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 Public Housing Scheme Eligibility Explainer
Format
Code-aware
Lines
71
Sections
11
Linked challenge
Build an Accessible Public Housing Scheme Eligibility Explainer
Prompt source
Original prompt text with formatting preserved for inspection.
71 lines
11 sections
No variables
1 code block
## Build
Evaluate urban migrant household survey records against mock affordable rental housing scheme criteria. Generate localized plain-language eligibility explanations and required documentation guides for community social workers.
## User
Urban housing aid caseworker
## Workflow
1. Ingest household income brackets, family size, disability status, and current tenancy records.
2. Evaluate criteria against mock municipal affordable rental housing policy tiers.
3. Identify specific disqualifying criteria or priority category reservations with explicit policy citations.
4. Synthesize a clear applicant explanation memo in localized language formatting for caseworker visits.
## Interface
Caseworker dashboard showing household income calculators, scheme matching criteria, and printable guides.
## Data
Create synthetic household survey profiles and mock municipal housing policy rulebooks in local JSON files.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Adopts Bhashini language tag taxonomy and translation framing to structure multilingual caseworker memos.
## Tools
dspy, fastapi, jinja2.
Optimizes caseworker explanatory tone and factual adherence to municipal housing scheme rules.
Hosted or local instruction model capable of structured rationale generation and rule adherence.
## 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
- Classifies applicant households into correct Economically Weaker Section or Lower Income Group categories.
- Highlights disability or single-parent priority weighting correctly.
- Generates casework memos without connecting to actual municipal registration backends.
## Starter Examples
```json
[
{
"input": {
"case_id": "HSG-102",
"annual_income_inr": 240000,
"family_size": 4,
"has_disability": true,
"owns_pucca_house": false
},
"expected_output": {
"category": "EWS",
"eligible": true,
"priority_status": "High_Priority_Disability_Quota",
"actionable_steps": [
"Submit Disability Certificate",
"Provide Rent Agreement",
"Obtain Income Verification"
]
}
},
{
"input": {
"case_id": "HSG-103",
"annual_income_inr": 900000,
"family_size": 3,
"has_disability": false,
"owns_pucca_house": true
},
"expected_output": {
"category": "MIG",
"eligible": false,
"priority_status": "None",
"actionable_steps": [
"Ineligible: Household income exceeds EWS/LIG threshold and already owns pucca dwelling."
]
}
}
]
```
## Safety
Maintains strictly advisory casework explanations without creating binding legal housing entitlements.
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.