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 Artisan Product Story and Evidence Dossier Generator
Format
Code-aware
Lines
77
Sections
11
Linked challenge
Build an Artisan Product Story and Evidence Dossier Generator
Prompt source
Original prompt text with formatting preserved for inspection.
77 lines
11 sections
No variables
1 code block
## Build
Compile geographical indication and artisan authenticity evidence into structured Beckn catalog listings. Synthesize rich product narratives from rural craft cooperative submissions.
## User
Handicrafts Cooperative Manager
## Workflow
1. Ingest artisan workshop photos, craft certificates, and informal production descriptions.
2. Extract raw material provenance, technique tags, and geographical origin credentials.
3. Draft compelling bilingual product stories conforming to open commerce catalog standards.
4. Assemble verifiable catalog payloads linked with digital craft evidence records.
## Interface
Artisan submission portal with multimedia preview, story narrative editor, and Beckn catalog export.
## Data
Curate synthetic artisan workshop profiles with handloom and terracotta craft descriptions.
Starter examples below are synthetic. They are not downloaded records.
## Source
[ONDC protocol specifications](https://raw.githubusercontent.com/ONDC-Official/ONDC-Protocol-Specs/master/README.md)
Leverages ONDC catalog taxonomy and descriptor extensions for traditional craft and artisan categories.
## Tools
anthropic-claude, fastapi, pydantic.
Synthesizes nuanced, culturally respectful product narratives from minimal artisan field notes.
Hosted Claude API for creative narrative synthesis and structured JSON generation.
## 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
- Extracts authentic material and craft method parameters into structured tags.
- Generates culturally accurate bilingual product descriptions.
- Structures catalog output with proper Beckn descriptor and media references.
- Verifies presence of craft certificates before marking items verified.
## Starter Examples
```json
[
{
"input": {
"coop_id": "COOP-WEAVERS-CHANDERI",
"notes": "Pure silk cotton saree woven on traditional pit loom by master weaver Mohan. Uses natural vegetable dye.",
"certificate_id": "GI-REG-IN-0028"
},
"expected_output": {
"catalog_item": {
"name": "Handcrafted Chanderi Silk Cotton Saree",
"technique": "PIT_LOOM_WEAVING",
"material": "SILK_COTTON",
"dye": "NATURAL_VEGETABLE",
"provenance": {
"gi_registered": true,
"gi_number": "GI-REG-IN-0028"
},
"evidence_verified": true
},
"status": "APPROVED_FOR_CATALOG"
}
},
{
"input": {
"coop_id": "COOP-POTTERS-01",
"notes": "Red clay water pot made locally.",
"certificate_id": null
},
"expected_output": {
"catalog_item": {
"name": "Red Clay Traditional Water Pot",
"technique": "POTTERS_WHEEL",
"material": "NATURAL_RED_CLAY",
"provenance": {
"gi_registered": false,
"gi_number": null
},
"evidence_verified": false
},
"status": "PROVISIONAL_PENDING_PROVENANCE"
}
}
]
```
## Safety
Uses synthetic cooperative profiles; marks evidence status as mock without legal GI endorsement.
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.