JevMade hello@JevMade.com
← Back to getting started videos

JevMade field notes / Video guide

Jev AI Explained in Hindi | TypeSafe AI Tutorial + Live Demo

Abhijeet Kalamkar introduces TypeSafe AI's Jev decision model in Hindi. He explains Jev's core assessment categories—Noul, choice, and score—explores official playground templates, and tests a custom decision dashboard with live customer support, sponsorship triage, and comment classification examples.

Original by AI Learners IndiaGetting startedIntermediate18 min 42 sec Published Source reviewed

Before you press play

What you’ll find in the video

  1. Jev structures decision evaluations around three primary constructs: Noul (truth probability), choice (categorical selection), and score (numerical rubric assessment).
  2. Application developers define the state and specific analytical questions, while Jev evaluates the input against those rules to return probability distributions.
  3. Small changes in input text (e.g., asking for access activation versus a refund) immediately alter Jev's category probabilities and secondary decision scores.
Worth knowing

Gemini-assisted video/transcript review. The custom dashboard is an illustrative educational prototype; returned probabilities depend heavily on user-provided rules and do not guarantee correct business decisions or automate downstream actions.

Jev AI Explained in Hindi | TypeSafe AI Tutorial + Live Demo