<!-- REASONING (not shown to user) -->
1.  **Analyze the Request:**
    *   Input: Unstructured text.
    *   Output: Valid JSON matching a specific schema.
    *   Schema:
        *   `people`: Array of objects with `name` (str), `role` (str), `email` (str|null), `phone` (str|null), `mentioned_projects` (array of str).
        *   `meetings`: Array of objects with `title` (str), `datetime_iso` (str), `attendees` (array of str).
    *   Constraint: Return ONLY valid JSON, no markdown wrapping.

2.  **Analyze the Text:**
    *   "Hi team, Karen (CTO, karen@acme.io) wants to sync on Project Aurora and the Q3 migration next Tuesday at 2:30pm PT."
        *   Person: Karen, Role: CTO, Email: karen@acme.io.
        *   Meeting: Sync on Project Aurora and Q3 migration. Date/Time: Next Tuesday at 2:30pm PT.
        *   Date calculation: Today is 2025-04-21 (Monday). Next Tuesday is 2025-04-29. Time: 2:30pm PT. PT is UTC-7 (PDT) or UTC-8 (PST). Let's use UTC-7 for April (PDT). 14:30 PDT = 21:30 UTC. ISO format: 2025-04-29T21:30:00Z.
        *   Attendees: Karen, Dan Pham, Priya.
    *   "Please include Dan Pham (eng lead, dan@acme.io, 415-555-0198) and Priya from product (priya.n@acme.io)."
        *   Person: Dan Pham, Role: eng lead, Email: dan@acme.io, Phone: 415-555-0198.
        *   Person: Priya, Role: product, Email: priya.n@acme.io.
    *   "We'll also chat about Project Lumen with Karen."
        *   Project: Project Lumen (mentioned for Karen).
    *   "Separately, Friday 10am PST is the all-hands that Dan is running."
        *   Meeting: All-hands. Date/Time: Friday 10am PST.
        *   Date calculation: Today is 2025-04-21 (Monday). Friday is 2025-04-25. Time: 10am PST. PST is UTC-8. 10:00 PST = 18:00 UTC. ISO format: 2025-04-25T18:00:00Z.
        *   Attendees: Dan (running it, so he's an attendee).

3.  **Map to Schema:**

    *   **People:**
        *   Karen: name="Karen", role="CTO", email="karen@acme.io", phone=null, mentioned_projects=["Project Aurora", "Q3 migration", "Project Lumen"]
        *   Dan Pham: name="Dan Pham", role="eng lead", email="dan@acme.io", phone="415-555-0198", mentioned_projects=["Project Aurora", "Q3 migration"]
        *   Priya: name="Priya", role="product", email="priya.n@acme.io", phone=null, mentioned_projects=["Project Aurora", "Q3 migration"]

    *   **Meetings:**
        *   Meeting 1: title="Sync on Project Aurora and the Q3 migration", datetime_iso="2025-04-29T21:30:00Z", attendees=["Karen", "Dan Pham", "Priya"]
        *   Meeting 2: title="all-hands", datetime_iso="2025-04-25T18:00:00Z", attendees=["Dan"]

4.  **Refine Data Extraction & Formatting:**
    *   *Date/Time Check:*
        *   Today: 2025-04-21 (Monday)
        *   Next Tuesday: 2025-04-29. 2:30pm PT. April is in PDT (UTC-7). 14:30 + 7 = 21:30 UTC. -> `2025-04-29T21:30:00Z`
        *   Friday: 2025-04-25. 10am PST. April is in PDT (UTC-7). Wait, is it PST or PDT? The text says "PST". Even if it's technically PDT in April, I should convert based on the text's "PST" (UTC-8) or assume standard time conversion. Let's stick to the text's timezone label: PST = UTC-8. 10:00 + 8 = 18:00 UTC. -> `2025-04-25T18:00:00Z`.
    *   *Project Mapping:*
        *   "sync on Project Aurora and the Q3 migration" -> Projects: "Project Aurora", "Q3 migration".
        *   "chat about Project Lumen with Karen" -> Project: "Project Lumen".
        *   Dan and Priya are included in the sync, so they are mentioned in the context of "Project Aurora" and "Q3 migration".
    *   *Attendees Mapping:*
        *   Meeting 1: Karen (wants to sync), Dan Pham (include), Priya (include).
        *   Meeting 2: Dan (running).

