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 Accessible Delivery Barrier and Drop-Off Assistant

Format
Code-aware
Lines
72
Sections
11
Linked challenge
Build an Accessible Delivery Barrier and Drop-Off Assistant

Prompt source

Original prompt text with formatting preserved for inspection.

72 lines
11 sections
No variables
1 code block
## Build
Aggregate hyper-local building access barriers reported by mock gig delivery partners. Compile structured delivery access guides for elderly and disabled residents.

## User
Delivery Accessibility Advocate

## Workflow
1. Ingest field delivery completion notes containing landmark and accessibility obstacles.
2. Extract physical obstruction tags including broken escalators, steep stairs, and gate closures.
3. Synthesize accessible delivery path dossiers for specific delivery hubs.
4. Format output as Beckn fulfillment instructions for subsequent courier dispatches.

## Interface
Map-based barrier log and instructions editor with quick-tag accessibility filters.

## Data
Construct synthetic delivery drop reports with varied accessibility issues across municipal zones.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Beckn protocol specifications](https://raw.githubusercontent.com/beckn/protocol-specifications/master/README.md)
Adopts Beckn final mile fulfillment tracking and delivery instruction schema conventions.

## Tools
anthropic-claude, fastapi, jinja2.
Generates clear, concise step-by-step navigation instructions from dense informal delivery notes.
Hosted Claude API for structured analysis and extraction from unstandardized text.

## 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
- Categorizes accessibility barriers into physical, temporal, and navigational tags.
- Generates multi-step safe drop-off navigation summaries for couriers.
- Formats instructions within Beckn fulfillment context requirements.
- Flags addresses lacking accessible paths for dispatcher intervention.

## Starter Examples
```json
[
  {
    "input": {
      "address_code": "ADDR-BLR-091",
      "courier_reports": [
        "Main elevator in Tower C under repair, use freight elevator behind service parking.",
        "Narrow entrance ramp blocked by two-wheelers after 6 PM."
      ]
    },
    "expected_output": {
      "accessible_route": "Enter through Tower C service lane; use rear freight elevator.",
      "known_barriers": [
        "MAIN_ELEVATOR_OUT_OF_SERVICE",
        "RAMP_CONGESTION_EVENING"
      ],
      "recommended_vehicle": "BICYCLE_OR_WALKER",
      "status": "ROUTE_ADAPTED"
    }
  },
  {
    "input": {
      "address_code": "ADDR-BLR-092",
      "courier_reports": [
        "Locked iron gate, no intercom, guard absent after 8 PM, high staircase only."
      ]
    },
    "expected_output": {
      "accessible_route": null,
      "known_barriers": [
        "ACCESS_LOCKED",
        "NO_ASSISTIVE_ENTRY",
        "STEEP_STAIRS_ONLY"
      ],
      "recommended_vehicle": null,
      "status": "MANUAL_RECHECK_REQUIRED"
    }
  }
]
```

## Safety
Maintains sanitized address identifiers without private contact details or residential occupant names.
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.