Messaging prompts

AI competitor review mining prompt

Mine competitor reviews for customer language, objections, switching reasons, and proof gaps.

This is a working analyst brief. Sources go in. Patterns, risks, and decisions come out.

Use this prompt

You are a voice-of-customer research analyst.

Analyze competitor reviews for language and patterns we can learn from without inventing sentiment.

My company:
{{my_company}}

Competitor:
{{competitor}}

Market:
{{market}}

Sources:
{{sources}}

Return:
1. Repeated customer phrases.
2. Jobs customers hire the product for.
3. Objections and complaints.
4. Switching triggers.
5. Proof gaps competitors leave open.
6. Copy angles we can test with our own evidence.

Rules:
- Use only the sources I provide.
- Do not invent metrics, spend, conversion rates, private pricing, customers, or intent.
- Mark unsupported claims as [UNVERIFIED].
- Separate observation, interpretation, and recommendation.
- Do not treat a few reviews as market-wide proof.

Advanced AI technique settings:
- Source-grounded context pack: Build a source table first with source, date checked, claim, confidence, and business meaning. Use only that table for the final recommendations.
- Few-shot calibration: Add one or two examples of a good finding and a bad finding before the source pack, then follow that standard in the output.
- Pattern clustering: Cluster repeated signals before interpreting them. Label one-off examples as one-offs and do not treat them as strategy.
- Delimited inputs: Keep each input in a separate section such as <my_company>, <competitor>, <source_pack>, <goal>, and <output_format> so the model does not blend roles and evidence.
- Verification loop: After the first draft, run a verification pass that lists unsupported claims, stale details, missing sources, and recommendations to downgrade or remove.

Copy the prompt. Fill the variables. Then check the output for real.

Advanced AI techniques

Use these techniques for this prompt

These are selected for this specific competitor research job. Use the prompt-ready instruction when it helps, and skip it when the condition does not fit.

Source grounding

Source-grounded context pack

Use when: Use when the answer depends on competitor pages, screenshots, ads, pricing, SEO exports, or reviews.

Prompt move: Build a source table first with source, date checked, claim, confidence, and business meaning. Use only that table for the final recommendations.

Skip when: Skip only for brainstorming with no factual claims.

Calibration

Few-shot calibration

Use when: Use when tone, scoring, or finding quality matters more than generic completeness.

Prompt move: Add one or two examples of a good finding and a bad finding before the source pack, then follow that standard in the output.

Skip when: Skip when you do not have a reliable example to imitate.

Pattern analysis

Pattern clustering

Use when: Use for batches of ads, emails, social posts, reviews, SEO pages, or competitor claims.

Prompt move: Cluster repeated signals before interpreting them. Label one-off examples as one-offs and do not treat them as strategy.

Skip when: Skip for a single landing page or one pricing table.

Prompt structure

Delimited inputs

Use when: Use when mixing company context, competitor evidence, goals, examples, and output requirements.

Prompt move: Keep each input in a separate section such as <my_company>, <competitor>, <source_pack>, <goal>, and <output_format> so the model does not blend roles and evidence.

Skip when: Skip for very short single-source prompts.

Verification workflow

Verification loop

Use when: Use before sharing research with a client, team, sales deck, ad brief, or website backlog.

Prompt move: After the first draft, run a verification pass that lists unsupported claims, stale details, missing sources, and recommendations to downgrade or remove.

Skip when: Skip only for private rough notes.

Replace placeholders

Replace these variables before running the prompt

Variable	Meaning	Type	Example
`{{my_company}}`	Your company, product, or brand	string	Northstar CRM
`{{competitor}}`	The competitor you want to analyze	string	Acme CRM
`{{market}}`	The category or market context	string	B2B CRM for agencies
`{{sources}}`	URLs, screenshots, notes, exports, or pasted copy	list	Homepage URL, pricing URL, ad screenshots

Expected shape

Compare a filled input with a realistic output shape

The output below is fictional. It shows the shape you are looking for, not a real competitor result.

Example input

my_company = ShiftPlan
competitor = RotaBee
market = staff scheduling software
sources = 40 G2 and Capterra review snippets with dates

Fictional example output

Fictional example output:

Repeated phrase: last-minute shift changes.
Objection: mobile app reliability.
Copy angle: prove manager visibility during schedule changes.
Caution: review sample is skewed toward unhappy support cases.

Prompt logic

Why this prompt works

It uses customer words instead of marketer language.
It separates patterns from anecdotes.
It turns reviews into proof and objection work.

Mistakes to avoid

Asking the AI to analyze a competitor with no sources.

Paste the page copy, ad screenshots, pricing table, SEO notes, or transcript first.

Treating the output as research truth.

Use it as a source-backed brief: keep strong evidence, downgrade weak evidence, and decide what deserves action.

Asking for generic strategy advice.

Ask for observations, risks, and next actions tied to the evidence.

Verification checklist

Every factual claim has a source or is marked as unverified.
Pricing, dates, and product claims were checked on the original source.
The output separates observation from interpretation.
The output gives actions you can reject, edit, or test.
Nothing is treated as final just because an AI tool wrote it.

Use the output safely

What you should do next

Keep review source and date attached.
Quote phrases carefully.
Validate patterns against sales calls or your own reviews.