Skip to main content
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 Assisted Vernacular Trade License Prep and Validation Assistant

Format
Code-aware
Lines
70
Sections
11
Linked challenge
Build an Assisted Vernacular Trade License Prep and Validation Assistant

Prompt source

Original prompt text with formatting preserved for inspection.

70 lines
11 sections
No variables
1 code block
## Build
Guide rural small business owners through municipal trade certificate requirements in regional languages. Verify document attributes and assemble standardized application manifests.

## User
Village digital service kiosk operator

## Workflow
1. Collect enterprise applicant details through conversational prompts in regional Indian dialects.
2. Translate citizen responses using mock Bhashini NMT services into official municipal forms.
3. Extract mandatory registration fields including trade class, shop premises area, and power usage.
4. Generate a structured verification dossier and missing certificate checklist for kiosk operator review.

## Interface
Step-by-step kiosk assistant with regional voice guidance, document upload, and readiness summary.

## Data
Synthesize mock municipal trade license rules and standard business category classification schemes.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Applies Bhashini NMT task pipelines for domain-specific translation between regional dialects and English.

## Tools
anthropic-claude, pydantic, fastapi.
Provides accurate multi-lingual reasoning over complex regional regulatory requirements.
Hosted Claude API for advanced multi-lingual comprehension and document field extraction.

## 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
- Translate applicant voice responses into English municipal trade form attributes.
- Validate applicant enterprise classification against standardized commercial codes.
- Flag missing identity or property lease documents in the final submission bundle.
- Require physical kiosk operator review before generating submission manifests.

## Starter Examples
```json
[
  {
    "input": {
      "applicant_name": "Satish Kumar",
      "spoken_input": "Hamara motor rewinding ka dukan hai 150 square feet aur 5 horsepower bijli connection hai",
      "language": "hi"
    },
    "expected_output": {
      "trade_category": "ELECTRICAL_REPAIR_WORKSHOP",
      "declared_area_sqft": 150,
      "power_load_hp": 5,
      "mandatory_documents_present": false,
      "missing_docs": [
        "ELECTRICITY_BILL",
        "RENT_AGREEMENT"
      ]
    }
  },
  {
    "input": {
      "applicant_name": "Lakshmi Amma",
      "spoken_input": "Chinna tea stall nadathuren rent agreement irukku",
      "language": "ta"
    },
    "expected_output": {
      "trade_category": "TEA_STALL_EATERY",
      "declared_area_sqft": null,
      "power_load_hp": 0,
      "mandatory_documents_present": false,
      "missing_docs": [
        "PREMISES_AREA_PROOF",
        "FSSAI_REGISTRATION"
      ]
    }
  }
]
```

## Safety
Assists documentation prep only; does not claim direct municipal filing or grant regulatory trade licenses.
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.