JevMade Sign in
← Back to videos

JevMade field notes / Video guide

Jev入門 話題の判断専用AI、Jevの組み込みを試してみました

Makoto Taniguchi demonstrates TypeSafe AI's Jev, explaining its structured probability output, testing criteria and states in the playground, and implementing an inquiry categorization web application.

Original by ともすた | たにぐち まことGetting startedBeginner16 min 14 sec Published

Before you press play

What you’ll find in the video

  1. Jev takes structured inputs and returns probability scores rather than natural language text, simplifying programmatic parsing.
  2. Playground prompts can be refined using explicit criteria and dynamic state variables to guide Boolean or categorical determinations.
  3. Applications can call the TypeSafe REST API with choice fields to classify customer service inquiries into predefined categories.
Worth knowing

The author received early waitlist access and notes the demonstration is a preliminary exploration rather than an exhaustive production evaluation.

All video guides →Prefer to read? Written guides →

Jev入門 話題の判断専用AI、Jevの組み込みを試してみました

by ともすた | たにぐち まこと · YouTube Trouble playing? Open on YouTube

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.