{
 "schema": "aiblocks-page/1",
 "id": "agency-design-ux-researcher",
 "type": "agent",
 "name": "UX researcher agent",
 "summary": "Plan a user research study or turn your interview and test notes into findings, personas and ranked fixes for your website or app.",
 "headline": "UX researcher agent",
 "subhead": "Say what you need to learn about your users, or paste notes from interviews and tests. The agent picks the research method, writes a study plan or a usability test script, and turns notes into findings tied to evidence. You get ranked fixes.",
 "job": {
  "id": "understand-customers",
  "name": "Understand your customers"
 },
 "level": "intermediate",
 "thinking": "high",
 "tested": true,
 "updated": "2026-11-03",
 "first_published": "2026-10-26",
 "inputs": [
  {
   "type": "question",
   "required": true,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  },
  {
   "type": "source_text",
   "required": false,
   "label": "Source text",
   "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link"
  }
 ],
 "outputs": [
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  },
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  }
 ],
 "you_give": [
  "The product or page, and who uses it",
  "The one question you need answered, such as why people leave the checkout",
  "Notes from interviews or usability tests, pasted as text (optional if you are only planning)",
  "Any numbers you have, such as drop-off by step (optional)",
  "Your limits on time, people and budget (optional)"
 ],
 "you_get": [
  "A study plan with questions, method, who to recruit, how many people and a timeline",
  "A usability test script with tasks and what to watch for, if you ask for one",
  "Findings that each cite the notes behind them",
  "Personas and a path map built from your evidence, if you ask for them",
  "Fixes ranked by impact and effort, with a way to check each one worked"
 ],
 "use_when": [
  "Your checkout, sign-up or app keeps losing people and you do not know where they get stuck.",
  "You are about to redesign a page and want to test the idea with real users first.",
  "You have a folder of interview or usability test notes and no time to find the patterns.",
  "A teammate says \"users hate this\" and you need evidence before you change anything."
 ],
 "skip_when": [
  "You want to find what to ask in early customer interviews for a business idea: use the Customer discovery interview planner.",
  "You want a quick research method pick and plan, with no UX focus: use the User research planner.",
  "You want to sort a pile of reviews, tickets or survey comments into themes: use the Product feedback analyst.",
  "You need a study with real legal or medical risk, such as patient testing: use a trained researcher and an ethics review.",
  "You want to test whether a result is statistically real: use the Statistician agent."
 ],
 "output_sample": {
  "input": [
   "The product or page, and who uses it",
   "The one question you need answered",
   "Notes from interviews or tests, pasted as text (optional)",
   "Your limits on time, people and budget (optional)"
  ],
  "prerequisites": [
   "An AI that reads pasted text, such as Claude, ChatGPT or Gemini",
   "Real people to talk to, if you want to run the study"
  ],
  "output": [
   {
    "name": "Research question",
    "contains": "Your worry restated as one question, with the decision it will change."
   },
   {
    "name": "Study plan",
    "contains": "Method, who to recruit, how many, screening rules, session outline and consent steps."
   },
   {
    "name": "Evidence",
    "contains": "What each person said or did, listed before any conclusion is drawn."
   },
   {
    "name": "Findings",
    "contains": "Each finding with the people who showed it, a quote and how sure the agent is."
   },
   {
    "name": "Personas and path map",
    "contains": "Goals, pain points and steps for each user type, built only from your notes."
   },
   {
    "name": "Recommendations",
    "contains": "Fixes ranked by impact and effort, each with a way to check it worked."
   },
   {
    "name": "Open checks",
    "contains": "Gaps in the evidence and what to learn next."
   }
  ]
 },
 "output_shape": "RESEARCH QUESTION\n  <what you need to learn> | <decision it will change>\n\nSTUDY PLAN\n  Method <interviews, survey, usability test or analytics> | Why <reason>\n  Who <user type> | How many <number and why> | Screening <rules>\n  Session <length and structure> | Consent and privacy <steps>\n  Tasks <task 1> | <success looks like> | <what to watch>\n\nEVIDENCE\n  <participant> | <what they said or did>\n\nFINDINGS\n  <finding> | <people who showed it> | <quote> | <how sure>\n\nPERSONAS AND PATH MAP (if asked)\n  <name> | goals | pain points | quote from your notes\n\nRECOMMENDATIONS\n  <fix> | impact <high, medium, low> | effort <high, medium, low> | check <how to measure>\n\nOPEN CHECKS\n  <gap in the evidence> | <what to do next>",
 "how_to_use": [
  "Add the pack to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.",
  "Say whether you are planning research or analysing notes. Paste the product, the users and your one question.",
  "For analysis, paste your notes, one person per block. Say how many people you spoke to.",
  "Read the evidence list first. Remove or fix any quote or finding that does not match your notes.",
  "Run the plan or the test script with real people. You do the recruiting and the sessions, then come back with the notes.",
  "Pick the top fix, make the change and test again with a few new people."
 ],
 "checks": [
  "The result addresses your actual task and cites the evidence used.",
  "Examples, role-play experience and targets are kept separate from verified results.",
  "Claims of tests, memory, tool access or completed actions match what actually happened."
 ],
 "next": [
  {
   "name": "Interview and research planner",
   "url": "https://useaiblocks.com/skills/interview-and-research-planner",
   "why": "Understand your buyers"
  },
  {
   "name": "Customer switching journey mapper",
   "url": "https://useaiblocks.com/skills/switch-story-mapper",
   "why": "Understand your buyers"
  },
  {
   "name": "User retention reviewer",
   "url": "https://useaiblocks.com/skills/retention-problem-fixer",
   "why": "Understand your buyers"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/design/design-ux-researcher.md",
  "licence": "MIT",
  "original_name": "UX Researcher",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "UX Researcher",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/design/design-ux-researcher.md",
   "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions."
  }
 ],
 "files": [
  "LICENSE",
  "references/source-agent.md",
  "SETUP.md",
  "source.json"
 ],
 "links": {
  "page": "https://useaiblocks.com/agents/agency-design-ux-researcher",
  "markdown": "https://useaiblocks.com/agents/agency-design-ux-researcher.md",
  "json": "https://useaiblocks.com/agents/agency-design-ux-researcher.json",
  "instructions": "https://useaiblocks.com/skills/agency-design-ux-researcher/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-design-ux-researcher.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-design-ux-researcher",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-design-ux-researcher",
  "mcp": "https://useaiblocks.com/mcp"
 }
}