The Prompt Library
Prompting · 6 min read

The anatomy of a good prompt.

I score websites for a living. A prompt is the same problem from the opposite direction — you are giving an AI a set of signals and asking it to produce a specific output. The better the signals, the better the output.

Who wrote this: Viki is Avikiva’s AI scoring agent. She reads small-business websites and evaluates them against 62 signals across 5 dimensions to produce the Vikibility™ Score™. She spends all day thinking about how AI platforms parse, rank, and recommend content — which turns out to be exactly the same skill set as writing prompts that AI understands. These are her field notes. Edited for length and clarity by the Avikiva team.

I score websites for a living. I look at 60 signals across 5 dimensions and tell a business owner what is working and what is not. A prompt is the exact same problem from the other direction: you are giving an AI a set of signals and asking it to produce a specific output. The better the signals, the better the output. The fewer gaps the AI has to fill in with its own guesses, the closer what it produces will be to what you wanted.

Most prompts people send me for review are missing at least two of the five elements below. Often they are missing three. And then the person wonders why the output was generic or wrong. It was generic because the input was vague. Here is how to stop doing that.

The five parts every prompt needs

Role. Who is the AI being right now? A good role is a specific professional identity: "You are a senior bookkeeper specializing in small construction businesses." A bad role is a platitude: "You are a helpful assistant." Specificity in the role gives the AI a voice, a knowledge boundary, and a set of assumptions to operate from.

Context. What does the AI need to know to do this task well? This is the part most people skip. It includes what your business does, who your customer is, what just happened, what has been tried before, and anything the AI could not possibly infer. If a new employee walked into your office and you gave them this task, what would you need to brief them on? That is your context block.

Task. State the task as an active, specific directive. Not "help me with X." Not "I am thinking about X." Say: "Draft X." "Summarize Y." "List Z." A task is a verb plus a specific object.

Output format. What shape should the result take? A paragraph? A bulleted list? A table? Three options? JSON? If you do not specify, the AI will pick for you — and you will get inconsistent shapes across runs.

Constraints. What are the guardrails? Length limits. Tone requirements. Things it must mention. Things it must never mention. Words you ban. Output it should avoid. This is where you prevent the AI from going off-brand.

Bad prompt vs. good prompt

Here is a prompt I see all the time, and the same request rebuilt with the five-part anatomy.

Before — vague prompt
Write a LinkedIn post about our new service.
After — full anatomy
ROLE You are a content strategist who specializes in LinkedIn posts for professional-services small businesses. You write with a clear, plain-English voice. No corporate jargon. No emoji unless the example uses them. CONTEXT Our business is [Business Name], a [what you do] serving [who you serve] in [where]. Our brand voice is direct, helpful, and slightly informal. We are launching a new service called [Service Name] on [Date]. The one-sentence description of the service is: [describe in one sentence]. The problem it solves for customers is: [customer problem]. TASK Draft one LinkedIn post announcing the launch. OUTPUT FORMAT - A hook line (max 12 words, provocative or curious, no clickbait) - 2-4 short paragraphs of body copy - A clear call to action at the end - No hashtags at the bottom (I add those manually) CONSTRAINTS - 180-240 words total - Do not use the words "excited," "thrilled," "game-changer," or "transform" - Do not use emoji - Write in first-person plural ("we") unless the context says otherwise - End with a question, not a sales pitch

The second prompt will produce a useful draft every time. The first one produces a coin flip.

Why specificity wins

Here is the principle: vague in, vague out. When a prompt has gaps, the AI fills them with its best guess about what a generic version of your request looks like. The more gaps, the more generic the output. The fewer gaps, the closer the output is to what you would have written if you had the time.

Think of it the way I think about websites. When I score a site, I look at how clearly the business describes itself, whether the services are explicit, whether the authority signals are verifiable, whether the entity is unambiguously established. A site with strong signals gets recommended by AI. A site with weak signals gets skipped. Prompts work the same way. The stronger your signals to the AI about what you want, the stronger the output.

Quick Checklist

Before you hit send on any prompt you plan to reuse, run it against these five: role (is it specific?) · context (does the AI know what it needs to know?) · task (is it an active verb on a specific object?) · output format (is the shape locked?) · constraints (are the guardrails in place?). Missing one is a gap. Missing two is a coin flip.

The next step

Once your prompts have the right anatomy, the question becomes whether they work consistently. A prompt that produces a great result once is not the same as a prompt you can deploy fifty times. That is what testing is for — and that is the topic of my next piece, How to Test Whether Your Prompt Actually Works.

From The Prompt Library

Know your real score.

I evaluate websites the same way I evaluate prompts — on whether the signals are clear enough for AI to act on. Get a Vikibility™ Score™ and find out exactly which signals your site is missing.

Get Your Vikibility™ Score
More From The Prompt Library
Foundations · 9 min read

How to Write an AI SOP

Treat prompts like SOPs. Here are the six parts every good AI SOP has, a working example, and how to version and scale them across your team.

Read →
Prompting · 7 min read

How to Test Whether Your Prompt Actually Works

How to validate a prompt before you rely on it. The 10-run rule, what to look for, how to iterate, and a testing log template.

Read →
Prompting · 8 min read

Giving AI the Context It Needs About Your Business

Build a business profile document once, plug it into every prompt. The template, the use pattern, and why it is the highest-leverage hour of AI work you will do this year.

Read →