How many questions does it ask Jev per review?

Fourteen — two for each of the seven topics, covering mention detection and satisfaction — sent to Jev together in one request per review, per the README.

Which topics does it analyze?

Camera, Battery, Display, Design, Performance, Build Quality and Value for Money.

How does it avoid inventing ratings for unmentioned topics?

It runs mention detection: a topic is only rated if the review actually discusses it, so there are no made-up ratings.

What kind of scores come back?

Fine-grained continuous satisfaction scores such as 3.4 stars, not just whole-star buckets, rolled up into a per-topic summary.

What does it need to run?

Python 3.8 or later and a TypeSafe SDK key for Jev; the digest shows a badge for 50 sample reviews, and the README's run steps are truncated in the capture.

Is there a licence or evaluation?

No licence is listed in the digest metadata and no accuracy evaluation is captured; the README excerpt ends inside the question table, so those details are unavailable here.

Jev directory

CommunityJev Demos & Experiments

Smartphone Review Analyzer

A Python first-project that turns messy free-text smartphone reviews into Flipkart-style per-topic star ratings, powered by Jev via the TypeSafe SDK: 14 questions per review — mention detection plus satisfaction — across 7 topics such as camera, battery and display.

See highlights Open github.com

Stars: 0
Language: Python
Reading time: 2 min
Published by: Community
Author: saksham110206
Last verified: Oct 2026

saksham110206/review-system-by-jev

User repository on GitHub

View on GitHub

first project using jev, for giving indivdual review on each characteristics or component of smartphone.

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity github python reviews

Works forJev for Classification Jev for Scoring

Used inJev for E-commerce & Retail

Languages: Python
Capabilities: Open sourceRequires API key

Highlights

Reads review text, detects which of 7 topics it discusses, and rates satisfaction per topic — 14 Jev questions per review in one request.
Topics: Camera, Battery, Display, Design, Performance, Build Quality and Value for Money.
Satisfaction comes back on a continuous scale, for example 3.4 stars, rather than whole-star buckets.
A topic is rated only when the review actually mentions it, so there are no made-up ratings.
Four small modules, no framework; sample data is 50 reviews and the badge asks for Python 3.8+.

Watch out

README and GitHub metadata reviewed 2026-10-17; the digest cuts off inside the question-type table, so install and run instructions, the exact question wording and any accuracy checks are not visible, and no licence is listed.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.

Jev Demos & Experiments#gaming#agents#control

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai