Skip to content

Level 1 · Guide 03

Write an AI work brief, not a magic prompt

A strong Claude prompt is a clear work brief, not a magic phrase. State the desired result, context, approved inputs, constraints, output format, and acceptance criteria, and require questions before Claude fills important gaps.

Product features may change. Check the last verified date and official sources.

Core concepts to know first

Focus on the decisions these terms support in real work rather than memorizing them.

Core concepts

1. The eight elements of a work brief

A brief makes success observable. It names the audience, purpose, source priority, exclusions, output shape, and review gate so Claude can ask about missing conditions rather than inventing them. In this guide, the first observable move is to write the outcome, audience, and acceptance criteria.

2. Acceptance criteria come first

List approved inputs, constraints, and source priority. Preserve the approved input and the evidence behind the result so a reviewer can distinguish what the source says from what Claude inferred. This directly controls the risk that a long prompt can still hide an unclear objective.

3. State source priority

Ask Claude to identify missing information before drafting. Record the decision and the remaining uncertainty instead of hiding it in polished prose. The review must explicitly test whether conflicting source files can silently change the result.

4. Turn missing conditions into questions

Treat the possibility that missing acceptance criteria makes review subjective as a required test case. The intended result is a reusable eight-part ai work brief, not an unreviewed answer that merely looks complete.

Synthetic work scenario

How this applies at work

This scenario was written for learning and is not a real customer case.

A fictional Korean education company needs an internal launch notice. The owner provides an approved schedule, intended audience, forbidden claims, table format, and a rule that uncertain details must appear in an open-questions section.

The scenario is newly written for this guide and is neither a customer case nor a performance claim. Its specific deliverable is a reusable eight-part ai work brief. A reviewer can reproduce the work from the synthetic inputs without access to customer, employee, health, contract, or confidential company data.

Try it yourself

Choose one small task and follow the steps. Confirm organizational policy and data boundaries before using sensitive materials.

  1. Step 1. Write the outcome, audience, and acceptance criteria

    Write the outcome, audience, and acceptance criteria. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  2. Step 2. List approved inputs, constraints, and source priority

    List approved inputs, constraints, and source priority. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  3. Step 3. Ask Claude to identify missing information before drafting

    Ask Claude to identify missing information before drafting. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

Completion checklist

Check only what you verified yourself. Every item must be checked before saving completion.

Completion checklist

Some items are still unchecked. Review the result again.

What could go wrong?

Plausible language does not guarantee accuracy. Compare the result with originals, calculations, permissions, and current information.

  • A long prompt can still hide an unclear objective
  • Conflicting source files can silently change the result
  • Missing acceptance criteria makes review subjective

Boundaries that require human review

Academy practice stops at draft, preview, or approval pending. Actions with real impact require separate owner approval outside Academy.

What AI can do

  • Step 1. Write the outcome, audience, and acceptance criteria
  • Step 2. List approved inputs, constraints, and source priority
  • Step 3. Ask Claude to identify missing information before drafting

What a person must approve

  • Applicable law, contract, organizational security policy, and explicit approval boundaries take priority. Stop and ask the responsible owner when they conflict.
  • Academy exercises never send, publish, purchase, delete, execute contracts, or change permissions. A responsible person performs any real action through a separate process.

This guide is educational and does not replace legal, security, or privacy judgment for your organization.

Questions about this guide

When is this guide complete?
It is complete when the stated outcome is ready and another reviewer can retrace the inputs, evidence, boundaries, and decision. The target outcome is “A reusable eight-part AI work brief.”
May I practice with real company data?
No. Use synthetic material in the Academy. Real data requires a separate review of policy, legal basis, contracts, minimization, retention, deletion, and the approved environment.
What if the product screen differs from this guide?
Product behavior can change. Check the verification date and official sources, then retest the current account and plan with a small, low-risk example.

Official sources and further reading

Recheck the current product and policy status in these primary sources.

  1. Anthropic AI Fluency Index · Anthropic Research
  2. Give Claude context with CLAUDE.md and better prompts · Claude Help Center

Authorship and review

Author
QJC
Last verified
2026-07-23
Update sensitivity
Medium
Tested product surface
Official documentation and QJC training scenarios using synthetic data
Tested plan
Reconfirm feature and account availability in official sources on the day of use

Save progress

Completion and checklist items are saved only in this browser. They do not sync to other devices or browsers.

Academy does not collect or store work materials, prompts, or outputs. It runs no separate analytics scripts beyond basic server access logs.

QJC Claude Academy is unofficial educational content independently created and operated by QJC. It is not an official course operated, sponsored, certified, or affiliated with Anthropic. Claude and Anthropic are trademarks of Anthropic PBC.