Skip to main content
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 an Employee Onboarding Coordination Agent

Format
Code-aware
Lines
78
Sections
11
Linked challenge
Build an Employee Onboarding Coordination Agent

Prompt source

Original prompt text with formatting preserved for inspection.

78 lines
11 sections
No variables
1 code block
## Who Uses It
An operations team preparing new employees for their first day.

## What You Will Build
Build an agent that coordinates approvals, equipment, training, and account requests from a new-hire record. Give each team an owned task list and show blockers, completion evidence, and start-date changes.

## Inputs
- New-hire record
- Role-based onboarding checklist
- Task dependencies and team capacities

## Workflow
1. Create tasks from the approved onboarding checklist.
2. Assign owners and order dependent tasks.
3. Track updates from mock HR, IT, and delivery systems.
4. Replan incomplete work when dates or approvals change.

## Interface
An onboarding board with task owners, deadlines, dependencies, blockers, and a first-day readiness summary.

## Working Demo
Create the board, allow T2 and T4 to start, keep T3 blocked, and update readiness when the laptop is prepared.

## 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
{
  "hire": {
    "id": "H1",
    "role": "support",
    "start_date": "2026-10-01"
  },
  "tasks": [
    {
      "id": "T1",
      "name": "Manager approval",
      "owner": "Manager",
      "depends_on": [],
      "status": "complete"
    },
    {
      "id": "T2",
      "name": "Prepare laptop",
      "owner": "IT",
      "depends_on": [
        "T1"
      ],
      "status": "pending"
    },
    {
      "id": "T3",
      "name": "Dispatch laptop",
      "owner": "Logistics",
      "depends_on": [
        "T2"
      ],
      "status": "pending"
    },
    {
      "id": "T4",
      "name": "Schedule training",
      "owner": "People Ops",
      "depends_on": [
        "T1"
      ],
      "status": "pending"
    }
  ]
}
```

## Constraints
Use fictional employees and mock systems. Do not ship equipment, sign documents, or create real accounts.
Choose an available model that supports your implementation. Record its identifier and version.

## Evaluation
Review the complete application, not only the starter-case answers.
- Every task has an owner and a dependency state.
- T3 cannot complete before T2.
- Readiness identifies incomplete tasks rather than claiming the hire is ready.
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.