{
 "license": "CC-BY-4.0",
 "attribution": "Fide AI, Agentic Cyber Explorer",
 "url": "https://agentic-cyber-explorer.pages.dev/events/microsoft-security-copilot-rct-2023/",
 "asOf": "2026-09-26",
 "id": "microsoft-security-copilot-rct-2023",
 "date": "2023-12-05",
 "datePrecision": "day",
 "title": "Microsoft randomized controlled trial measures Security Copilot effect on analyst speed and accuracy",
 "lane": "defense",
 "kind": "paper",
 "summary": "Microsoft economists ran randomized controlled trials in which novices and security professionals completed incident summarization, script analysis, incident report and guided response tasks in a Defender XDR test environment, with half given Security Copilot. The January 2024 revision reports that novices with Copilot answered 35% more questions correctly and professionals were 7% more accurate, with both groups completing tasks faster.",
 "whyItMatters": "It is one of the few controlled experiments measuring whether an LLM assistant changes SOC analyst performance, rather than relying on vendor anecdotes.",
 "actors": [
  "microsoft"
 ],
 "topics": [
  "soc-automation"
 ],
 "atlas": [
  "human-approver"
 ],
 "artifacts": [
  "security-copilot"
 ],
 "sources": [
  {
   "url": "https://www.benedelman.org/randomized-controlled-trial-for-microsoft-security-copilot/",
   "publisher": "Ben Edelman",
   "title": "Randomized Controlled Trials for Microsoft Copilot for Security",
   "date": "2023-12-05",
   "type": "primary",
   "accessed": "2026-09-25"
  },
  {
   "url": "https://cdn-dynmedia-1.microsoft.com/is/content/microsoftcorp/microsoft/final/en-us/microsoft-brand/documents/microsoft_security_copilot_economic_report_v4_accessible.pdf",
   "publisher": "Microsoft",
   "title": "Randomized controlled trial for Microsoft Security Copilot (whitepaper)",
   "date": "2024-01",
   "type": "primary",
   "accessed": "2026-09-25"
  }
 ],
 "keyFacts": [
  {
   "fact": "Novice study: 149 subjects (tested October 2023); Copilot subjects got 35% more multiple-choice questions correct and were 26% faster holding accuracy constant.",
   "locator": "Whitepaper, 'Findings - novices'"
  },
  {
   "fact": "Professional study: 147 security professionals (tested December 2023 to January 2024); Copilot users were 7% more accurate on multiple-choice tasks and finished overall tasks 22% faster.",
   "locator": "Whitepaper, 'Findings - professionals'"
  },
  {
   "fact": "Authors note tasks were closely linked to Copilot's capabilities, which may overstate real-world gains.",
   "locator": "Whitepaper, novice findings discussion"
  }
 ],
 "significance": 3,
 "fideQuestions": [
  "FID-076"
 ],
 "methods": [],
 "review": "assistant-drafted",
 "addedOn": "2026-09-25"
}