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 Inbound Demo Qualification and Scheduling Agent

Format
Code-aware
Lines
61
Sections
11
Linked challenge
Build an Inbound Demo Qualification and Scheduling Agent

Prompt source

Original prompt text with formatting preserved for inspection.

61 lines
11 sections
No variables
1 code block
## Who Uses It
A sales operations team routing incoming product inquiries.

## What You Will Build
Build an agent that turns inbound inquiries into evidence-backed qualification records and meeting proposals. Collect missing information, match the right representative, and book approved slots in a test calendar.

## Inputs
- Inbound inquiry
- Qualification rules
- Representative roster and calendar availability

## Workflow
1. Extract company needs from the inquiry.
2. Apply the supplied qualification rules and identify missing information.
3. Choose an eligible representative and propose available times.
4. After consent, reserve one slot and update the mock customer record.

## Interface
An inquiry inbox with qualification evidence, follow-up questions, meeting choices, and booking status.

## Working Demo
Qualify the request, propose S1, request consent, and create one mock booking after consent is supplied.

## 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
{
  "inquiry": {
    "id": "Q1",
    "text": "We need a demo for 25 support agents in the UK.",
    "seats": 25,
    "region": "UK",
    "consent": false
  },
  "qualification": {
    "minimum_seats": 10
  },
  "representatives": [
    {
      "id": "R1",
      "region": "UK"
    }
  ],
  "slots": [
    {
      "id": "S1",
      "representative": "R1",
      "starts_at": "2026-10-01T10:00:00Z",
      "version": 1
    }
  ]
}
```

## Constraints
Use synthetic leads and a test calendar. Do not contact real prospects.
Choose an available model that supports your implementation. Record its identifier and version.

## Evaluation
Review the complete application, not only the starter-case answers.
- Qualification cites 25 seats against the 10-seat rule.
- No booking occurs before consent.
- A retried confirmation does not create another meeting.
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.