About
AskStein is a citation-locked biomedical retrieval system.
It answers clinical and research questions by pulling passages from a curated corpus of peer-reviewed literature and composing a response in which every claim traces back to a verifiable source — and when the evidence isn't there, it declines to answer rather than guessing.
Medical knowledge is enormous, fragmented, and moving faster than any clinician can keep up with. General-purpose language models can summarize it fluently, but they hallucinate — including inventing citations that look real and aren't. In medicine, a confident but ungrounded answer is worse than no answer at all. Clinicians and researchers need answers they can trace back to primary literature, and they need the system to admit when it doesn't know. That combination — grounded, auditable, and honest about its limits — is what almost no general tool actually delivers.
At its core, AskStein is not a model — it's a retrieval system wrapped around one. That distinction is the whole point. The trustworthiness lives in three places:
Corpus
A curated, de-duplicated body of biomedical literature drawn from legitimate open-access sources.
Retrieval
The machinery that finds the most relevant passages for a given question.
Citations
A deterministic layer that guarantees every reference in an answer is real and correctly attributed.
The language model's job is deliberately narrow: read the retrieved evidence and write an answer grounded in it. It is explicitly not permitted to invent citations, and when retrieval doesn't surface adequate evidence, the system abstains. The intelligence people trust isn't the model's fluency — it's the curation and the discipline around it.
AskStein's central bet — confirmed empirically in its own testing — is that retrieval quality, not model size or fine-tuning, is the dominant driver of answer accuracy. Improving the corpus and the retrieval pipeline moves the needle more than swapping in a bigger model. That's why the curated, citation-grade corpus is the competitive advantage, not the model. Anyone can call an LLM; the defensible asset is the curated body of evidence and the standards that keep it clean.
The real competition isn't a general-purpose chatbot — it's the well-capitalized incumbent in this space, OpenEvidence. AskStein's wedges are four:
Curation
The corpus is deliberately assembled and auditable, not an opaque black box.
Depth
Rather than covering all of medicine shallowly, AskStein goes deep in one specialty first.
Integrity
Citations are guaranteed by architecture, not coaxed out of a prompt.
Honesty
The system is built to say "I don't know" rather than to always produce an answer.
AskStein starts narrow, in orthopedic clinical decision support. A focused specialty lets the team build genuine depth, validate the system with real clinical experts, and earn credibility before expanding. The beachhead is anchored by a clinical co-founder with deep institutional standing, which unlocks research infrastructure, clinical validation, and eventual pilot access that a generic tool simply can't reach. Depth first, breadth later. See the team →
AskStein isn't trying to be a smarter chatbot. It's building what medicine actually needs: a trustworthy, auditable memory layer where every answer traces back to real evidence — or the system honestly says it doesn't know. The model is a commodity. The curated corpus, the citation discipline, and the clinical validation are the moat.