Laugh Track: rehearse a speech for 200 Jev listeners

# ⚡ Jev Kit

**Your LLM thinks. Jev decides.**

A growing kit of tools that plug [Jev](https://docs.typesafe.ai), TypeSafe AI's System One decision model, into Claude, ChatGPT, your browser and your terminal. Jev answers typed questions (yes/no, pick one, score on a scale) with probabilities in well under a second for fractions of a cent, so you can afford to ask thousands of small questions that would be slow or expensive to send to an LLM. Your LLM does the writing and explaining; Jev does the judging.

Published on npm as [`@leighefford/jev-kit`](https://www.npmjs.com/package/@leighefford/jev-kit). It's unrelated to the separate `jev-kit` package.

## 😂 Laugh Track: rehearse in front of a room

<p align="center">
  <img src="docs/laugh-track.gif" width="860" alt="Laugh Track playing a best man speech to a room of 200 simulated people: seats light up gold for laughs, pink for moved, blue for applause and green for groans as each line plays, with per-line scores on the left.">
</p>

Paste a speech, stand-up set or pitch, or bring a recording of yourself giving it. Two hundred simulated people react to every line: laughs, groans, silence, or being moved. Jokes are judged on laughs and heartfelt lines on warmth, and you get the three lines to rework first. With a recording, it's transcribed for you, your pace and pauses are part of the analysis, and you can play it back alongside the room.

```bash
npx -y @leighefford/jev-kit laugh-track
```

Your browser opens, the seats fill up, and each line plays to the room in turn. When it finishes you get a score for every line, averages for the jokes and the sincere lines, and the three lines to rework first:

<p align="center">
  <img src="docs/laugh-track-results.png" width="860" alt="Laugh Track results for the example best m