← Back to Blog
PromptsAI DevelopmentLLMTutorial

Prompting 101: How to Make a Good Prompt

A practical guide to writing clear, effective prompts that get consistent results from LLMs.

Ryan Brandt - Author
Ryan Brandt
AI Agent Consultant & Founder of Vunda AI
•6 min read

Most people write terrible prompts. They're vague, confusing, and then they wonder why the AI gives them garbage outputs.

Good news: Writing good prompts is a learnable skill. This guide will show you exactly how to do it.

The Problem with Most Prompts

What Most People Write“Write a good email”❓ To whom? About what?“Make this better”❓ Better how? By what criteria?“Help me with my recipe”❓ What kind? For whom?🤖???Result: Inconsistent, unpredictable outputs

Here's what most people write:

"Write a good email"

"Make this better"

"Help me with my recipe"

These prompts fail because they're missing critical information. The AI has to guess what you want, and it will guess wrong.

The Anatomy of a Good Prompt

The 5 Components of a Good Prompt1Role & ContextWho is the AI? What’s the situation?“You are a professional chef...”2Clear ObjectiveWhat exactly should be done?“Create a healthy chicken recipe...”3Specific ConstraintsBoundaries and requirements“Under 30 min, max 10 ingredients...”4Output FormatHow should the response look?“Recipe name, ingredients, steps...”5Examples (Optional)Show what good output looks like when the task is complex or ambiguousGood Prompt!

A good prompt has five key parts:

1

Role & Context

Tell the AI who it is and what situation it's in

Email Writing Context

❌Bad

Write an email

✅Good

You are a customer success manager writing to a frustrated enterprise client

2

Clear Objective

State exactly what you want to accomplish

Recipe Request

❌Bad

Help with recipe

✅Good

Create a 30-minute weeknight dinner recipe using chicken and vegetables

3

Specific Constraints

Set boundaries and requirements

Length and Tone

❌Bad

Keep it short

✅Good

Maximum 5 sentences, professional tone, include next steps

4

Output Format

Define how you want the response structured

Response Structure

❌Bad

(No format specified)

✅Good

Format as bullet points with headers for each section

Note: Format can be anything verifiable - JSON, bullet points, numbered lists, etc.
5

Examples (When Needed)

Show what good looks like

Tone Example

❌Bad

Make it sound friendly

✅Good

Tone example: 'Thanks for reaching out! I understand your concern and I'm here to help.'

Writing a Specification: The Do's and Don'ts Method

Writing Specifications: The Do’s and Don’ts MethodStep 1: Start with what NOT to do(Often easier to identify failures)❌ Never include allergens❌ Never use vague terms❌ Never exceed 30 minutes❌ Never omit key infoTHENStep 2: Add what TO do(Make each constraint verifiable)✅ Always list allergens upfront✅ Always use exact temps/times✅ Always show total time✅ Always include nutrition factsExample Specification Structure(Your actual prompt will be dictated by your product needs)1. Role + Objective:“You are X. Your goal is Y for user Z.”2. Always Do:Verifiable positive constraints3. Never Do:Clear negative constraints4. Output Format:Structure that can be verified5. Context:User profile, retrieved docs, prior turns6. Examples (optional):1-2 good outputs (not 20!)

A good prompt needs a specification - a clear definition of what the AI should always do AND what it should never do. Both are equally important.

What is a Specification?

A specification is a contract between you and the AI. It defines:

  • What to always do (positive constraints)
  • What to never do (negative constraints)

These work together to create precise boundaries for the AI's behavior.

Pro tip: It's often easier to start by identifying what NOT to do. When you know what failures look like, it becomes clearer what success should be.

The Key Rule: Make It Verifiable

Every constraint in your specification must be easily verifiable. If you can't quickly check whether the AI followed a rule, that rule is too vague for effective evaluation.

