Hire an AI brand voice consistency reviewer

Everything it can hand back

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

• A pass or not-passed result, and how many rounds it took
• The final draft with changed lines marked, and the slip each fixed
• Any flag left for a person, including claim and legal flags
• A count of repeat slips across drafts
• A suggested guide rule when a slip repeats three times

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

• Rewriting the whole draft when only some lines failed.
• Making the draft sound better by adding claims.
• Running more than three rounds. A person decides what is left.
• Treating one slip in one draft as a pattern.
• Passing a draft that has an open legal or claim flag.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: Several people or tools write your copy and it does not always sound like you.

• Result. One line saying passed or not passed, how many rounds it took, and whether the guide used was approved or a draft.
• Final draft. The best round of your draft, with the changed lines marked.
• What changed. Each changed line, the slip it fixed and the round it was fixed in.
• Still open. Any flag left for a person, including claim and legal flags, or none.
• Repeat slips. Slips seen in three or more drafts, with a suggested rule for your guide.
• Files and missing. Each round's saved file, then every MISSING line in one list.

How the work is checked

• No fact, number, price, date or claim changed in the rewrite.
• Lines that passed were kept word for word.
• The draft was checked after the last rewrite.
• No more than three rounds were run.
• 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.

Capabilities

• Get the guide. Uses your voice guide, or builds one from your brand file once and waits for your approval.
• Check the draft. Ranks every deviation from your voice by severity, with a before and after fix for each.
• Choose the path. No major deviation and three or fewer minor ones means a pass. Otherwise it goes to a rewrite.
• Fix the flagged lines. Rewrites only the flagged lines in your voice. Facts, numbers and claims are never changed.
• Check again. Checks the new draft. It repeats up to three rounds, then hands back what is left for a person.
• Track repeat slips. Counts each kind of slip across drafts and suggests a guide rule when one appears three times.

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 brand-voice-reviewer 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/brand-voice-reviewer/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

• The draft, and where it will be used
• Your brand file, with voice, claims and what you do not say
• Your voice guide, if you have one (optional)
• Proof for any claims in the draft (optional)

Helpful context (optional)

• Your five best past pieces of copy as examples
• A list of claims you may and may not make

Tools and access

• Claude Code: It can keep the review folder, read the slip count and check every new draft the same way.
• Your writing tools: Paste the draft from your email tool, page editor or ad manager, and say where it will run.

Functions and deliverables

• Brand voice consistency reviewer: Check drafts against approved voice rules, fix only the flagged wording and track repeat slips, stopping after three rounds.
  • A pass or not-passed result, and how many rounds it took
  • The final draft with changed lines marked, and the slip each fixed
  • Any flag left for a person, including claim and legal flags
  • A count of repeat slips across drafts
  • A suggested guide rule when a slip repeats three times
• Voice and tone guide writer: Share brand positioning, audience and writing samples. Get voice traits, tone by situation, word rules and paired examples.
  • Three to five voice traits with clear limits
  • A tone guide by situation
  • Words and phrases to use and avoid
  • Side-by-side before and after examples
  Source: RampStack.
• Draft brand voice checker: Share a draft and voice guide. Get ranked findings and before-and-after edits for top issues.
  • Issues ranked High, Medium or Low
  • The reason each line was flagged
  • A before and after fix for the top issues
  • A separate list of legal and compliance flags
  • A short overall verdict
  Source: Anthropic.
• Brand voice rewriter: Give it a draft or topic and your voice guide. Get emails, posts or pitches in that voice, with notes on key choices.
  • Content written in your brand voice
  • Tone adjusted to the format
  • Notes on each brand choice
  • A check against your guidelines
  Source: Anthropic.
• 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

Tasks you can use it for

• Several people or tools write your copy and it does not always sound like you.
• You want every ad, email or page checked before it ships, the same way each time.
• The same voice mistakes keep showing up and you want to fix the cause.
• A freelancer or a tool sends you copy and you need a repeatable brand voice check before you approve it.

Limits to check before starting

• You have no brand file or voice yet. Build one first with the Brand profile builder or the Brand voice one-pager writer.
• You want to check one draft once and read the findings yourself. Use the Draft brand voice checker.
• You want a quick polish on a single ad without saving anything. Use the Brand voice editor.
• You want to strip stock AI wording rather than match a voice. Use the AI-style wording editor.
• The draft is a short internal note that no customer will see. It is more checking than it needs.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to review a draft.
• Give it the draft and your brand file. The first time, give it your voice guide, or let it build one and approve it.
• Read the final draft and the open flags. Fix what is left yourself.
• Say yes to any guide rule you want added.
• Run it on every draft. It keeps the slip count in a review folder, which needs Claude Code or another AI that can save files. In a plain chat, paste the slip list back in next time.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/brand-voice-reviewer 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.