{
 "schema": "aiblocks-page/1",
 "id": "agency-product-feedback-synthesizer",
 "type": "agent",
 "name": "Product feedback analyst",
 "summary": "Turn reviews, support tickets and survey answers into ranked themes with real quotes and clear product fixes, so you know what to build next.",
 "headline": "Product feedback analyst",
 "subhead": "Paste feedback from reviews, tickets, surveys or interviews. The agent cleans it, groups it into themes, counts each one and picks quotes. You get a ranked list of what users want fixed, with the evidence behind each item.",
 "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": "voc_reviews",
   "required": true,
   "label": "Voc reviews",
   "what": "customer words from reviews, tickets, surveys or calls, with source and date"
  },
  {
   "type": "question",
   "required": false,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  }
 ],
 "you_give": [
  "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)"
 ],
 "you_get": [
  "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"
 ],
 "use_when": [
  "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."
 ],
 "skip_when": [
  "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."
 ],
 "output_sample": {
  "input": [
   "Your feedback, pasted as text or CSV, from reviews, tickets or surveys",
   "The decision it must help with",
   "The source of each item, and user type (optional)"
  ],
  "prerequisites": [
   "An AI that reads pasted text or a CSV file, such as Claude, ChatGPT or Gemini"
  ],
  "output": [
   {
    "name": "Feedback set",
    "contains": "How many items remain after cleaning, the sources, the period and any gaps."
   },
   {
    "name": "Themes",
    "contains": "Themes ranked by count, with quotes taken from your text and why each matters."
   },
   {
    "name": "Rare but serious",
    "contains": "Low-volume items that still need attention, such as billing errors or safety worries."
   },
   {
    "name": "Priorities",
    "contains": "Feature requests scored by reach, impact, confidence and effort, when you ask for it."
   },
   {
    "name": "Recommendations",
    "contains": "Product fixes, support actions and questions to ask users next."
   },
   {
    "name": "Open checks",
    "contains": "Where one source or user type may skew the result, and what to confirm."
   }
  ]
 },
 "output_shape": "FEEDBACK SET\n  Items <count after duplicates removed> | Sources <list> | Period <dates>\n  Gaps <missing source or user type>\n\nTHEMES (ranked)\n  <theme> | <count> of <total> | sources <list>\n  Quotes \"<quote>\" | \"<quote>\"\n  Why it matters <effect on users or business>\n\nRARE BUT SERIOUS\n  <item> | <why it counts despite low volume>\n\nPRIORITIES (if asked)\n  <request> | reach <n> | impact <n> | confidence <n> | effort <n> | score <n>\n\nRECOMMENDATIONS\n  Product <fix> | Support <action> | Ask users next <question>\n\nOPEN CHECKS\n  <bias or gap> | <what to confirm>",
 "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.",
  "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."
 ],
 "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": "Customer needs profile builder",
   "url": "https://useaiblocks.com/skills/job-based-avatar-builder",
   "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/product/product-feedback-synthesizer.md",
  "licence": "MIT",
  "original_name": "Feedback Synthesizer",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "Feedback Synthesizer",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/product/product-feedback-synthesizer.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-product-feedback-synthesizer",
  "markdown": "https://useaiblocks.com/agents/agency-product-feedback-synthesizer.md",
  "json": "https://useaiblocks.com/agents/agency-product-feedback-synthesizer.json",
  "instructions": "https://useaiblocks.com/skills/agency-product-feedback-synthesizer/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-product-feedback-synthesizer.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-product-feedback-synthesizer",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-product-feedback-synthesizer",
  "mcp": "https://useaiblocks.com/mcp"
 }
}
