Feedback prism
Turn a pile of product feedback into themes, severity, sentiment, and concrete-request signals.
- Time
- 45–60 min
- Level
- Useful app
- Shape
- Feedback batch → four focused judgments → sortable review queue
- You’ll practice
- Batching · Multi-axis analysis · Review queues
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 "Feedback prism" app in this repository with Jev from TypeSafe AI.
Inspect the repository first and preserve its stack and conventions. Use the official TypeSafe skill for current SDK guidance; if missing, install it with npx skills add typesafe-ai/skills --skill typesafe-ai.
Users paste up to 20 short feedback items. For each item, ask independent questions in one System One call: a Choice for theme (bug, usability, performance, pricing, feature request, other), a Score for severity (minor friction, meaningful blocker, prevents use), a Choice for sentiment (positive, mixed, negative), and a Noul for whether it contains a concrete request. Display a sortable table, summary counts, and a review queue for uncertain classifications.
Requirements:
- Use the official SDK and keep TYPESAFE_API_KEY server-side.
- Limit input size and concurrency; show per-item failures without losing the batch.
- Put confidence thresholds and review policy in named application code.
- Store nothing remotely; make export an explicit CSV download.
- Add fixtures, mocked API tests, and one end-to-end happy path.
- Document setup and why every question is atomic.
Run the relevant checks and summarize changed files, decisions, and how to try it.Built something like this
Community projects in the directory that solve a similar problem: