacturing commits.
5. Track fulfillment
Monitor delivery, QA, and exception handling to close.
Guardrails
Rules the agent must follow so it cannot cheat the exit condition.
- Require human approval before customer-facing sends, payments, or legal submissions unless pre-approved templates apply
- Preserve full audit trail linking source data to every automated action
- Escalate compliance, safety, or regulatory-sensitive items immediately
More Design loops
Inbox Triage with Approval
On an interval, classify incoming mail, draft safe replies for routine threads, and escalate anything that needs a human decision.
Morning Operator Brief
Daily interval loop that reads your calendar, open tickets, and inbox priorities, then delivers a concise operator brief with ranked actions.
Customer Onboarding Watch
Interval loop that watches new signups, runs the onboarding checklist against each account, and nudges or escalates stuck users.
