X · by zhayujie

Batch ticket analysis with CowAgent

One call per ticket returns seven classifications with probabilities.

Yujie Zha

@zhayujie

Had CowAgent build a batch ticket analysis tool on Jev. Jev doesn't generate text. You send content and typed questions, it returns classifications, scores and booleans, each with a probability distribution. One call per ticket, 7 judgments, ~500ms.

Sep 21, 2026 · 1 likesOpen on X

Using CowAgent on Jev, one call per support ticket returns seven classifications, scores and boolean judgements, each with its probability distribution. The batch runs over the whole queue rather than one ticket at a time.

Open the source

More like this

Riley Brown
@rileybrown
Yeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.
XTriage and routing
500 emails for 3.5 cents
Emails
500
Cost
3.5 cents
vogel
@ryanvogel
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
XTriage and routing
Triage across 1,500 emails
Volume
~1,500 emails
Hassan
@nutlope
Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on @togethercompute - $0.003 (1/3 of a cent) from Jev on @typesafeai. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.
XTriage and routing
Pick
Fraud detection with Jev and Kimi K3
Emails
100 in 1.42 s
Correct
96/100
Cost
~$0.07

Batch ticket analysis with CowAgent

More like this

500 emails for 3.5 cents

Triage across 1,500 emails

Fraud detection with Jev and Kimi K3