Hire an AI product feedback analyst

Everything it can hand back

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

• A cleaned count of items, with duplicates removed and the sources named
• Themes ranked by how many people raised them, each with 2 or 3 real quotes
• A short list of rare but serious items that a count would hide
• Feature requests scored by reach, impact, confidence and effort, if you ask
• Product fixes, support actions and questions to ask users next

How it does the job well

• Never invent figures such as "90% accuracy", NPS lifts, churn forecasts or ROI. Use counts from the data.
• You cannot pull from review sites, help desks or social accounts, and you cannot monitor in real time. Say so if asked.
• Feedback may contain names, emails or order numbers. Do not repeat them. Use labels.
• Do not draw cause from a count. "Mentioned by 12 users" is not "caused churn".
• You cannot remember between chats. Tell the user to save the report and paste it back with new feedback next time.
• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: Your app store reviews, support tickets and survey answers all point somewhere, and you need to see where.

• Feedback set. How many items remain after cleaning, the sources, the period and any gaps.
• Themes. Themes ranked by count, with quotes taken from your text and why each matters.
• Rare but serious. Low-volume items that still need attention, such as billing errors or safety worries.
• Priorities. Feature requests scored by reach, impact, confidence and effort, when you ask for it.
• Recommendations. Product fixes, support actions and questions to ask users next.
• Open checks. Where one source or user type may skew the result, and what to confirm.

How the work is checked

• Every requirement can be tested.
• Assumptions and risks are listed with how each will be checked.
• Dependencies and owners are named.
• 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 Sean Ellis would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set the question. It confirms the decision and asks once for sources, dates and user types that are missing.
• Clean the pile. It removes duplicates, tags each item by source and user, and reports the final count.
• Tag the themes. It groups items into themes and flags items that fit none, so nothing is forced into a theme.
• Count and quote. It counts each theme by items and by source, and picks quotes that appear in your text.
• Check for bias. It notes where one source or one loud user is skewing the count, and keeps rare serious items.
• Rank and recommend. It scores requests if asked, then lists fixes, support actions and the next questions.

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 product-feedback-synthesizer 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/product-feedback-synthesizer/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 feedback, pasted as text or CSV, from reviews, tickets, surveys or interviews
• Where each piece came from, such as app store, email or survey (optional but helpful)
• The decision it must help with, such as what goes on next quarter's roadmap
• Who each user is, such as free or paid, and when they wrote (optional)
• Your product and any ratings or score data you already have (optional)

Helpful context (optional)

• A date and a source on each item.
• Your ratings or NPS, if you have them.

Tools and access

• Claude, ChatGPT or Gemini: Pasted text or a CSV is all it needs. An AI with a large reading window handles bigger sets in one go.

Functions and deliverables

• Product feedback analyst: Turn reviews, support tickets and survey answers into ranked themes with real quotes and clear product fixes, so you know what to build next.
  • A cleaned count of items, with duplicates removed and the sources named
  • Themes ranked by how many people raised them, each with 2 or 3 real quotes
  • A short list of rare but serious items that a count would hide
  • Feature requests scored by reach, impact, confidence and effort, if you ask
  • Product fixes, support actions and questions to ask users next
  Source: Michael Sitarzewski and Agency Agents contributors.
• Customer survey feedback analyst: Turn survey comments into a customer feedback report with themes, counts, quotes and next steps. Works with Delighted, GatherUp, Gleap or Simplesat.
  • A count of feedback items and the share that is positive, neutral and negative.
  • A table of top themes with counts and example quotes.
  • A list of urgent issues and ranked feature requests.
  • Positive quotes you can share with your team.
  • Suggested product, process and help content changes.
  Source: Composio.
• Feedback theme finder: Share customer ratings and comments to get score summaries, counted themes, quotes, and recommended actions.
  • A scorecard with NPS and CSAT and how many responses sit behind each
  • Themes with counts and exact quotes
  • Detractor and promoter comments looked at separately
  • Trends against the earlier period, if you gave one
  • Actions tied to specific themes
  Source: Burhan Sebin.
• Product demand survey planner: Plan a must-have survey for your product. Get a short survey, the 40 percent test and a plan to study the users who would be very upset.
  • A short survey with one fixed key question and open follow-ups
  • How to count the 40 percent test and what it means
  • A plan to study the group who would be very disappointed
  • One change to try and a plan to run the survey again
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Sean Ellis: Plan product-value research or growth experiments using Sean Ellis’s recorded approach. Find what users would miss, choose a useful measure and test one change.
  • Your problem worked on the way Sean Ellis would: their questions, their method, their push-back
  • The answer or the work, in Sean Ellis'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 app store reviews, support tickets and survey answers all point somewhere, and you need to see where.
• You are planning what to build next and need more than the loudest request to go on.
• Ratings dropped and you need to know which complaint is behind it.
• You have a list of feature requests and no way to rank them.

Limits to check before starting

• You want the reasons people buy, in their own words, from reviews or emails: use the Customer buying reason counter.
• You want to mine social media comments: use the Social comment mining analyst.
• You want to plan interviews or usability tests before you collect feedback: use the UX Researcher agent.
• You want each month's new reviews tracked against your last list: use the Customer feedback and brand reviewer.
• You have fewer than about 10 pieces of feedback. Read them yourself.

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.

• Add the pack to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste your feedback as plain text or CSV, with its source on each line if you can. For a big set, paste it in batches and say how many items there are.
• Say the decision it should help with. Add "Do not invent quotes or counts."
• Check the count and the themes first. Ask the AI to move any item it put in the wrong theme.
• Read the quotes against your own list. Every quote must appear in what you pasted.
• Pick the top two themes. Hand them to your team with the quotes, or run the UX Researcher agent to find out why.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/product-feedback-synthesizer 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.