Ontelic builds Vellit — an AI that helps people know their rights, and helps lawyers and advocates work faster. Tuned hard against hallucinations, starting in Uzbekistan and expanding across the CIS toward the EU.
Ontelic builds Vellit — an AI that helps people know their rights, and helps lawyers and advocates work faster. Tuned hard against hallucinations, starting in Uzbekistan and expanding across the CIS toward the EU.
Ontelic isn't just another startup wrapping someone else's API. We build Vellit to help people know their rights — and to help lawyers and advocates work faster, grounded in real law, not guesses.
Ontelic was founded with a single goal: to make the law legible. Legal knowledge has always belonged to those who could afford a lawyer. Vellit exists to close that gap — a system that reads legislation the way it actually is, cites where an answer comes from, and says "I don't know" when it doesn't.
Vellit is fine-tuned and constrained specifically to minimize hallucinations in a domain where a wrong answer has real consequences. Every response is traceable to a source — either the live text of the law or a dated, versioned snapshot of it. We never let the model blend the two silently.
Our philosophy is simple: the model must be predictable, safe, and useful. Legal answers go through source-grounding and explicit uncertainty handling before they reach a user. We don't chase hype — we chase accuracy.
We don't run our own legal database from scratch. Vellit is built on top of official public sources — live government portals and open legislative datasets — transformed into a system that actually understands the difference between what the law says today and what it said in an archived snapshot. This is real engineering, aimed at one very concrete problem: people not knowing what they're entitled to.
Updates on the company and on Vellit as it moves toward launch.
Ontelic is discontinuing the Orynt model line and the Leili image generator to focus entirely on Vellit.
No fixed release date yet — but it launches fully self-sufficient from version one, starting in Uzbekistan.
Heading to Google Play first, with an App Store release to follow.
A single assistant that separates live legislation from archived snapshots, walks you through complex cases with follow-up questions, and never guesses when it isn't sure.
Chat about your legal situation, launch a multi-step case investigation, and get a shareable report — through a dedicated app, coming soon to Google Play and later App Store.
Ask about your situation in plain language. Every answer names its source — the live text of the law, or a dated snapshot — so you always know how current it is.
Vellit's chat is built around one rule: never mix "what the law says right now" with "what the law said in an archived dataset." Every reply is explicitly tagged with its source and, for the dataset, its cutoff date. If the two disagree, Vellit tells you — it doesn't quietly average them into a guess.
The model is fine-tuned specifically to minimize hallucination in a legal context. When it isn't confident, it says so and points you toward what to check next, instead of inventing a plausible-sounding article number.
A long-running investigation into your specific case. Vellit can pause to ask a clarifying question, remembers everything gathered so far, and picks up exactly where it left off.
A dossier is a case, not a chat message. Vellit works through it step by step, and if it needs more information from you, the session pauses cleanly in an "awaiting input" state — nothing is lost, nothing is rushed.
Once the investigation concludes, Vellit builds a clear report you can download as a PDF or share with a private link — useful when you need to hand your situation to a lawyer, an employer, or a government office.
Two sources, never silently blended: the live government legal portal, and a versioned, dated open dataset of Uzbek legislation. Vellit always tells you which one an answer came from.
Most legal-answer tools quietly average "what's probably still true" with "what used to be true." Vellit refuses to do that. Live lookups against the government legal portal are rate-limited and permission-gated, exactly as the source requires. The archived dataset is pinned, dated, and clearly labeled as a snapshot — not a live source.
If a lookup fails, Vellit says so — a failed request is never quietly returned as an empty, "nothing found" result. You always know whether Vellit found nothing, or simply couldn't check.
This separation is the whole point: the moment a legal assistant blurs old and current law without telling you, it stops being trustworthy. Vellit is built specifically not to do that — for a country and, soon, a region where knowing your rights shouldn't require a law degree.
Legal systems don't generalize easily — each jurisdiction has its own codes, its own language, its own institutions. So we're not expanding by translation. We're expanding by rebuilding the grounding for each country before we call it live.
Ontelic's first attempt: a general-purpose model line (Orynt) and an image generator (Leili). Retired in August 2026 — small demand, huge competition, and a market already full of strong general-purpose models from far larger labs. That experience is what pointed us toward a narrower, underserved problem instead.
Development is underway, with no fixed release date yet. Vellit isn't shipping until it's ready — but it launches fully self-sufficient from version one: legal chat, multi-step case investigations, and shareable reports all working from day one, not added later.
