Secure Your Spot
← Guides
AI Prompting · Guide 4 of 6

How to write prompts that actually get results.

MakerSquare 7 min read Beginner

Most people's first instinct with AI is to type something like "write me a marketing email" and see what comes out. The output is usually fine. Technically correct, nothing obviously wrong — and totally generic. You rewrite most of it anyway.

The problem isn't the AI. It's that you gave it almost nothing to work with. A vague prompt produces a vague output. The fix isn't a new tool or a different model — it's understanding what a good prompt actually contains.

Why most prompts don't work

Bad prompts fail for three predictable reasons:

1
No context
The AI doesn't know who you are, what you're building, who the reader is, or what constraints you're working under. It fills in the blanks with generic defaults.
2
No output format
You didn't say what you wanted: a list, a paragraph, a table, a short answer, a long answer, bullet points, a JSON object. The AI picks something. It's often not what you needed.
3
No constraints
Length, tone, audience, what to avoid, what not to make up — without these, the AI optimizes for "looks complete" instead of "actually useful."

The anatomy of a prompt that works

A reliable prompt has four parts. You don't always need all four — but knowing them helps you diagnose what's missing when the output misses the mark.

1
Role (optional but powerful)

Tell the AI what perspective to take. "You are a senior product manager reviewing this feature brief." "You are a direct, skeptical editor." This shifts the entire framing of the response.

You don't always need this — but when the tone or expertise level of the output matters, it's the fastest lever you have.

2
Context

What's the situation? Who are you? Who is the reader? What are you trying to accomplish? What has already been decided?

This is the part most people skip. It's also the part that does most of the work. The AI can't invent context you didn't give it — it can only guess, and guessing is how you get generic output.

3
Task
State what you want done. Be specific. "Write a 3-paragraph email" is better than "write an email." "List the three biggest risks" is better than "tell me about the risks."
4
Format

Tell the AI what to return. Bullet points, a numbered list, a table, a short paragraph, a JSON object, a markdown file, a 50-word summary. If the format matters for how you'll use the output, say so explicitly.

Before and after

Here's what this looks like in practice. Same goal, two different prompts.

Before
Write me a LinkedIn post about our AI bootcamp.
After
You are helping me write a LinkedIn post for MakerSquare, a 2-week in-person AI program in Austin for operators and founders who want to build real AI tools — not just learn about AI. My audience on LinkedIn is mid-career professionals, founders, and people who work in operations, marketing, or sales. They're curious about AI but don't know how to make it practical. Write a post that leads with a specific observation about why most AI training doesn't stick (something concrete, not generic). Then briefly explain what we do differently. End with a question or soft CTA. Tone: direct, warm, no hype. Short paragraphs. No hashtag spam. Under 200 words.

The second prompt takes 30 seconds longer to write. The output takes 30 seconds to edit instead of 10 minutes.

Giving Claude context about your project

If you're using Claude for a specific project — building an app, writing content for a company, analyzing a dataset — you'll be repeating the same context in every prompt. That gets tedious fast.

The solution is a CLAUDE.md file in your project folder. Claude reads it automatically at the start of every session. You write the context once; it's always there.

Rule of thumb: If you're pasting the same paragraph of context into every prompt, put it in CLAUDE.md instead. If you're writing a one-off prompt for a task you'll never repeat, include the context inline.

How to iterate when the output is wrong

The first output is rarely the final output. Iteration is the skill — knowing how to redirect without starting over.

1
Say what was wrong specifically

"Make it better" gives the AI almost no signal. "Make it shorter" or "the tone is too formal — make it sound like I'm talking to a colleague" gives it something to work with.

Vague
This isn't quite right. Can you try again?
Specific
The opening is too generic — it sounds like a press release. Rewrite just the first paragraph to start with the concrete problem, not a broad statement about AI.
2
Ask clarifying questions back
If the AI's output is ambiguous or went in an unexpected direction, ask it to explain its reasoning before asking it to redo the work. "Why did you structure it this way?" often reveals a misunderstanding you can quickly correct.
3
Show an example of what you want
If you have something that worked well before — a past email, a post you liked, a format that hit the right note — paste it in. "Write something like this, but for X audience and Y topic" is one of the most reliable prompts there is.

A quick-reference template

Copy this and fill in the blanks whenever you're starting a new task.

# Context
I am [who you are]. I'm working on [what the project is].
The audience for this is [who they are and what they care about].

# Task
[What you want done — specific action verb, not "help me with"]

# Constraints
- Tone: [direct / warm / formal / casual / etc.]
- Length: [under 200 words / 3 paragraphs / a list of 5 / etc.]
- Avoid: [jargon / clichés / specific phrases you don't like]
- Don't make up: [statistics / quotes / names / etc.]

# Format
[Bullet list / numbered steps / a single paragraph / markdown / JSON / etc.]

One more thing: Claude will tell you if your prompt is unclear or if it needs more information to do the task well. If you get a response that asks clarifying questions — that's a good sign. Answer them. The next output will be substantially better.

At MakerSquare, we spend Day 1 building the mental model for how to talk to AI so it produces useful work, not generic output. It's the foundation everything else builds on.

See the curriculum Secure Your Spot