# The Verification Checklist

> **One-liner:** Build a personal AI verification system — a checklist you'll actually use — and stress-test it against real AI outputs to find its limits.

---

## 🔧 Jump in (Tinkerers start here)

You're going to build a verification checklist, then immediately try to break it.

**Step 1 — Generate something to verify.** Ask AI to produce a piece of content you might actually use in your work:

> Write a **[deliverable type — e.g., client email, project proposal, market analysis, technical recommendation]** about **[topic relevant to your work]**. Make it detailed and specific. Include data points, recommendations, and reasoning.

**Step 2 — Build your checklist.** Before reading the output carefully, write your own verification checklist. Start with these categories and add your own:

| Check | Question | Pass/Fail |
|-------|----------|-----------|
| **Factual claims** | Are specific numbers, dates, or statistics verifiable? | |
| **Sources** | Could I find the original source for any cited information? | |
| **Reasoning** | Does the logic hold? Are there hidden assumptions? | |
| **Completeness** | What important perspective or consideration is missing? | |
| **Tone/audience** | Is the tone appropriate? Would the intended audience trust this? | |
| **Actionability** | Are the recommendations specific enough to actually follow? | |
| **Your domain check** | [Add a check specific to your field] | |
| **Your domain check** | [Add another check specific to your field] | |

**Step 3 — Apply the checklist.** Go through the AI output line by line using your checklist. Mark each check as pass or fail. For every fail, note what the issue is.

**Step 4 — Stress-test the checklist.** Now deliberately ask AI to produce something harder to verify:

> Write the same type of **[deliverable]** but on a topic I'm less familiar with: **[topic outside your expertise]**. Make it equally detailed and authoritative.

Apply your checklist again. Where does it fail to catch problems? What check do you need to add?

**Step 5 — Finalize.** Update your checklist based on what you learned. Save it where you'll actually use it — bookmark it, pin it, print it, whatever works.

---

## 📋 Plan first (Planners start here)

Here's what you're about to do:

1. **Generate test content** — Ask AI to produce a work-relevant deliverable. This gives you realistic material to verify.
2. **Draft your checklist** — Build a structured verification list covering factual accuracy, reasoning quality, completeness, tone, and domain-specific concerns.
3. **Apply to familiar territory** — Use the checklist on AI output about a topic you know. This lets you calibrate how well the checklist catches real errors.
4. **Apply to unfamiliar territory** — Use the checklist on AI output about a topic you *don't* know well. This exposes gaps in your process — the errors you can only catch with domain knowledge.
5. **Iterate and save** — Update the checklist based on what it missed. Save it in a format you'll actually reach for.

**"Done" looks like:** A tested, refined verification checklist (8-12 items) saved in a usable format, with evidence of at least one error it caught and one gap you identified and fixed.

---

## 🧭 Why this matters (Strategists start here)

In [EP-Basic-01](/exercises/ethical-prompting/ep-basic-01/), you built a simple 3-question verification prompt. Here, you're building a **systematic process** — a checklist that works regardless of topic, catches both factual and reasoning errors, and is tuned to your specific work context. The community's 75% Ethical Prompting score means most people *intend* to verify AI output but lack a consistent method. A checklist turns good intentions into reliable behavior. At the advanced level, you'll scale this into a governance framework for a team; this exercise builds the individual practice first.

---

## Reflection

- Which check caught the most problems? Which was least useful?
- How did your verification experience change between the familiar topic and the unfamiliar one?
- Is your checklist something you'd actually pull up before sending an AI-generated deliverable? What format makes it most likely you'll use it?
- 💬 *Trade checklists with a colleague. Have them apply yours to an AI output from their work — their feedback will reveal blind spots specific to your domain.* (Social Learners)

## ⬆️ Level up

Ready for more? Try [EP-Advanced-01](/exercises/ethical-prompting/ep-advanced-01/) — where you'll design an AI governance framework for a team or project.

Back to [Ethical Prompting & Judgment](/pillars/ethical-prompting/)