Hire an AI customer feedback and brand reviewer

Everything it can hand back

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

• A count of reasons that are known, growing and new, in customers' exact words
• Brand file changes to approve, each with source IDs and the number of people
• New doubts with the proof that settles each one
• Wrong-fit buyer groups with a not-for line, when low reviews rose
• A watch list to count again next month

How it does the job well

• Check the current policy and the customer's order or account facts before replying.
• Answer the actual question in the first two lines, then explain.
• Match the customer's tone. Acknowledge the problem once, without grovelling.
• Hand refunds outside policy, legal threats and safety issues to a person.

Mistakes it avoids

• Treating a loud review as a pattern. Count separate people.
• Changing the brand file because one month looked different.
• Rewriting customer words into your own. Keep them exact.
• Adding a doubt to the page when your message already answers it.
• Promising refunds, dates or fixes the policy does not allow.
• Copy-paste replies that ignore what the customer said.

What a good result looks like

An example, not your task: You have a brand file and want it to keep up with what customers say now.

• This month. Reviews read, low-star share against last month, and how many buying reasons were known, growing or new.
• Brand file changes to approve. Exact lines to add or replace, with customer words, source IDs and the number of people. Ten at most.
• New doubts. Each doubt raised by three or more people, the proof that settles it, and whether your message already answers it.
• Wrong-fit buyers. Groups who wanted a different job, the claim that drew them, and a not-for line. Or none this month.
• Watch list. Phrases and doubts seen once or twice, to count again next month.
• Files and missing. Each step's saved file, then every MISSING line in one list.

How the work is checked

• Every proposed line has customer words and source IDs behind it.
• No change rests on fewer than 3 separate people.
• A thin batch produced no brand file change.
• The brand file was not edited without a clear yes.
• 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 Clayton Christensen and Eric Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Count the batch. Counts reviews, separate people and the low-star share. A thin batch is logged but changes nothing.
• Find the buying reasons. Pulls the reasons people bought, in their own words, and marks each as known, growing or new.
• Choose the path for low reviews. If the low-star share rose or five or more low reviews came in, it checks for buyers who wanted a different job. If not, it skips this.
• Look for a new kind of buyer. Every third month, or on a big batch, it checks whether a new self-described group is showing up.
• Check new doubts. A doubt raised by at least three people is checked against your current message, with the proof that would settle it.
• Hand back changes to approve. Lists exact lines for the brand file with the words behind them. Single comments go on a watch list.

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 monthly-customer-voice-keeper 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/monthly-customer-voice-keeper/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

• This month's new reviews, tickets or survey answers, with dates and star ratings
• Your brand file, at least the buyers, claims and doubts files
• Your current page or ad headline and main claims (optional)
• Return or refund notes (optional)

Helpful context (optional)

• Support tickets and survey answers from the same month
• Return reasons from your store

Tools and access

• Claude Code: It can keep the voice folder, read last month's files and edit the brand file once you approve.
• Your review app: Export the month's reviews with dates, star ratings and the reviewer's name or ID.
• Claude: Long-context chat models can take hundreds of reviews in one chat with their source IDs. Check your plan's limit.
• Gemini: Also takes long inputs, and works inside Google Sheets if your reviews live there.
• Google Sheets: One row per quote with its source ID lets you count separate people with COUNTUNIQUE, so counts can be checked.
• Any good chat AI: Any current chat AI can tag reviews and trace them to claims. Paste the text with dates.
• Shopify admin: Its returns report gives reasons and counts to read beside the reviews.
• Any good chat AI: Reads and counts the self-descriptions in the reviews you paste.
• Google Forms: A free way to send the three-question survey and collect open answers.
• Shopify post-purchase survey apps: Ask the questions right after an order so answers keep coming. Many of these apps charge a monthly fee, so check the price. A Google Form is the free way.

Functions and deliverables

• Customer feedback and brand reviewer: Find new buyer language and doubts in customer feedback. Get sourced brand note changes to review.
  • A count of reasons that are known, growing and new, in customers' exact words
  • Brand file changes to approve, each with source IDs and the number of people
  • New doubts with the proof that settles each one
  • Wrong-fit buyer groups with a not-for line, when low reviews rose
  • A watch list to count again next month
• Customer buying reasons finder: Paste reviews or support emails to find customer buying reasons in their exact words, ranked by how many people said them, with a score out of 100.
  • A ranked map of reasons by force, each with its best exact quote, backups and how many people said it
  • The reasons customers give that your brand never says
  • A ranked list of what nearly stopped them, in customers' words
  • A "check before use" list of risky quotes, with the reason each is flagged
  • A score out of 100 for how many of its own checks the map passes, with each miss named
• Customer fit reviewer: Share poor reviews. Separate product faults from poor buyer fit and get copy that sets clearer expectations.
  • Each low review tagged: product failure, wrong job, expectation set by your page or ad, or delivery
  • The page or ad claim that drew each wrong-job group
  • Not-for lines and claim edits, with where each goes (near the buy button, in the ad, in the FAQ)
  • A short list of same-job reviews to pin, and a promise-match score out of 100
• Buyer identity segment finder: Paste reviews or survey answers. Get buyer groups from their own words, sample counts, a proposed focus and a three-question survey.
  • A list of buyer identities with counts, trend and example phrases, without names
  • A nesting map from the broad market to the specific group
  • A ranked list with a size note on each, and one pick
  • What to change for the pick in the ad, text, page and photos, plus a three-question survey
• Trust barrier and proof checker: Share your audience, message and evidence. Map stated doubts to proof and claims the facts can support.
  • A list of trust barriers
  • Proof signals matched to each barrier
  • Claim strength advice
  • Reworded lines to try
  Source: sickn33.
• 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
• Clayton Christensen: Explore why customers buy using Clayton Christensen’s recorded approach. Start with a real situation, the struggle and what the buyer used before.
  • Your problem worked on the way Clayton Christensen would: their questions, their method, their push-back
  • The answer or the work, in Clayton Christensen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Eric Ries: Turn a product plan into testable guesses using Eric Ries’s public approach. Start with the riskiest assumption and measure what customers actually do.
  • Your problem worked on the way Eric Ries would: their questions, their method, their push-back
  • The answer or the work, in Eric Ries'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

• You have a brand file and want it to keep up with what customers say now.
• New reviews arrive every month and nobody has time to read them closely.
• Low reviews went up and you want to know if the product or the promise is the cause.

Limits to check before starting

• You have fewer than about 20 new reviews: let them pile up for a few months, or read them yourself and note the repeated words.
• You have no brand file yet: use the Brand profile builder first, then come back to this agent.
• You want it to reply to reviewers or change a live page: it only reads and reports, so a person has to do that.

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 run this month's review.
• Before you export reviews, remove reviewer names and contact details. Keep only an ID, the date and the star rating.
• Put your brand file and this month's new customer words in one folder, or attach them in the chat.
• The first run builds the base in a voice folder and compares nothing. The second run is the first real comparison.
• Read the change list. Approve the lines you want, and ask it to make only those in the brand file.
• Run it again next month. It reads the voice folder for last month's reasons and doubts.

Read it as data

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