Home/Starter Kit/Practical Prompt Framework
4Component Four

The CLEAR Prompt Framework

The gap between a disappointing AI result and an excellent one is almost never the tool. It is the five pieces of information you did or did not supply.

15 min read
5 elements
Highest leverage skill

When output is poor, most people rephrase and hope. The skill worth building is being able to say precisely which element was missing — and add it deliberately.

Why vague prompts produce vague output

An AI model has no access to your situation. It does not know your role, who will read the result, how much detail you need, what format you require, or what "good" looks like to you. When you leave those unstated, the model does the only thing it can: it produces the statistically average response to your question.

Average is exactly what you get. Generic, plausible, mildly useful, and not quite right. Then you conclude AI is overrated.

Consider the difference:

Vague

Write about project management.

Produces a generic overview useful to nobody in particular.

Specific

You are a delivery manager. Write a 200-word update for non-technical executives explaining a two-week slip, its cause, and the recovery plan. Direct tone, no jargon, end with what we need from them.

Produces something you could almost send.

Same model. Same session. The entire difference is supplied information.

The five elements

C

Context — the situation and background

What is happening, what led to it, and what the model needs to know to respond sensibly. This is the most frequently omitted element and the most costly one.

Weak: "Help me write an email."
Strong: "A client missed our third deadline. We have worked together two years. I want to raise it firmly without damaging the relationship."

L

Level — the required difficulty or experience level

Tells the model how much to assume. Without it, explanations land either patronising or impenetrable.

Examples: "Explain as if I have never seen this before." · "I have eight years in this field, skip the fundamentals." · "Pitch it for a smart colleague from a different department."

E

Expected outcome — what you actually want

Name the artefact. "Help me with the report" is a topic. "Produce a one-page summary with three findings and a recommendation" is an outcome.

A useful test: could someone else look at the result and tell whether it satisfied your request? If not, you named a topic rather than an outcome.

A

Audience — who the result is for

Changes vocabulary, length, tone, and what can be assumed. The same content for a CEO, a junior engineer, and a customer are three genuinely different documents.

Examples: "For our CFO, who cares about cost and risk." · "For new joiners in week one." · "For a frustrated customer awaiting a fix."

R

Requirements — format, tone, limits, quality standards

The constraints that make output usable without reformatting. Length, structure, tone, things to include, things to avoid.

Examples: "Under 300 words." · "Use a table." · "No marketing language." · "Include one worked example." · "Flag anything you are uncertain about."

You do not always need all five

For simple requests, Context and Expected outcome are often enough. The framework is a diagnostic checklist, not a mandatory form. Its real value appears when output disappoints — run through the five and you will almost always find the missing one.

The reusable template

CLEAR template
You are a [role or expert]. Context: [Explain the situation and relevant background.] My experience level is: [Beginner / intermediate / advanced in this area.] My goal is: [Describe the specific outcome you want.] The audience is: [Who will read or use this, and what they care about.] Requirements: - Use simple language - Organise the answer step by step - Include practical examples - Avoid unnecessary jargon - Mention common mistakes - End with an action checklist Before finalising, review your answer for clarity, usefulness, accuracy, and completeness.

That final instruction matters more than it looks. Asking the model to review its own output against named criteria consistently improves the result, because it forces a second pass rather than a single generation.

Diagnosing bad output

This is where the framework earns its place. When a result disappoints, do not rewrite blindly — identify the symptom.

SymptomMissing elementFix
Generic, could apply to anyoneContextAdd your situation, constraints, and history
Too basic, or too advancedLevelState your experience explicitly
Interesting but not what you neededExpected outcomeName the exact artefact and its structure
Wrong tone or wrong vocabularyAudienceSay who reads it and what they care about
Right content, unusable shapeRequirementsSpecify length, format, and what to avoid
Confidently wrong factsRequirementsAdd "flag anything uncertain" — then verify independently

Before you press send

Prompt quality checklist
  • Did I explain the context?
  • Did I clearly state the outcome I want?
  • Did I identify the audience?
  • Did I mention the required format?
  • Did I define important limitations?
  • Did I ask for examples?
  • Did I ask the AI to review its own answer?

A worked upgrade

Watch the same request improve across three passes.

Attempt 1 — topic only
Help me prepare for my performance review.

Returns generic advice: list achievements, be positive, ask about growth. Nothing you did not already know.

Attempt 2 — context and outcome added
I am a QA engineer with 6 years experience. My review is next week. I led automation for two releases but missed a delivery date in Q3. Help me prepare talking points that acknowledge the miss without undermining the wins.

Substantially better — now specific to the situation.

Attempt 3 — full CLEAR
You are an experienced engineering manager who has run hundreds of performance reviews. Context: I am a QA engineer, 6 years experience. My annual review is next week. I led test automation for two major releases which cut regression time by 40%. I also missed a Q3 delivery date by two weeks due to unclear requirements. My experience level: I have had five reviews before but have never negotiated a promotion. Goal: Prepare six talking points I can genuinely defend, plus how to raise the missed deadline before my manager does. Audience: My manager — data-driven, dislikes excuses, responds well to ownership and specifics. Requirements: - Each point in one or two sentences I could say aloud - Include the metric or evidence supporting each - For the missed deadline: ownership, then what changed - Flag any point that sounds defensive - End with three questions I should ask about progression Review your answer for whether each point would survive a sceptical follow-up question.

Now returns something genuinely usable — specific, defensible, tailored to the person in the room.

The third prompt took perhaps ninety seconds longer to write. It saved an hour of editing and produced a materially better outcome.

Common mistakes

Retrying with slightly different words when output disappoints
Diagnose which of the five elements was missing, then add exactly that.
Writing a long prompt that is still vague
Length is not specificity. A short prompt with clear context beats a long one full of adjectives.
Abandoning after the first attempt
Treat the first output as a draft that reveals what your prompt was missing.
Never saving prompts that worked
A good prompt is an asset. Rewriting it from scratch each time discards the work.
Accepting confident output without checking
Fluent and correct are unrelated properties. Verify anything with consequences.

Practise this week

✍️ Prompt practice

A note, a doc, anywhere you will find it again.

What comes next

You now have the structure. The next component gives you working prompts built on it — ready to adapt for learning, career planning, productivity, email, meetings, research, and problem-solving.

Previous component ← Beginner AI Tool Guide

Get the full AI Starter Kit

This framework is one of eight components. The complete kit includes printable worksheets, the prompt library, job-specific use cases, and the full 30-day plan.

All eight components