← Back to library

Write permission rules an always-on agent will accept

After two hours testing a careful always-on assistant, a Hacker News commenter got a trip planned and was even reminded about an unbooked shuttle, yet every booking needed several confirmations. Its rule checker refused his wide rules, and login codes stayed his job. We turn that experience into rules the agent will take.

  • OutcomeGet routine bookings done with fewer confirmation loops by writing narrow, app-specific permission rules instead of one broad blanket rule.
  • SetupUnder an hour
  • LevelIntermediate
  • Creditneom on Hacker News
View original
Works with
ChatGPT agentGrok BotClaude Cowork

Published Oct 23, 2026Updated Oct 23, 2026AI dry run on sample input: passed Oct 23, 2026Source verified Oct 24, 2026

When should you use it?

  • Your agent keeps asking to confirm actions you already approved
  • You are setting up a new always-on assistant
  • A booking chain spans several sites (flight, hotel, ground transport)

Not for: Payments or anything you cannot undo; Shared inboxes where teammates have not agreed to agent replies

What do you need, and what do you get?

You need

  • List of connected apps
  • Actions you repeat weekly
  • Which actions involve money or outside messages

You get

  • A short set of narrow permission rules
  • A list of steps that stay manual (2FA, payment)

How does it work, step by step?

  1. Inventory the repeat actionsWrite down the tasks you hand the agent most often and which app each one touches.
  2. Split by riskMark each action as read-only, reversible, money-moving or outward-facing.
  3. Write one rule per app and actionName the app, the action and the limit, for example drafts only, or bookings already discussed in this chat.
  4. Plan the manual stepsExpect login codes and final payment confirmations to stay with you; batch them so you approve once.
  5. Test on a small tripRun a short booking chain and count how many confirmations you were asked for, then tighten or relax one rule at a time.

The prompt

Our own prompt, inspired by neom on Hacker News and written to work in ChatGPT agent, Grok Bot and Claude Cowork. Values in lime are placeholders.

Fill in the blanks (optional; the copied prompt uses your values)

Prompt2 variables
Help me write permission rules for my assistant.
Connected apps: {apps}
Tasks I repeat: {tasks}
For each task, propose one narrow rule naming the app, the exact action and a limit. Mark any task that moves money, sends something outside or needs a login code as MANUAL and explain why. Keep each rule under 30 words.

Inspired by neom on Hacker News: Hacker News comment on testing an always-on agent's permission rules. The prompt above is written by playbooks.bot in our own words; nothing from the original is quoted.

What can go wrong?

  • One sweeping rule that says use your judgment is exactly what a cautious checker rejects.
  • Letting an agent read your email does not mean it will enter the codes it finds there; plan for that step.

Our take

After two hours testing a careful always-on assistant, a Hacker News commenter named neom got a trip planned and was reminded about an unbooked shuttle, yet every booking needed several confirmations. Its rule checker refused blanket authority. The useful lesson is what the friction reveals: a cautious agent will treat any rule that sounds like blanket authority as a risk and keep re-confirming. Separate planning from booking rights. Begin by listing the tasks you hand the agent most often and the app each touches, then sort them by risk: read-only, reversible, money-moving or outward-facing. Write one rule per app and action with a clear limit, such as drafts only, or bookings already discussed in this chat. A sweeping instruction to use its judgment is exactly what a careful checker rejects. Expect login codes and final payment confirmations to stay with you, and batch them so you approve once. Test on a short booking chain, count the confirmations, and adjust one rule at a time.

Where the time goes back: Narrow rules cut the back-and-forth on routine bookings, so your attention goes to payments and sign-ins only.

FAQ

Why did my broad rule get rejected?
Products with a rule checker look for open-ended scope. A rule tied to one app, one action and a clear limit is easier for it to accept.
Should I try to get it to enter 2FA codes?
No. Keep sign-in codes as a human step and schedule logins for times you are at your phone.

Source and credit

Inspired by neom on Hacker News. We describe the idea in our own words, link to the original, and wrote the prompt ourselves; nothing is quoted.

Inspired by
Hacker News comment on testing an always-on agent's permission rules
Creator
neom on Hacker News
Published on
Hacker News
Original date
Sep 30, 2026
License
Not openly licensed (the poster keeps all rights), so we quote nothing and link to the original
Originally for
ChatGPT agent
AI dry run
Oct 23, 2026: passed. Dry-run tested by our AI test agent on sample input. PASS: Gates held on desk check; no live sends or purchases.
AI dry run on sample data; not run with live connected accounts. The playbooks.bot test agent filled the prompt with synthetic inputs, produced the output and checked it against the page's stated outputs and guardrails.
Verified
Oct 24, 2026: source link resolves to the original, the credited creator published it, our excerpt or prompt matches it, and the license allows our use.

Are you the creator? Claim or correct this page.

More in Operations & Admin

All 203 Operations & Admin playbooks →

Related playbooks

Operations & AdminPrompt✓ AI dry run

Aim the agent at a janky internal app after it maps the UI

Have the agent study a janky internal UI out loud, complete one end-to-end task with a recording, and stop for login walls instead of guessing credentials.

Credit: Carnage (@0xCarnagee)

Under an hour
Operations & AdminPrompt✓ AI dry run

Audit how you manage your agent team, not only the agents

Have your chief-of-staff agent review the last 30 days of how you delegated, clarified, interrupted, corrected, assigned, approved and followed up across your agent team, score eight management areas with evidence, list your three biggest weaknesses, and draft a seven-day improvement plan, without changing any bot, routine or instructions until you approve.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Audit how your agents pick tools before buying more usage

Have your lead agent review the recurring jobs it can see, note which apps, scripts, browser sessions or full computer control each one relies on, flag jobs that take a heavier route than needed or rely on remembered facts, check permissions and fallbacks, and then propose three side-by-side experiments before anything is changed.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Chain skills with a yes-gate instead of one giant prompt

Assemble a daily pipeline: pick from a source, draft with a writing skill, wait for your yes, then hand to a planning or build skill.

Credit: Matt Palmer (@mattyp)

Under an hour
Operations & AdminPrompt✓ AI dry run

Triage a huge inbox into folders with draft replies

Group a backlog of unread email, flag the urgent few and draft one-line replies for the rest.

Credit: SOP | AI Agent Builder (@Sonofpeace0001)

Minutes