Back to Prompt Library
implementation
Build the application
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build an Accessible Rural Pension Eligibility and Grievance Navigator
Format
Code-aware
Lines
87
Sections
11
Linked challenge
Build an Accessible Rural Pension Eligibility and Grievance Navigator
Prompt source
Original prompt text with formatting preserved for inspection.
87 lines
11 sections
No variables
1 code block
## Build
Evaluate senior citizen demographic attributes against mock regional social pension schemes using Bhashini translation concepts. Formulate plain-language eligibility summaries and structured grievance filings for delayed or blocked pension disbursements.
## User
Village digital kiosk operator
## Workflow
1. Ingest citizen inquiry notes regarding missed pension disbursements and record claimant age, domicile, and category.
2. Evaluate applicant details against mock old-age and widow pension entitlement policies.
3. Identify specific administrative causes of disbursement stoppages such as annual life certificate non-submission.
4. Generate a structured grievance petition dossier and translated citizen guidance brief with next steps.
## Interface
Kiosk touch interface showing eligibility scorecard, cause of benefit pause, and printable grievance letter.
## Data
Construct synthetic pension disbursement logs and scheme qualification matrices for simulated beneficiaries.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Implements Bhashini API conventions for multilingual intake and translated official communication generation.
## Tools
ollama, pydantic, sqlite3.
Ollama runs localized instruction models locally on low-cost edge kiosk hardware without constant internet connectivity.
Local quantized Llama or Mistral model running via Ollama on edge kiosk hardware.
## 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
- Accurately maps applicant age and domicile against mock regional pension thresholds.
- Pinpoints procedural stoppage triggers such as missing biometric life certificates or unlinked accounts.
- Constructs a formal administrative grievance filing formatted with structured complaint categories.
## Starter Examples
```json
[
{
"input": {
"beneficiary": {
"id": "pen_8812",
"age": 68,
"domicile_state": "Rajasthan",
"last_disbursement_date": "2024-10-01",
"life_certificate_verified": false,
"preferred_lang": "hi"
},
"scheme_criteria": {
"min_age": 60,
"annual_life_cert_required": true,
"cert_due_month": "November"
}
},
"expected_output": {
"eligibility": "ENTITLED_CURRENTLY_STALLED",
"stoppage_reason": "Annual life certificate verification overdue since November 2024.",
"corrective_actions": [
"Submit digital life certificate (Jeevan Pramaan) at nearest kiosk or post office",
"Submit proof of submission to block development office"
],
"grievance_category": "DISBURSEMENT_HOLD_LIFE_CERTIFICATE"
}
},
{
"input": {
"beneficiary": {
"id": "pen_9941",
"age": 52,
"domicile_state": "Rajasthan",
"last_disbursement_date": null,
"life_certificate_verified": true,
"preferred_lang": "hi"
},
"scheme_criteria": {
"min_age": 60,
"annual_life_cert_required": true,
"cert_due_month": "November"
}
},
"expected_output": {
"eligibility": "INELIGIBLE_AGE",
"stoppage_reason": "Applicant age 52 is below the minimum qualifying age of 60 years.",
"corrective_actions": [
"Verify birth certificate or official school records for age proof correction",
"Explore disability or widow pension schemes if applicable"
],
"grievance_category": "INITIAL_APPLICATION_REJECTION"
}
}
]
```
## Safety
Demonstration tool using mock policy parameters; does not access official government databases or Aadhaar services.
Use mock external writes. Require human review before any real deployment.Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.