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 Vernacular Trade Document Preparation and Verification Assistant
Format
Code-aware
Lines
78
Sections
11
Linked challenge
Build a Vernacular Trade Document Preparation and Verification Assistant
Prompt source
Original prompt text with formatting preserved for inspection.
78 lines
11 sections
No variables
1 code block
## Build
Guide small rural traders through local-language document prep for commercial trade permits. Validate uploaded certificate metadata against municipal trade schema guidelines.
## User
Rural business facilitation assistant
## Workflow
1. Process trader queries regarding municipal market vendor permits in local dialects.
2. Translate trader metadata and business premises descriptions into standardized formats.
3. Inspect uploaded proof metadata for validity dates, address matches, and file sizes.
4. Export a normalized vendor permit submission dossier for municipal clerk verification.
## Interface
Multi-step vernacular form displaying field-by-field document completeness status and translation checks.
## Data
Curate synthetic municipal permit application guidelines and mock trader business profiles with simulated proof documents.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Implements Bhashini API task sequence conventions (NMT + TTS task mapping) for bilingual verification steps.
## Tools
semantic-kernel, pydantic.
Semantic Kernel orchestrates modular vernacular skill plugins and structured validation filters for document metadata.
API-hosted or local model supporting multilingual schema transformation and document validation.
## 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
- Identifies missing mandatory premises permits or expired validity windows.
- Outputs dual-language application summaries for municipal submission.
- Enforces strict metadata schema validation without hallucinating missing fields.
## Starter Examples
```json
[
{
"input": {
"trader_name": "Kishan Lal",
"business_type": "GRAIN_RETAIL",
"lang": "hi",
"document_records": [
{
"doc_type": "MUNICIPAL_TAX_RECEIPT",
"valid_until": "2026-03-31",
"address_match": true
}
]
},
"expected_output": {
"dossier_status": "READY_FOR_CLERK",
"missing_docs": [],
"language_handled": "hi",
"summary_hi": "Anaj bikri hetu dastavej purn hain."
}
},
{
"input": {
"trader_name": "Ananya Rao",
"business_type": "EDIBLE_OIL_DEPOT",
"lang": "kn",
"document_records": [
{
"doc_type": "FIRE_SAFETY_NOC",
"valid_until": "2023-01-15",
"address_match": true
}
]
},
"expected_output": {
"dossier_status": "ACTION_REQUIRED_EXPIRED_NOC",
"missing_docs": [
"ACTIVE_FIRE_SAFETY_NOC",
"TRADE_TAX_RECEIPT"
],
"language_handled": "kn",
"summary_kn": "Agnisuraksha pramanapatrada avadhi mugidide."
}
}
]
```
## Safety
Strictly excludes official government tax account logins or direct government server write actions.
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.