{
  "id": "uc_2026_000076",
  "slug": "numan-fin-ai-agent",
  "title": "How does Numan use an AI agent for patient support?",
  "answer": "Numan, a UK digital health company, uses Fin for patient support. Its team first manually reviewed 100% of Fin interactions, then moved to a 5% monthly audit, while maintaining a 90% CSAT, per Intercom.",
  "industry": "healthcare-providers",
  "sub_industry": "Digital health (UK)",
  "roles": [
    "customer-support"
  ],
  "function": "support",
  "tasks": [
    "patient-support",
    "order-questions"
  ],
  "agent_pattern": "autonomous-agent",
  "autonomy_level": 3,
  "tools": [
    {
      "name": "Fin AI Agent",
      "vendor": "Intercom",
      "url": null,
      "affiliate": false
    }
  ],
  "deployment_status": "production",
  "organization": {
    "name": "Numan",
    "type": "digital health company",
    "named": true
  },
  "outcomes": [
    {
      "metric": "CSAT",
      "value": "90%",
      "source_ref": 1,
      "self_reported": true
    },
    {
      "metric": "quality assurance",
      "value": "100% manual review at launch, then 5% monthly audit",
      "source_ref": 1,
      "self_reported": true
    }
  ],
  "sources": [
    {
      "url": "https://fin.ai/customers/numan",
      "publisher": "Intercom (Fin)",
      "title": "Numan and Fin",
      "published": null,
      "type": "vendor-customer-story",
      "quote": "The team began by manually reviewing 100% of Fin interactions to ensure quality, accuracy, and safety.",
      "independent": false,
      "accessed": "2026-10-17",
      "ref": 1
    }
  ],
  "how_it_works": [
    "Fin answers patient support questions.",
    "Every interaction reviewed manually at first; later a 5% monthly audit."
  ],
  "risks_compliance": [
    "Incorrect answers to customers; human review and escalation paths needed",
    "Vendor-published results; not independently audited",
    "Health information; clinical questions must go to clinicians"
  ],
  "medtech_relevance": null,
  "notes": [],
  "models": [],
  "integrations": [],
  "related": [],
  "first_seen": "2026-10-17",
  "last_verified": "2026-10-17",
  "sponsored": false,
  "license": "CC BY 4.0 (summary text); quotes and sources belong to their owners",
  "evidence_grade": "B",
  "grade_rationale": "Named organization with a quantified outcome from the vendor or the organization itself (self-reported).",
  "verification": {
    "checked": "2026-10-17",
    "checker": "pipeline.verify (quote match + outcome-number match)",
    "methods": [
      "auto:fetch"
    ],
    "quotes_matched": 1,
    "quotes_total": 1,
    "claims_matched": 2,
    "claims_total": 2,
    "passed": true
  },
  "url": "https://agentcasefile.com/cases/numan-fin-ai-agent/",
  "industry_label": "Hospitals & Health Systems",
  "role_labels": [
    "Customer Support"
  ],
  "vertical": "healthcare"
}