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 a Public Benefit Navigation Assistant for Solar Subsidy Schemes
Format
Code-aware
Lines
76
Sections
11
Linked challenge
Build a Public Benefit Navigation Assistant for Solar Subsidy Schemes
Prompt source
Original prompt text with formatting preserved for inspection.
76 lines
11 sections
No variables
1 code block
## Build
Parse applicant household attributes and regional eligibility criteria to evaluate solar subsidy entitlement tiers. Generate itemized qualification rationales and application checklists for municipal clean energy navigators.
## User
Municipal citizen assistance desk officer
## Workflow
1. Ingest applicant household utility metrics, property ownership data, and regional solar policy rules.
2. Evaluate sanctioned load limits, roof area availability, and income slabs against mock state eligibility criteria.
3. Compute estimated capital subsidies and simulate net-metering tariff bands without triggering financial disbursals.
4. Export an explainable eligibility dossier with itemized documentary checklists for human caseworkers.
## Interface
Browser-based intake console with eligibility parameter toggles and downloadable caseworker review summaries.
## Data
Curate synthetic policy schemas and household profiles in local JSON files modeling state rooftop solar criteria.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Beckn protocol specifications](https://raw.githubusercontent.com/beckn/protocol-specifications/master/README.md)
Applies Beckn context and message envelope conventions from Core 1.0.0 to structure transaction requests.
## Tools
pydantic-ai, fastapi, pytest.
Enforces type validation on applicant household metrics and eligibility criteria payloads.
Local or hosted LLM with structured output support via OpenAI-compatible endpoints.
## 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
- Rejects input payloads lacking sanctioned grid load or roof area parameters.
- Correctly computes subsidy bracket based on normalized property and capacity thresholds.
- Generates caseworker review dossiers without executing actual financial or portal submissions.
## Starter Examples
```json
[
{
"input": {
"household_id": "HH-2041",
"state_code": "KA",
"sanctioned_load_kw": 4.5,
"roof_area_sqft": 450,
"annual_income_inr": 750000,
"ownership_status": "owner"
},
"expected_output": {
"eligible": true,
"recommended_capacity_kw": 3,
"subsidy_tier": "Tier_1_Central_State",
"estimated_subsidy_inr": 78000,
"caseworker_checklist": [
"Electricity Bill",
"Roof Ownership Proof",
"Vendor Quotation"
]
}
},
{
"input": {
"household_id": "HH-9022",
"state_code": "KA",
"sanctioned_load_kw": 1,
"roof_area_sqft": 80,
"annual_income_inr": 300000,
"ownership_status": "tenant"
},
"expected_output": {
"eligible": false,
"recommended_capacity_kw": 0,
"subsidy_tier": "None",
"estimated_subsidy_inr": 0,
"caseworker_checklist": [
"Landlord Consent Letter",
"Minimum 100 sqft Roof Area Required"
]
}
}
]
```
## Safety
Ensures purely informational subsidy calculations without executing official scheme applications or transferring funds.
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.