Build an Assisted Public Healthcare Scheme Navigator for Asha Workers — implementation

## Build
Screen rural household demographic and clinical milestone profiles against mock national health scheme entitlement rules. Synthesize localized plain-language eligibility explanations and required documentation checklists in regional languages.

## User
Accredited Social Health Activist (ASHA) facilitator

## Workflow
1. Ingest family household survey records containing maternal status, child immunization milestones, and income tier.
2. Screen profiles against mock Ayushman and maternal assistance scheme qualification rubrics.
3. Identify unfulfilled prerequisite milestones such as missing institutional checkups or vaccination stages.
4. Generate a localized counseling checklist with explicit next steps for the household in regional dialects.

## Interface
Tablet-friendly mobile web interface presenting household eligibility status, missed milestones, and action items.

## Data
Create synthetic de-identified maternal and infant health survey cards with mock scheme entitlement tables.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Leverages Bhashini Indic translation pipeline standards to formulate multilingual counseling outputs for health workers.

## Tools
semantic-kernel, pydantic, pytest.
Semantic Kernel orchestrates procedural scheme validation skills and vernacular explanation plugins smoothly.
Hosted or local model supporting Indian languages with consistent factual adherence to policy rules.

## 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
- Evaluates infant vaccination completion milestones accurately against synthetic scheme guidelines.
- Flags specific missing prerequisites without producing false eligibility guarantees.
- Translates counseling action items into selected regional language (e.g., Hindi, Bengali) with vernacular phrasing.

## Starter Examples
```json
[
  {
    "input": {
      "household_profile": {
        "mother_age": 24,
        "pregnancy_trimester": 3,
        "institutional_visits_completed": 3,
        "income_category": "bpl",
        "preferred_lang": "hi"
      },
      "scheme_id": "matru_vandana_mock"
    },
    "expected_output": {
      "eligibility": "CONDITIONALLY_ELIGIBLE",
      "qualified_installment": "First and Second Installments",
      "pending_milestones": [
        "Minimum 4 prenatal checkups required before institutional delivery"
      ],
      "action_checklist_hi": [
        "चौथी प्रसव पूर्व जांच (ANC) स्वास्थ्य केंद्र पर पूरी करें",
        "मातृ एवं शिशु सुरक्षा कार्ड (MCP Card) जमा करें"
      ]
    }
  },
  {
    "input": {
      "household_profile": {
        "mother_age": 28,
        "pregnancy_trimester": 1,
        "institutional_visits_completed": 0,
        "income_category": "apl_above_threshold",
        "preferred_lang": "hi"
      },
      "scheme_id": "matru_vandana_mock"
    },
    "expected_output": {
      "eligibility": "INELIGIBLE",
      "qualified_installment": "None",
      "pending_milestones": [
        "Income exceeds BPL threshold criteria for targeted grant assistance"
      ],
      "action_checklist_hi": [
        "नियमित स्वास्थ्य जांच के लिए निकटतम प्राथमिक स्वास्थ्य केंद्र से संपर्क करें"
      ]
    }
  }
]
```

## Safety
Uses simulated health guidance only; clearly marked as informational guidance for training without clinical diagnoses.
Use mock external writes. Require human review before any real deployment.