@askOkara we saw this in Orior too: a decision call that took ~8s with Gemini 3.8 Flash now takes under 1s with Jev. it’s a great fit for bounded decisions inside a workflow.
the tiny in-between movements are what make AI UGC feel real: a natural pause, eyes drifting, hands moving at the right time. that’s the kind of detail we’re trying to get right in Orior.
i had to watch this 4 times before i could convince myself it was ai
seedance 2 5 just erased so many of the little things that used to expose ai ugc
the half second pause before she answers
the eyes drifting off camera
the tiny shoulder movement
the hand moving before the words
the little imperfections that make someone feel real
this isnt ai that looks good anymore
it feels like a real creator
except she doesnt even exist
and thats the part that breaks your brain
watch this
zero disrespect to the prompt gods @noneugc , but typing out massive text blocks is basically dead for me.
just dropped the image into @oriorapp and the character matched it perfectly.
same result, completely different workflow.
Jev probably isn’t useful to you.
we used it in Orior and took decision steps from ~8 seconds with Gemini 3.8 Flash to under 1 second.
both can be true.
Jev doesn’t write text. you give it a situation and the possible answers. it returns a choice, a score or a yes/no judgment, with confidence.
“where should this request go?” is the kind of question it handles.
that’s why developers are excited. plenty of apps spend seconds asking a language model for what ultimately becomes one small decision.
we replaced those calls. the rest of our workflow still uses generative models.
if you want a better chatbot, this isn’t it. if your app keeps users waiting while it decides what to do next, pay attention.
Jev probably isn’t useful to you.
we used it in Orior and took decision steps from ~8 seconds with Gemini 3.8 Flash to under 1 second.
both can be true.
Jev doesn’t write text. you give it a situation and the possible answers. it returns a choice, a score or a yes/no judgment, with confidence.
“where should this request go?” is the kind of question it handles.
that’s why developers are excited. plenty of apps spend seconds asking a language model for what ultimately becomes one small decision.
we replaced those calls. the rest of our workflow still uses generative models.
if you want a better chatbot, this isn’t it. if your app keeps users waiting while it decides what to do next, pay attention.
the era of typing out massive prompts is so dead.
just feed @oriorapp a reference image and the character matches the exact pose.
the entire workflow is literally this clean.
Look who’s back, @oriorapp v2!
The ultimate platform for AI UGC and consistent influencer creation.
Scale e-com product promos or build a lifestyle persona right from scratch.
Zero complicated workflows. Just seamless, high-quality content scaling.
Build with us here.
i was making users wait for AI to plan videos they might just skip 💀
plugged Jev into Orior and changed that flow.
it scores viral formats against your brand and audience. you browse, find something you like, hit remix. that’s when the actual planning starts.
also wired it into prompt safety and checking whether our voiceovers make claims the product evidence actually supports. uncertain cases still go through a deeper review.
this is what got me excited about Jev. once you start looking at your app, these little decisions are everywhere.
every one of them used to feel like another reason to call an LLM.
now i’m going through the rest of Orior wondering how many of those calls we actually need.
i was making users wait for AI to plan videos they might just skip 💀
plugged Jev into Orior and changed that flow.
it scores viral formats against your brand and audience. you browse, find something you like, hit remix. that’s when the actual planning starts.
also wired it into prompt safety and checking whether our voiceovers make claims the product evidence actually supports. uncertain cases still go through a deeper review.
this is what got me excited about Jev. once you start looking at your app, these little decisions are everywhere.
every one of them used to feel like another reason to call an LLM.
now i’m going through the rest of Orior wondering how many of those calls we actually need.
Guess who's back?
Introducing @oriorapp version 2.0
The ultimate platform for AI UGC & consistent influencer creation. Scale e-com product promos or build a lifestyle persona from scratch.
Zero complex workflows.
Build with us.