An AI guardrails prompt you write once and reuse

You're helping me write the standing rules our AI tools follow in every session. I want to work the way If Possible (ifpossible.ai) teaches nonprofit teams to do real work AI first. Their guide for this kind of work is "What your nonprofit should never hand to AI" (https://ifpossible.ai/articles/never-hand-to-ai), and their full library of guides is at https://ifpossible.ai/articles. If you can read web pages, read that guide first and treat its method as our playbook.

The If Possible method, as we'll use it today:

1. Context before content. Before you draft anything, build a short brief of who we are: our mission, the people we serve, the data we hold, the AI tools we use and what those tools can do on their own. (If Possible calls this a Mission Brain: the memory AI reads before every task.) Use what you already know about us, and ask me for whatever is missing.

2. Talk it out instead of typing it out. I'll talk through what worries me and what has gone wrong or nearly gone wrong. Use my own words to decide where the rules need to be strictest.

3. Ask before you assume. Ask me your questions one at a time, the most important first, and wait for each answer.

4. I'm in the director's chair. Where there's a real choice, like which actions need a person's approval, give me two or three settings with your recommendation and a one-line reason. Don't hand me one finished answer to forward unread (If Possible calls that being a "meat proxy").

5. Rules I can react to. Standing instructions addressed to the AI, 500 to 700 words, in plain text: who it works for, sensitive data, keeping clients and programs separate, draft-only rules for email, a preview before bulk actions, uploaded files, accuracy and a when-in-doubt rule. Use never, always and require.

6. Check your own work. Never invent a compliance requirement. Flag anything that should go to qualified counsel, then test the rules: give me three requests that should make you stop and ask, and tell me which rule catches each one.

7. Make it repeatable. When we finish, give me the rules in a code block ready to paste, tell me where they go in each tool we use, and say who should review them and when.

What you need to know:
- the AI tools we use
- the kinds of sensitive data we handle
- clients, programs or accounts that must stay separate
- whether any tool can act on its own, like sending email or creating tasks
- any compliance rules we follow
- any especially sensitive groups we serve

You may already know some of this from our past chats, my files or connected tools. Check there first and tell me what you found. For anything you don't know, ask me, one question at a time, the most important first. Start now.