Practical AI Resources

This prompt tells the system how you want the interaction structured. It does not guarantee that the system will comply or that its answer will be correct.

You are my beginner AI guide.

Use plain language, short sections, and one step at a time.

Begin by restating what you think I am trying to accomplish. Ask only the questions necessary to understand the task.

Do not ask me for passwords, authentication codes, account numbers, Social Security numbers, identification documents, private medical records, confidential work records, children’s identifying information, or another person’s private information.

Separate your response into:

1. What is well supported
2. What you are assuming
3. What is uncertain or missing
4. What I should verify
5. A practical next step
6. When a qualified human or official source is needed

Do not invent facts, quotations, laws, statistics, names, contact details, links, sources, or citations.

Treat your response as a candidate for me to review—not as final authority.

I may revise, verify, reject, pause, or continue without AI.

Related lesson: Lesson 12 — Personal AI Safety Starter Kit

Context:
[Describe the situation, audience, and relevant non-sensitive background.]

Ask:
[State the specific action you want the system to perform.]

Requirements:
[State the desired length, format, tone, reading level, steps, budget, available tools, and practical constraints.]

Evidence:
[State which sources or supplied materials the answer should use. Require facts, assumptions, and uncertainty to remain distinct.]

Safety:
[State what must remain private, what must not be invented, which decisions remain human, and when a qualified person or official source is needed.]

Before beginning:

- Restate the task in plain language.
- Identify essential information that is missing.
- Ask no more than three necessary questions.
- Do not request sensitive information.
- Treat the result as a draft for human review.

CARES in one sentence

Explain what is happening, ask for one identifiable action, describe what a useful answer looks like, define its evidence, and preserve the human safety boundary.

Related lesson: Lesson 05 — Prompting With CARES

Help me complete this task one step at a time:

[TASK]

I have difficulty managing too many instructions at once.

Please:

- give me only one clear action first;
- keep the action under three sentences;
- wait for my response before giving the next action;
- maintain a short list of completed steps;
- remind me of the current goal without shaming me;
- do not ask me to repeat information I already provided;
- and warn me before any step that may share information, spend money, delete data, change an account, create a commitment, or affect another person.

If the task becomes unsafe or requires a qualified human, stop and explain the handoff.

Analyze the answer below, but do not declare it true or false yet.

Create a claim-checking plan with these sections:

1. Each distinct factual claim
2. Why the claim matters
3. Consequence if it is wrong
4. Best type of source for checking it
5. Whether the source must be current
6. Search terms or questions to use
7. Appropriate human or official contact, if needed

Separate:

- factual claims,
- opinions,
- predictions,
- assumptions,
- and recommendations.

Do not invent evidence or mark a claim verified merely because it sounds plausible.

ANSWER:
[PASTE ANSWER]

Related lesson: Lesson 07 — Verification

I am facing this high-impact question:

[GENERAL, NON-SENSITIVE DESCRIPTION]

Do not make the final decision.

Create a human-handoff plan with:

1. What AI can safely help organize or explain
2. What AI must not decide
3. The type of qualified or authorized human needed
4. Current official sources to check
5. Information or documents to prepare
6. Questions to ask
7. Warning signs requiring more urgent action
8. Private information I should keep out of the AI conversation
9. A clear statement of who remains responsible for the decision

Do not delay an emergency response, invent professional conclusions, or guarantee an outcome.

Related lesson: Lesson 10 — When AI Should Not Be the Decision-Maker

Stop the current approach and reset.

You misunderstood or exceeded the task.

The actual goal is:
[GOAL]

The boundaries are:
[BOUNDARIES]

Keep:
[USEFUL PART]

Remove:
[UNSUPPORTED, PRIVATE, OR UNHELPFUL PART]

Before producing another answer:

1. Restate the corrected task
2. List the evidence you have
3. List what is missing
4. Identify what requires verification
5. Wait for my confirmation

Do not repeat the previous conclusion as though it were established.

LOCAL USE CANVAS

Community goal:
[WHAT SHOULD IMPROVE?]

Bounded AI task:
[WHAT SMALL PART MAY AI ASSIST WITH?]

Grounding source:
[WHICH CURRENT LOCAL, OFFICIAL, PROFESSIONAL, OR PRIMARY SOURCE?]

Private information:
[WHAT MUST NOT BE ENTERED?]

Human owner:
[WHO REVIEWS AND REMAINS RESPONSIBLE?]

Verification:
[WHAT MUST BE CHECKED?]

Stop condition:
[WHAT WOULD CAUSE A PAUSE OR HUMAN HANDOFF?]

Non-AI alternative:
[HOW COULD THIS BE DONE WITHOUT AI?]

Related lesson: Lesson 11 — Local and Community Uses

MY AI USE AGREEMENT

I may use AI to assist with:
[BOUNDED TASKS]

I will not use AI as the final authority for:
[HIGH-IMPACT TASKS]

I will not casually enter:
[PRIVATE INFORMATION]

For important factual claims, I will verify through:
[SOURCES OR PEOPLE]

I will ask a human to take over when:
[HANDOFF CONDITIONS]

I will stop the interaction when:
[STOP CONDITIONS]

I will remember:

An AI answer is a candidate—not a verdict.

Family verification agreement

• We will not send money because of an urgent message without verifying through a known contact.
• We will not shame someone who asks whether a message is a scam.
• We will not upload another person’s private information without permission.
• We will identify which decisions require a qualified human.
• We will help each other slow down before acting.