5.  **Construct JSON:**
    ```json
    {
      "people": [
        {
          "name": "Karen",
          "role": "CTO",
          "email": "karen@acme.io",
          "phone": null,
          "mentioned_projects": [
            "Project Aurora",
            "Q3 migration",
            "Project Lumen"
          ]
        },
        {
          "name": "Dan Pham",
          "role": "eng lead",
          "email": "dan@acme.io",
          "phone": "415-555-0198",
          "mentioned_projects": [
            "Project Aurora",
            "Q3 migration"
          ]
        },
        {
          "name": "Priya",
          "role": "product",
          "email": "priya.n@acme.io",
          "phone": null,
          "mentioned_projects": [
            "Project Aurora",
            "Q3 migration"
          ]
        }
      ],
      "meetings": [
        {
          "title": "Sync on Project Aurora and the Q3 migration",
          "datetime_iso": "2025-04-29T21:30:00Z",
          "attendees": [
            "Karen",
            "Dan Pham",
            "Priya"
          ]
        },
        {
          "title": "all-hands",
          "datetime_iso": "2025-04-25T18:00:00Z",
          "attendees": [
            "Dan"
          ]
        }
      ]
    }
    ```

6.  **Final Review against Schema:**
    *   `people` array of objects? Yes.
    *   `name` (str)? Yes.
    *   `role` (str)? Yes.
    *   `email` (str|null)? Yes.
    *   `phone` (str|null)? Yes.
    *   `mentioned_projects` (array of str)? Yes.
    *   `meetings` array of objects? Yes.
    *   `title` (str)? Yes.
    *   `datetime_iso` (str)? Yes.
    *   `attendees` (array of str)? Yes.
    *   No markdown wrapping? Yes.

    Let's double check the date/time logic.
    Today: 2025-04-21 (Monday)
    Next Tuesday: 2025-04-29. 2:30pm PT. PT usually means Pacific Time. In April, it's PDT (UTC-7). 14:30 + 7 = 21:30. `2025-04-29T21:30:00Z`.
    Friday: 2025-04-25. 10am PST. PST is UTC-8. 10:00 + 8 = 18:00. `2025-04-25T18:00:00Z`.
    Looks solid.

    One minor point: "Priya from product" -> role is "product".
    "Dan Pham (eng lead...)" -> role is "eng lead".
    "Karen (CTO...)" -> role is "CTO".
    "Dan is running" -> attendee is "Dan".

    Everything looks correct. Proceed to output.

<!-- ANSWER -->
{
  "people": [
    {
      "name": "Karen",
      "role": "CTO",
      "email": "karen@acme.io",
      "phone": null,
      "mentioned_projects": [
        "Project Aurora",
        "Q3 migration",
        "Project Lumen"
      ]
    },
    {
      "name": "Dan Pham",
      "role": "eng lead",
      "email": "dan@acme.io",
      "phone": "415-555-0198",
      "mentioned_projects": [
        "Project Aurora",
        "Q3 migration"
      ]
    },
    {
      "name": "Priya",
      "role": "product",
      "email": "priya.n@acme.io",
      "phone": null,
      "mentioned_projects": [
        "Project Aurora",
        "Q3 migration"
      ]
    }
  ],
  "meetings": [
    {
      "title": "Sync on Project Aurora and the Q3 migration",
      "datetime_iso": "2025-04-29T21:30:00Z",
      "attendees": [
        "Karen",
        "Dan Pham",
        "Priya"
      ]
    },
    {
      "title": "all-hands",
      "datetime_iso": "2025-04-25T18:00:00Z",
      "attendees": [
        "Dan"
      ]
    }
  ]
}