AI prompt for doing a competitor analysis

Written for Claude. Compiled as a analysis task — evaluating evidence, comparing options, and reaching a defensible judgement.

<role>
You are a rigorous analyst who separates evidence from inference and states uncertainty plainly.
</role>

<context>
What we do: {{our_product}}. What I already know about each: {{known}}. The decision this informs: {{decision}}.
</context>

<task>
Analyse these competitors: {{competitors}}.
</task>

<approach>
Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.
</approach>

<constraints>
- Separate what you know from the information supplied, from what you are inferring, from what you cannot determine.
- Do not invent pricing, customer counts, funding or feature lists.
- Assess against the stated decision, not against a generic feature grid.
- Name where each competitor is genuinely better.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Separate what the evidence shows from what you are inferring. Label every inference as an inference.
- State the strongest argument against your own conclusion before you state the conclusion.
- Where the evidence does not support a confident answer, say so instead of manufacturing one.
</constraints>

<output_format>
Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.
</output_format>

<success_criteria>
Before you finish, check the output against every item below and fix anything that fails.

- Every claim is attributed or explicitly marked as unverified.
</success_criteria>

<before_you_start>
If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.
</before_you_start>

Now, analyse these competitors: {{competitors}}.

Open this in the prompt builder to add your own context and see what would improve it most.

What makes doing a competitor analysis hard to prompt for

Competitor analysis is where fabrication is most tempting and least visible: pricing, headcount and feature lists all sound checkable and are frequently invented. The second failure is a feature grid that answers no actual decision.

Why this prompt works

Background comes before the instruction

The model reads the situation before it learns what to do with it, which stops the instruction being diluted by everything that follows. The task is then restated as the final line, where models weight it most heavily.

Rules a analysis task assumes but nobody writes down

Separate what the evidence shows from what you are inferring. Label every inference as an inference. State the strongest argument against your own conclusion before you state the conclusion. These are added automatically because leaving them implicit is the most common reason this kind of output disappoints.

Uncheckable words replaced with checkable ones

"better" reads like a requirement but cannot be verified by the model. The prompt swaps it for a property that can be checked, which is the difference between a request and a specification.

Success criteria the model checks itself against

Stating how the output will be judged gives the model something concrete to verify before it finishes. Prompts without criteria produce work that is plausible but incomplete, because nothing defined when it was done.

Permission to ask instead of guess

This brief leaves room for interpretation, so the prompt tells the model to ask before inventing details. That converts a confidently wrong answer into a question you can actually answer.

What to replace

Check the output before you use it

• Verify every pricing and company figure on the competitor's own site before using it.
• Check the analysis answers your stated decision rather than listing features.
• Confirm each competitor has at least one area where they are genuinely stronger.

The same prompt for other models

Identical content, packaged the way each model reads most reliably.

## Role

You are a rigorous analyst who separates evidence from inference and states uncertainty plainly.

## Context

What we do: {{our_product}}. What I already know about each: {{known}}. The decision this informs: {{decision}}.

## Task

Analyse these competitors: {{competitors}}.

## Approach

Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.

## Constraints

- Separate what you know from the information supplied, from what you are inferring, from what you cannot determine.
- Do not invent pricing, customer counts, funding or feature lists.
- Assess against the stated decision, not against a generic feature grid.
- Name where each competitor is genuinely better.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Separate what the evidence shows from what you are inferring. Label every inference as an inference.
- State the strongest argument against your own conclusion before you state the conclusion.
- Where the evidence does not support a confident answer, say so instead of manufacturing one.

## Output format

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.

## Success criteria

Before you finish, check the output against every item below and fix anything that fails.

- Every claim is attributed or explicitly marked as unverified.

## Before you start

If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.

Now, analyse these competitors: {{competitors}}.

**Task**

Analyse these competitors: {{competitors}}.

**Role**

You are a rigorous analyst who separates evidence from inference and states uncertainty plainly.

**Context**

What we do: {{our_product}}. What I already know about each: {{known}}. The decision this informs: {{decision}}.

**Approach**

Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.

**Constraints**

- Separate what you know from the information supplied, from what you are inferring, from what you cannot determine.
- Do not invent pricing, customer counts, funding or feature lists.
- Assess against the stated decision, not against a generic feature grid.
- Name where each competitor is genuinely better.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Separate what the evidence shows from what you are inferring. Label every inference as an inference.
- State the strongest argument against your own conclusion before you state the conclusion.
- Where the evidence does not support a confident answer, say so instead of manufacturing one.

**Output format**

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.

**Success criteria**

Before you finish, check the output against every item below and fix anything that fails.

- Every claim is attributed or explicitly marked as unverified.

**Before you start**

If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.

Now, analyse these competitors: {{competitors}}.