Build a Yente Entity Screening Task Auditor — implementation

## Build
Audit investigative shift logs to ensure all mentioned counterparties were properly formatted as FollowTheMoney entities and screened via the yente match API. All outputs are mock reviews.

## User
Shift continuity supervisor

## Workflow
1. Ingest unstructured shift notes detailing investigative leads.
2. Extract counterparty names and map them to FollowTheMoney entity schemas.
3. Verify if the shift ledger includes a recorded yente API match operation for each entity.
4. Generate a discrepancy report highlighting entities mentioned but never screened.

## Interface
Dashboard displaying unscreened entity alerts and screening continuity metrics.

## Data
Construct local synthetic JSON files containing shift notes with entity mentions, alongside yente API request logs. Use simplified synthetic app records, not complete official schema files.
Starter examples below are synthetic. They are not downloaded records.

## Source
[OpenSanctions data toolkit](https://raw.githubusercontent.com/opensanctions/yente/main/README.md)
Applies FollowTheMoney schema standards to structure extracted entities for yente match verification.

## Tools
mastra-ai, pydantic, sqlite3.
Provides stateful agent orchestration to ingest shift notes, extract entities, and identify missing yente screening events.
Local or hosted LLM with strong logical deduction to map stated entities against yente action logs.

## Deliverables
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

## Acceptance
- Extracts all counterparty entities from unstructured shift notes.
- Maps extracted names to the FollowTheMoney schema.
- Generates an accurate discrepancy report listing entities that lack a corresponding yente screening action.

## Starter Examples
```json
[
  {
    "input": {
      "shift_id": "SHIFT-01",
      "analyst_logs": [
        {
          "time": "09:00",
          "content": "Will review alerts for Acme Corp."
        },
        {
          "time": "11:00",
          "content": "Screened Global Trade LLC via yente, cleared."
        }
      ]
    },
    "expected_output": {
      "shift_id": "SHIFT-01",
      "extracted_entities": [
        "Acme Corp",
        "Global Trade LLC"
      ],
      "screened_entities": [
        "Global Trade LLC"
      ],
      "dropped_screenings": [
        "Acme Corp"
      ]
    }
  },
  {
    "input": {
      "shift_id": "SHIFT-02",
      "analyst_logs": [
        {
          "time": "14:00",
          "content": "Need to check Oceanic Ltd against sanctions."
        },
        {
          "time": "15:30",
          "content": "yente match API returned no hits for Oceanic Ltd."
        }
      ]
    },
    "expected_output": {
      "shift_id": "SHIFT-02",
      "extracted_entities": [
        "Oceanic Ltd"
      ],
      "screened_entities": [
        "Oceanic Ltd"
      ],
      "dropped_screenings": []
    }
  }
]
```

## Safety
Does not autonomously alter alert systems; only flags potential screening gaps for human supervisor review.
Use mock external writes. Require human review before any real deployment.