Hire an AI customer complaint design researcher

Everything it can hand back

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

• A theme map with each theme tied to the task users were doing, with sources, dates and versions
• Where complaints disagree, kept side by side
• Design questions ranked by how many complaints support them, how badly they block the task and how well the evidence backs the explanation
• For each top question, an explanation to test and a small design option to try
• A small research plan with the method, who to ask and what answer would change your decision

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Saying how many of all users have a problem.
• Ranking themes by count when the sample is under 10.
• Dropping a complaint that disagrees with the main theme.
• Repeating names, emails or other personal details from the complaints.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.

What a good result looks like

An example, not your task: Support says the same thing keeps coming up, but nobody can say what to fix first.

• Theme map. Themes grouped by user task, with quotes, sources, dates, versions and any disagreement.
• Ranked design questions. Each question with its evidence, a testable explanation and a small design option.
• Research plan. For each top question, the method, who to ask and the answer that would change your decision.
• Sample note. How many complaints were read and what the counts do not tell you.
• Hand-back summary. Files saved, MISSING lines, checks not run and one next step.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• 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 Susan Kare would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Feedback theme finder. Groups the complaints by the task the user was doing. Keeps each source, date and version, and keeps people who disagree. Counts only the sample you gave it. Hands step 2 the theme map with quotes. Check before moving on, every theme shows at least one quote and its source.
• Hypothesis-first design planner. Turns the strongest themes into explanations you can test and small design options for each. Ranks them by number of complaints, how badly they block the task and the strength of the evidence. Hands step 3 the ranked questions. Check before moving on, every question traces to quotes.
• Interview and research planner. Picks research tasks that tell the explanations apart before a redesign is approved. Gives the method, who to ask, the questions and what answer would change your decision. Hands back the research plan. Check before moving on, each task can tell two explanations apart.

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 turn-user-complaints-into-design-questions 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/turn-user-complaints-into-design-questions/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

• Support tickets, reviews or survey comments, with the date and product version if you know them
• The screens or flows the complaints are about
• Who the users are, such as new customers or admins (optional)
• What you have already tried or changed (optional)
• Any research you have done before (optional)

Helpful context (optional)

• Approved examples of a good result.
• A named reviewer and their acceptance rules.

Tools and access

• A capable chat AI with file support: Read the full pack and supplied sources; connected actions need the corresponding authorized tools.
• Any good chat AI: A chat AI can read a CSV and group comments into themes.
• Google Sheets or Excel: Use them to clean and export your survey results first.

Functions and deliverables

• Customer complaint design researcher: Share dated complaints, product versions and relevant screens. Get themes, ranked design questions and a small research plan to test possible causes.
  • A theme map with each theme tied to the task users were doing, with sources, dates and versions
  • Where complaints disagree, kept side by side
  • Design questions ranked by how many complaints support them, how badly they block the task and how well the evidence backs the explanation
  • For each top question, an explanation to test and a small design option to try
  • A small research plan with the method, who to ask and what answer would change your decision
• 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.
• Lean UX experiment planner: Describe a design problem. Get assumptions to check and small tests to plan before you build.
  • A ranked assumptions list
  • Hypotheses with success rules
  • Lightweight experiment plans
  • A score of your current process with fixes
  Source: Wondel.ai.
• Interview and research planner: Share a decision, research question and who you can reach. Get a study plan and interview guide, not findings before research.
  • A sharper version of your research questions
  • A recruiting plan with numbers
  • An interview guide
  • Steps for turning notes into findings
  • A list of product decisions the findings should inform
  Source: RampStack.
• 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
• Susan Kare: Plan icons or small screen details using Susan Kare’s recorded approach. Find clear metaphors, sketch options and test what people understand at real sizes.
  • Your problem worked on the way Susan Kare would: their questions, their method, their push-back
  • The answer or the work, in Susan Kare'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

• Support says the same thing keeps coming up, but nobody can say what to fix first.
• A new release brought a spike in tickets and you need to know which screens to look at.
• A stakeholder wants a redesign and you want the questions to answer first.
• You collected reviews or survey comments and need to turn them into a short research plan.

Limits to check before starting

• You have one ticket or one bug report. Send it to the team that owns the bug.
• You only want the complaints grouped. Use the Feedback theme finder on its own.
• You want to find the cause of one mistake users keep making. Use the Product ease of use checker.
• You already know the problem and want fixes. Use the Design revision usability test planner workflow.

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 workflow pack and add it to your AI, such as Claude, ChatGPT or Gemini.
• Remove names, emails and account numbers from the complaints, or paste only the text you may use. Add dates and versions.
• After step 1, read the themes against the quotes. Move any complaint that landed in the wrong theme.
• After step 2, read the ranking. Counts describe your sample only. Ask what would make you wrong.
• Run the research plan from step 3 before you approve a redesign.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-user-complaints-into-design-questions 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.