Jev AI is a TypeSafe AI System One model and developer platform for turning shared state into typed decisions with probabilities. It supports classification, routing, scoring, safety checks, and agent workflows through an online playground, SDK or REST API, with Choice, Score, and Noul question types.
Who it is for
Developers and teams building agents, routing, scoring, and safety workflows.
Problem it solves
Chat interfaces are hard to integrate when systems need a typed decision, a score, or calibrated probabilities from shared state.
The solution
Jev AI converts shared state into typed decisions through the Jev model, online playground, SDK, and REST API.
What makes it unique
Not chat: Choice, Score, and Noul question types return structured, probability-backed outcomes for production systems.
Features1 listed
Probability-backed decisions
Turn real-world state into structured choices, scores, and probabilities.
Details
Platforms
Web
Pricing
Free
Built for
Developers and teams building agents, routing, scoring, and safety workflows.
In IndieTools' mobile lab test on November 9, 2026, the Jev AI website scored 93 out of 100 (good). Largest Contentful Paint took 1.50 s, rated good. It placed #1075 overall in the finalized week 2026-W45.
Measured (UTC)
LCPLargest Contentful Paint
1.50 s
Good
TBTTotal Blocking Time
170 ms
Good
CLSCumulative Layout Shift
0.000
Good
FCPFirst Contentful Paint
1.50 s
Good
Ranked #1075 overall in 2026-W45, best #622.
Jev AI lab metrics
Speed metrics for Jev AI, measured November 9, 2026
Metric
Result
Status
Trend
Mobile lab testMid-range phone on a throttled 4G connection, two runs averaged. Changes compare with the run on Nov 9.
Performance score
GoodUp 6 points
93 / 100
GoodUp 6 points
First Contentful PaintFCP
GoodAbout the same
1.50 s
GoodAbout the same
Largest Contentful PaintLCP
GoodAbout the same
1.50 s
GoodAbout the same
Speed IndexSI
Needs improvementAbout the same
5.30 s
Needs improvementAbout the same
Total Blocking TimeTBT
Good192 ms faster
170 ms
Good192 ms faster
Cumulative Layout ShiftCLS
GoodAbout the same
0.000
GoodAbout the same
Unthrottled observationsTimed on the test machine's own fast connection, so they read lower than the lab metrics above.
Page loadLoad
165 ms slower
2.78 s
165 ms slower
Server responseTTFB
10 ms slower
26 ms
10 ms slower
Jev AI performance history
52 comparable mobile lab runs since September 27, 2026. Choose a metric and a range, then move along the line to read each run.
Jev AI Speed ranking
Weekly Speed standing for Jev AI
Weekly standingLatest finalized week 2026-W45. Bests cover the last 52 finalized weeks.
Stored lab observations from controlled test runs, not real-user Core Web Vitals or a guarantee of search rankings. Weekly standings remain attached to their finalized edition.Method psi-mobile-two-sample-mean-v1, 2 samples per reading. Lab results can vary between runs.
Model difference+2. DR4 is 2 points higher than DR3.
Measured · thejevai.com
What do DR4, DR3 and the model difference mean?
DR4:
Ahrefs' newer model. It gives more weight to links from sites with organic search traffic and rates a subdomain on its own links.
DR3:
The previous model, shown in the Ahrefs app until 1 December 2026.
Model difference:
DR4 minus DR3 for the same domain. The models calculate differently, so this is not growth or a drop; the “since” lines compare each model with itself.