Ubik Studio

The Problem

Existing AI assistants hallucinate citations and treat "research" as question-answering. Ubik Studio is built for the researchers who can't afford that — people writing theses, long-form journalism, policy analysis, or any work where citations actually get checked.

The product sits at the intersection of LLM tooling and epistemics: every claim the AI makes has to trace back to a real source the user has in hand.

What I Built

I designed and built the entire product from scratch as the sole technical co-founder.

• Full-stack application: Next.js frontend, Python backend
• Multi-model routing — researchers pick their provider (OpenAI, Anthropic, etc.) and switch mid-workflow without losing context
• PDF annotation engine — upload a paper, highlight a passage, and the AI cites from that passage specifically rather than paraphrasing from memory
• Citation verification pipeline — cross-references AI-generated claims against uploaded sources to flag potential hallucinations
• Local-first architecture — institutions with data privacy requirements can run Ubik on-premise

[TODO: Expand on any of these with a sentence or two about the specific technical approach — e.g. how does the citation verification work at a high level?]

Technical Architecture

[TODO: 3–4 sentence overview of the stack from top to bottom — what does a request lifecycle look like? Where does Cloudflare Workers come in specifically?]

Status

[TODO: Is Ubik Studio live and public? Are there paying users or institutional pilots? Any coverage or recognition worth noting?]