{
 "schema": "aiblocks-page/1",
 "id": "agency-marketing-x-twitter-intelligence-analyst",
 "type": "agent",
 "name": "X research analyst",
 "summary": "Turn X (Twitter) posts into a sourced brief on your brand, rivals or audience, with a reusable search list and next steps.",
 "headline": "X research analyst",
 "subhead": "Paste posts, an export or links from X, and say what decision they should help with. It separates real signals from noise and shows how sure it is. You get a sourced brief, a search list you can reuse and a short monitoring plan.",
 "job": {
  "id": "research-topics",
  "name": "Research a topic properly"
 },
 "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"
  },
  {
   "type": "spreadsheet",
   "required": false,
   "label": "Spreadsheet",
   "what": "a spreadsheet with its data, formulas and charts"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  },
  {
   "type": "document",
   "required": true,
   "label": "Document",
   "what": "a finished document, such as a Word file, a PDF or a page of notes"
  }
 ],
 "you_give": [
  "The decision the research should help with, in one line, such as \"Should we answer a rival's price cut?\"",
  "Your brand name, handles and product names, and the rivals and topics to cover",
  "The posts to study, pasted with links, or an export from X or a data service",
  "The date range to cover and any words to leave out (optional)"
 ],
 "you_get": [
  "A sourced brief with the question, the scope, the key findings and the confidence for each",
  "A signal timeline of what happened and when, with a link for each entry",
  "A search table of phrases, handles and exclusions you can reuse",
  "A monitoring plan with what to watch, how often and what counts as a spike"
 ],
 "use_when": [
  "A rival just launched something and you want to know how buyers on X are reacting before you reply.",
  "Mentions of your brand jumped overnight and you need to know if it is a real problem, a support issue or a few loud accounts.",
  "You want to know what your customers complain about or ask for on X, in their own words.",
  "You need a list of search phrases and accounts to watch for your brand and category."
 ],
 "skip_when": [
  "You want to write or schedule posts. This agent does research only. Use the X post and reply writer for replies.",
  "You want to track results of paid social ads. Use the Paid social advertising strategist.",
  "You expect it to watch X live and alert you. A chat AI cannot do that without a data service and a webhook set up by you.",
  "You want to find out who is behind an account or collect personal details. It will not do that."
 ],
 "output_sample": {
  "input": [
   "The decision the research should help with",
   "Your brand names, handles, rivals and topics",
   "The posts to study, with links, or an export",
   "The date range and words to leave out (optional)"
  ],
  "prerequisites": [
   "Posts from X pasted in, an export, web search in your AI, or an X data service"
  ],
  "output": [
   {
    "name": "Brief",
    "contains": "The question, scope and numbered findings, each with a link, a confidence level and what it means."
   },
   {
    "name": "Signal timeline",
    "contains": "A table of what happened and when, with the source link and action for each signal."
   },
   {
    "name": "Search table",
    "contains": "Reusable search phrases, handles, languages, words to leave out and how often to review each."
   },
   {
    "name": "Monitoring plan",
    "contains": "What to watch, how often to check, and the spike level that should trigger a review."
   },
   {
    "name": "Recommended actions",
    "contains": "Steps sorted into now, this week and watch list."
   },
   {
    "name": "Limits and checks still needed",
    "contains": "What the posts cannot show, and what you must confirm before you act."
   }
  ]
 },
 "output_shape": "X/TWITTER INTELLIGENCE BRIEF\n\nQUESTION\n  <the decision this supports>\n\nCOLLECTION SCOPE\n  Search phrases <list> | Accounts <list> | Date range <dates> | Left out <terms> | Data source <paste, export or search> | Posts used <number>\n\nKEY FINDINGS\n  1. <finding> | Evidence <link, count> | Fact or reading <which> | Confidence <low, medium or high> | Impact <what it means for you>\n\nSIGNAL TIMELINE\n  <time in UTC> | <signal> | <source link> | <confidence> | <action>\n\nSEARCH TABLE\n  <theme> | <phrase> | <accounts> | <language> | <leave out> | <priority> | <how often to review>\n\nRECOMMENDED ACTIONS\n  Now <list> | This week <list> | Watch <list>\n\nLIMITS AND CHECKS STILL NEEDED\n  <what the posts cannot show>",
 "how_to_use": [
  "Download the pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.",
  "Tell it the decision you need to make, your brand names and handles, and the rivals or topics to cover.",
  "Paste the posts with their links and times, or attach an export. If your AI can search the web, say so. If you have an X data service such as Xquik, which is paid, say that too.",
  "Type \"Make the brief. Show the link for each finding. Say how sure you are and how many posts it rests on.\"",
  "Read the confidence lines first. Open two or three of the cited posts yourself before you act on a finding.",
  "Take the search table to your monitoring tool, or run the brief again each week with fresh posts."
 ],
 "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": "Market research report writer",
   "url": "https://useaiblocks.com/skills/market-research-report-writer",
   "why": "Market research report writer"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/marketing/marketing-x-twitter-intelligence-analyst.md",
  "licence": "MIT",
  "original_name": "X/Twitter Intelligence Analyst",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "X/Twitter Intelligence Analyst",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/marketing/marketing-x-twitter-intelligence-analyst.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-marketing-x-twitter-intelligence-analyst",
  "markdown": "https://useaiblocks.com/agents/agency-marketing-x-twitter-intelligence-analyst.md",
  "json": "https://useaiblocks.com/agents/agency-marketing-x-twitter-intelligence-analyst.json",
  "instructions": "https://useaiblocks.com/skills/agency-marketing-x-twitter-intelligence-analyst/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-marketing-x-twitter-intelligence-analyst.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-marketing-x-twitter-intelligence-analyst",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-marketing-x-twitter-intelligence-analyst",
  "mcp": "https://useaiblocks.com/mcp"
 }
}
