Back to Prompt Library
Build the complete application
Implementation brief
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Supply Chain Disruption Planning Agent
Format
Code-aware
Lines
64
Sections
11
Linked challenge
Build a Supply Chain Disruption Planning Agent
Prompt source
Original prompt text with formatting preserved for inspection.
64 lines
11 sections
No variables
1 code block
## Who Uses It
A logistics planner responding to delayed shipments and inventory shortages.
## What You Will Build
Build an agent that combines shipment disruptions, inventory demand, and carrier options into a recovery plan. Compare feasible routes, explain cost and delivery tradeoffs, and request planner approval before dispatch.
## Inputs
- Shipment and disruption records
- Inventory requirements
- Carrier routes, capacity, and prices
## Workflow
1. Identify affected orders and inventory deadlines.
2. Retrieve alternative routes and capacities.
3. Calculate feasible plans against delivery and budget limits.
4. Present a ranked proposal and record planner approval in the mock system.
## Interface
A shipment planning board with route comparisons, inventory impact, estimated costs, and a reviewable dispatch proposal.
## Working Demo
Recommend R1, explain why R2 and R3 fail the supplied limits, and keep dispatch pending planner approval.
## Deliverables
- A working local application with the specified review interface.
- Source code, dependency lockfile, and setup commands.
- A recorded end-to-end demo using the supplied starter data.
- Example outputs, action logs, and automated tests.
## Starter Data
These fictional records are a small development fixture, not a production dataset. Implement the mock services described in the brief.
```json
{
"shipment": {
"id": "S1",
"units": 10,
"deadline_hours": 24,
"budget": 100
},
"disruption": "Original port is closed.",
"alternatives": [
{
"id": "R1",
"hours": 20,
"capacity": 10,
"cost": 80
},
{
"id": "R2",
"hours": 12,
"capacity": 10,
"cost": 120
},
{
"id": "R3",
"hours": 30,
"capacity": 10,
"cost": 60
}
]
}
```
## Constraints
Use synthetic inventory and carrier responses. Do not reroute real freight or place purchase orders.
Choose an available model that supports your implementation. Record its identifier and version.
## Evaluation
Review the complete application, not only the starter-case answers.
- R1 meets the capacity, deadline, and budget requirements.
- Rejected routes have specific reasons.
- No dispatch occurs without approval.
Add one normal case, one incomplete-input case, and one failure-recovery case.Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the source structure until you know which part of the prompt is actually driving the result quality.
Tune next
Change domain facts, examples, and tool context first before you rewrite the instruction scaffold.
Verify after
Validate one failure mode at a time so prompt changes stay attributable instead of getting noisy.