Personal Ops
Inbox Decision Triage
Turn inbox sludge into a small list of decisions, drafts, and explicit no-actions.
Use when
Email, DMs, or comments are creating invisible obligations and context switching.
Cadence
Daily or before deep work
Verification
Every sampled message is archived, labeled, delegated, converted to a task, or left with a drafted reply; no external message is sent without approval.
Structured loop spec
| Field | Value |
|---|---|
| Name | Inbox Decision Triage |
| Category | Personal Ops |
| Trigger | Daily or before deep work |
| Objective | Turn inbox sludge into a small list of decisions, drafts, and explicit no-actions. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Search only the agreed inbox, channel, label, or time window.; Classify each item as FYI, action, decision, relationship-sensitive, or safe archive.; For each action item, capture owner, due date, source link, and next step.; Draft replies or task notes in the user's voice, but keep them unsent unless approval is already explicit.; Do not delete, unsubscribe, spend money, accept terms, or commit the user without approval; stop when only human-judgment items remain. |
| Verification | Every sampled message is archived, labeled, delegated, converted to a task, or left with a drafted reply; no external message is sent without approval. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
Steps
- Search only the agreed inbox, channel, label, or time window.
- Classify each item as FYI, action, decision, relationship-sensitive, or safe archive.
- For each action item, capture owner, due date, source link, and next step.
- Draft replies or task notes in the user's voice, but keep them unsent unless approval is already explicit.
- Do not delete, unsubscribe, spend money, accept terms, or commit the user without approval; stop when only human-judgment items remain.
Prompt
Run the Inbox Decision Triage loop for the specified inbox, channel, label, or time window. Classify messages into FYI, action, decision, relationship-sensitive, and safe archive. For action items, capture owner, due date, source link, and next step. Draft replies or task notes in the user's voice, but do not send, delete, unsubscribe, spend money, accept terms, or make commitments without approval. Return the cleaned count, review queue, and drafted decisions.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Inbox Decision Triage" loop from AI Loop Library (https://ailooplibrary.com/loops/inbox-decision-triage/) as a bounded loop.
Goal: Turn inbox sludge into a small list of decisions, drafts, and explicit no-actions.
Rules: one change per round; run the same verification every round (Every sampled message is archived, labeled, delegated, converted to a task, or left with a drafted reply; no external message is sent without approval.); append each round to docs/loops/inbox-decision-triage/progress.md and update docs/loops/inbox-decision-triage/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.