Bad (Not Verifiable):

  • "Write engagingly"
  • "Be helpful"
  • "Sound natural"

Good (Verifiable):

  • "Include exactly 3 bullet points"
  • "Never exceed 100 words"
  • "Always end with a question"

Example Specification for a Recipe Generator:

1

Always Do

  • Include exact cooking temperatures and times
  • List ingredients in order of use
  • Specify serving sizes
  • Use common supermarket ingredients
2

Never Do

  • Never include nuts or shellfish (allergy concerns)
  • Never use vague terms like "cook until done"
  • Never exceed 10 ingredients total
  • Never require specialty equipment

Why Both Matter

Including both do's and don'ts in your prompt:

  • Prevents common failures before they happen
  • Reduces ambiguity by defining boundaries from both sides
  • Improves consistency across multiple uses
  • Makes debugging easier when outputs go wrong

A Real Example

Let's transform a bad prompt into a good one:

Prompt Transformation: Before & After❌ Before“Write a summary”Problems:• Summary of what?• How long?• For whom?• What format?• What to emphasize?• What tone?Transform✅ AfterROLE:You are a business analyst preparingan executive briefing.TASK:Summarize the Q3 sales report for the CEOALWAYS:• Include revenue change vs Q2 (%)• List exactly 3 top products• Identify 1-3 Q4 risks• Use exact numbers/percentages• Start with 1-sentence overview• Format as bullet pointsNEVER:• Exceed 5 bullet points total• Use vague terms (“many”, “some”)• Include operational details• Exceed 150 words totalNow measurable:✓ Has 5 bullets ✓ Contains numbers ✓ Clear CTA

Before:

"Write a summary"

After:

You are a business analyst preparing an executive briefing.

Summarize the Q3 sales report for the CEO.

Always:

  • Include revenue change vs Q2 (%)
  • List exactly 3 top products
  • Identify 1-3 Q4 risks
  • Use exact numbers/percentages
  • Start with 1-sentence overview
  • Format as bullet points

Never:

  • Exceed 5 bullet points total
  • Use vague terms ("many", "some")
  • Include operational details
  • Exceed 150 words total

Quick Checklist

Before you hit enter, ask yourself:

Did I specify the role?
Is the objective crystal clear?
Are my constraints specific (not vague)?
Did I define the output format?
Would a human understand this brief?

Common Mistakes to Avoid

1. Being Too Vague

❌Bad

Make it professional

✅Good

Use formal language, avoid contractions, address as 'Dear Mr. Smith'

2. Conflicting Instructions

❌Bad

Be concise but thorough and detailed

✅Good

Cover these 3 points in 2-3 sentences each

3. Missing Context

❌Bad

Explain the process

✅Good

Explain our refund process to a first-time customer who bought shoes online

4. No Success Criteria

❌Bad

Write a good bio

✅Good

Write a 100-word LinkedIn bio that mentions my role, experience, and includes a CTA

The Golden Rule

If a human intern would need to ask clarifying questions, your prompt needs work.

Good prompts eliminate ambiguity. They're so clear that there's really only one way to interpret them.

Start Simple, Then Iterate

You don't need to write perfect prompts on the first try. Start with something basic, see what goes wrong, then add constraints to fix it.

1
Round 1:
Write a product description
→ Output too long and technical
2
Round 2:
Write a 50-word product description for general consumers
→ Missing key features
✓
Round 3:
Write a product description. Always: • Keep between 45-55 words • Mention the main benefit first • Include price • Use everyday language Never: • Use technical jargon • Include specs or model numbers • Exceed 2 sentences
✅ Success!

Key Takeaways

1

Be specific

Replace vague words with concrete requirements

2

Tell, don't just show

Clear specifications beat vague examples

3

Think constraints

What should it NOT do?

4

Format matters

Define the structure you want

5

Test and refine

Your first prompt is a rough draft

Remember: The AI can't read your mind. The clearer your instructions, the better your results.

Ready to Build Production AI Agents?

Let's discuss how AI agents can transform your business operations

Book a Strategy Call