Inbox triage

The agent prompt

Copy this brief into your coding agent from the root of the project you want to build in. It names the behaviour, the constraints, and the checks to run — the decisions Jev makes stay explicit so you can see what the model actually decided.

Build a small "Inbox triage" app in this repository using Jev from TypeSafe AI.

Inspect the repository first and work with its existing stack and design system. Use the official TypeSafe skill to verify the current SDK usage. If it is missing, install it with:
npx skills add typesafe-ai/skills --skill typesafe-ai

The app should accept a customer-support message as the state and evaluate these independent questions in one System One call:
1. A Choice named department with billing, technical, and sales options, each described clearly.
2. A Score named urgency with an ordered three-step rubric: can wait, respond this week, respond today.
3. A Noul named needs_human that asks whether the message needs a human follow-up.

Show the selected department, urgency, human-follow-up value, confidence, and probability distribution in a compact result card. Include three example messages users can load with one click.

Requirements:
- Use the official TypeSafe SDK appropriate for this codebase.
- Keep TYPESAFE_API_KEY on the server only and document it in the example environment file.
- Keep each question atomic; combine or route results in ordinary application code.
- Do not auto-send or mutate customer data. This is a transparent demo.
- Handle loading, invalid input, API errors, and low-confidence results.
- Add focused unit tests plus one happy-path UI test.
- Document setup, the question design, and how to run the project.

Run the relevant checks when finished, then summarize the architecture and the files you changed.

Built something like this

Community projects in the directory that solve a similar problem:

• JevTicktRouter
• typesafe-jev-workflow