Hire an AI brand message consistency reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A brand file of eight plain files with each fact tagged by its source
• A fit score out of 100 and a ranked fix list, ordered by what shoppers see first
• A voice score out of 100 for your sample copy, with the weak lines rewritten
• A printable brand guide with colour pairs checked for readable contrast, and a tokens file

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: Your site, emails and packaging feel like different companies.

• Step 1: Brand file. Eight plain files on facts, offers, buyers, claims, voice and look, with each fact tagged by its source.
• Step 2: Touchpoint audit. A scan of each asset, a touchpoint list, price fit, a score out of 100 and fixes ranked by visibility.
• Step 3: Voice edit. A line-by-line voice check, the rewritten weak lines and a voice score out of 100.
• Step 4: Brand guide. A quick sheet, checked colour pairs, type, voice, do and don't, and a tokens file.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Step 1: every voice rule, promise and claim names the page it came from.
• Step 2: every touchpoint has a score, and each ranked gap quotes the line that causes it.
• Step 3: every rewrite uses only facts from the brand file.
• Step 4: the guide has voice rules, look notes, do and don't lists, and before and after lines.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Seth Godin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Build your brand file. Reads the site and your reviews, tags every fact by source and status, and writes eight plain files on offers, buyers, claims, voice and look.
• Audit your touchpoints. Scans each asset for three seconds, lists every touchpoint, checks price fit and trust cues, scores the fit and ranks the fixes.
• Edit the voice. Checks each line of sample copy against the voice rules and rewrites weak lines. It changes wording only, never claims or offers.
• Build the brand guide. Packages voice, colours, type and do and don't into a guide with a quick sheet first, plus a copy-paste tokens file.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id make-every-touchpoint-say-the-same-thing only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/make-every-touchpoint-say-the-same-thing/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your store address, plus any pasted pages if it can't be read
• Customer reviews or survey answers (optional)
• Screenshots of your homepage, a product page, your pack and a promo email
• A sample of your current ad or email copy (optional)
• Your logo rules and colour codes (optional)

Tools and access

• Any good chat AI that reads images: It must see the real screens. Attach each as a file at full size.
• A phone and a friend: Hand a stranger your phone for three seconds. It is the quickest check of the scan result.
• Any good chat AI: Claude, ChatGPT and Gemini all do this well when the voice notes and customer quotes are pasted in full.
• Claude: Writes the whole guide as one HTML file and shows a live preview, so you can check the pages before printing.
• Google Chrome: Its Print to PDF follows the A4 page size and page breaks the guide sets.

Functions and deliverables

• Brand message consistency reviewer: Share store pages, emails, packaging and buyer evidence. Get message mismatches ranked, sample copy edits and a practical brand guide.
  • A brand file of eight plain files with each fact tagged by its source
  • A fit score out of 100 and a ranked fix list, ordered by what shoppers see first
  • A voice score out of 100 for your sample copy, with the weak lines rewritten
  • A printable brand guide with colour pairs checked for readable contrast, and a tokens file
• Store brand consistency reviewer: Check your store brand signals before a redesign. Give it your site, emails, pack and ads. You get a score out of 100 and a fix list.
  • A score out of 100 and how it was worked out, now and with the fixes made
  • A signal-by-signal list of what each asset reminds a scanner of, who it attracts and who it repels
  • A touchpoint list with the main message, voice and look at each
  • A fix list, ordered by how many shoppers see each problem, with owners
• Brand voice editor: Paste your ad, voice rules and customer quotes. Get small wording fixes that keep claims intact, plus a line-based voice score.
  • A verdict, on voice or needs fixes, with a one-sentence summary
  • Each off-voice phrase quoted exactly, with the rule or customer quote it breaks
  • The full corrected line for each fix, with numbers and claims unchanged
  • A voice score out of 100 (the share of lines on voice), now and after the fixes
• Brand guide builder: Turn your brand file into a printable brand guide and a values file to paste into any design tool. Colour pairs are checked so text stays readable.
  • A printable HTML guide of up to eight A4 pages, in your own colours and fonts, with a quick sheet on page 2
  • A contrast table showing which text colours can sit on which backgrounds
  • A tokens file with every colour, font and rule, plus CSS variables and a design tokens block
  • A two-line note on what was left out and which colour pairs fail for text
  • Any of its seven checks the guide still misses, each named
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Seth Godin: Plan audience choice, email permission or a small launch using Seth Godin’s recorded approach. Name your audience and what makes the work worth sharing.
  • Your problem worked on the way Seth Godin would: their questions, their method, their push-back
  • The answer or the work, in Seth Godin's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your site, emails and packaging feel like different companies.
• A new writer, designer or agency keeps getting the voice wrong.
• You are about to redesign or relaunch and want to know what is off first.

Limits to check before starting

• Your brand has no live site or reviews yet: start with the Brand profile builder alone, then come back.
• You only need a short voice summary for writers: use the Brand voice one-pager writer.
• You only want a guide from a brand file you already have: use the Brand guide builder.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your store link and attach screenshots. The AI can read images, so do not describe them in words.
• Answer its short check-in question about anything the site can't say.
• Check the ranked fix list before you act on it. The audit measures fit, not whether copy sells.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/make-every-touchpoint-say-the-same-thing for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.