Vellit's first launch. Full coverage of lex.uz as the live source, plus an open, dated dataset of Uzbek legislation from 1991 to present as an archival fallback. This is where we prove the model, the sourcing discipline, and the case-dossier workflow.
Country by country, starting with jurisdictions that share structural similarities with Uzbek civil and administrative law. Each new country gets its own live-source integration and its own dated dataset — never a shared, blurred model of "post-Soviet law in general."
EU law spans supranational regulation and national implementation at once. We're not rushing it — this stage starts only once the sourcing and hallucination-minimization discipline from stages 1 and 2 has been proven at scale.
What doesn't change at any stop on this route: live law and archived snapshots are never mixed silently, every answer is sourced, and the model says "I don't know" rather than invent an article number. That discipline is the product — the country list is just where we apply it.
Ontelic is small on purpose. Two people, no committee, no layer of process between an idea and its deployment.
Nat Drexov — founder and sole developer of Vellit. Years of self-study in programming and systems design led him to a single, specific problem worth solving: people don't know their own rights, and the tools that promise to explain the law can't be trusted to get it right.
Without formal education in computer science, Nat learned to program through books and forums, and gradually came to an understanding: the most useful place for AI isn't answering trivia — it's standing next to a person at the exact moment they need to know what they're legally entitled to, and telling them the truth, sourced and dated.
That conviction shaped Vellit's core design rule: never blend live law with an archived snapshot without saying so. Nat believes a legal assistant's first duty isn't to sound confident — it's to be honest about what it actually knows and where that knowledge came from.
Today Nat leads all directions of the company — from the sourcing architecture to the product itself. His approach to development is characterized by an unwavering commitment to minimalism: remove everything superfluous, leave only what is essential. This philosophy shows up in Vellit's product design as much as in its technical implementation.
Every decision passes through that lens. There is no room for a shortcut that trades accuracy for speed. If a feature doesn't bring direct benefit to someone trying to understand their rights, it's removed. That takes more time to build — but the result is a system that's predictable, safe, and honest about its own limits.
A legal AI that sounds certain is more dangerous than one that admits doubt. We didn't build Vellit to have an answer for everything. We built it to know the difference between what it knows and what it doesn't — and to say so, every time.Nat Drexov CEO Ontelic
Ramazan — DevOps engineer keeping Vellit's backend alive on a shared FreeBSD box that was never designed for this. He was a friend of Nat's for years before he was a colleague, which is exactly why he's here.
Ramazan's job is unglamorous by design: deploys that don't break the running service, webhooks that stay registered, a JWT layer that doesn't quietly rot. When something in the pipeline silently pushes a stale build, he's the one who notices before it becomes a user-facing bug. Reliability isn't a feature he ships — it's the absence of things going wrong that nobody sees.
He and Nat go back to before Ontelic existed. Long before there was a company, a product, or a plan — there was just two people who trusted each other, in a city where trust is worth more than a resume.
That trust showed up in the most literal way possible early on: at a point when Nat didn't have a laptop to build on and Vellit was still nothing but an idea in his head, Ramazan bought him one and paid for it in crypto — no paperwork, no interest, no expectation of anything back. It's the kind of thing that doesn't show up on an org chart, but it's part of why this company exists at all.
Today that same instinct — show up, fix the thing, don't make a production out of it — is what keeps Vellit's infrastructure quiet and boring in exactly the way infrastructure should be.
"Before he ever touched a config file for us, Ramazan sent me a laptop I couldn't afford — paid in crypto, no strings. Every deploy he ships since is just the same thing, at a different scale." — Nat Drexov, on Ramazan
Vellit is more than a single model. The discipline around sourcing, caching, and error handling is what keeps it honest.
Every response is tagged with where it came from — the live government legal portal, or a dated, versioned open dataset. The two are never blended without saying so.
A failed lookup is always returned as an explicit error, never as a quiet "no results." You always know whether Vellit found nothing, or simply couldn't check.
Live lookups against the government legal portal honor its rate limits by design — Vellit was built to be a good citizen of the sources it depends on, not to hammer them.
© Ontelic. Vellit is fine-tuned and constrained specifically for legal accuracy — long chat sessions, multi-step case investigations that can pause on a clarifying question, and a strict separation between live and archived law. We invest in that discipline because in a legal context, a confident wrong answer is worse than no answer at all.
Important: Vellit is a tool for understanding your rights, not a substitute for a licensed lawyer in matters that require one. We're upfront about that distinction, every time it matters.