Undermind

What is Undermind?

Undermind is an AI literature-discovery agent purpose-built for scientific research, not general web search. It was founded in 2024 by CEO Joshua Ramette and CTO Tom Hartke — both MIT-trained physicists, with research backgrounds spanning LIGO gravitational-wave astrophysics, CERN particle physics and quantum computing — and backed by Y Combinator's Summer 2024 batch. Given a research question, it iteratively reads and evaluates hundreds of full-text papers and follows citation trails rather than matching keywords, aiming at the "long-tail" papers a conventional database search misses. It is used by researchers at MIT, Harvard, Caltech, Princeton, Berkeley and Cambridge, and by industry teams including 1,000+ scientists at GSK.

What does Undermind do?

You describe a research question in plain language and Undermind runs an iterative, multi-hop search: it reads and evaluates hundreds of candidate papers' full texts (not just abstracts and titles), follows citation trails to surface work a keyword search would miss, and scores each result for relevance. A distinguishing feature, independently reviewed in the Journal of the Canadian Health Libraries Association (August 2025): a "discovery curve" statistical model that estimates roughly what percentage of the actually-relevant literature has been found, so you get a completeness signal rather than just an unranked result list. The same review clocked a typical search at 8-10 minutes, delivered as an organized report with match scores and a citation network; you can save searches into projects and paper libraries, set up recurring alerts when new matching papers publish, and refine a complex question through follow-up dialogue the way you would with a research librarian. Team and Enterprise tiers add shared projects, an admin dashboard and organization-wide SSO.

How Undermind works

1. 1Describe a research question in plain language, optionally refining it through follow-up dialogue.
2. 2Undermind reads and evaluates hundreds of candidate papers' full texts and follows citation trails rather than matching keywords.
3. 3Results are scored for relevance and delivered as an organized report (8-10 minutes typical) with a citation network and a "discovery curve" completeness estimate.
4. 4Save the search into a project or paper library, and optionally set a recurring alert for new matching papers.

Who is Undermind for?

• Individual researchers and grad students doing exploratory literature discovery on a niche or cross-disciplinary topic
• R&D and industry science teams (e.g. biotech, pharma) who need to catch long-tail prior art a keyword search would miss
• Institutional research teams that already have access to Elicit or PubMed and want a second, citation-trail-based search pass

Key features

• Multi-hop citation-trail search: Reads and evaluates hundreds of full papers and follows citation trails, rather than one-shot keyword matching against abstracts.
• Discovery-curve completeness estimate: A statistical model estimates roughly what percentage of the relevant literature has actually been found — a completeness signal most keyword search tools don't offer.
• Match-scored, cited reports: Each candidate paper gets a relevance score; findings are delivered as an organized report with a citation network, not a flat list.
• Recurring alerts: Notifies you when new papers matching a saved research topic are published.
• Dialogue-based query refinement: Iteratively narrows a complex or niche research question through follow-up questions, echoing a librarian reference consultation.

What are Undermind's use cases?

• Novelty and prior-art check: A researcher scoping a new project asks Undermind to surface everything already published on a niche or cross-disciplinary question before committing to a research direction.
• Finding papers a manual search missed: A scientist who has already done a keyword-based literature search runs the same topic through Undermind's citation-trail search to catch long-tail, cross-disciplinary papers a database search style misses.
• Ongoing topic monitoring: A lab sets a recurring alert on a research area so new relevant papers surface automatically instead of a manual re-search each month.

Why use Undermind?

• Reads full paper texts and follows citation trails rather than keyword-matching abstracts — independently reviewed as genuinely finding papers a conventional search misses.
• Publishes a "discovery curve" completeness estimate so you know roughly how much of the literature was actually covered, not just an unranked result list.
• Founded by two MIT-trained physicist-researchers who built it to solve their own literature-review problem, YC-backed (Summer 2024).
• Real institutional adoption: used at MIT, Harvard, Caltech, Princeton and Berkeley, and by 1,000+ scientists at GSK — not just a demo product.
• A genuine free tier, not just a time-limited trial, so you can evaluate it on a real question before paying.

Pros & cons

Undermind pricing

• Free$0
• Pro$16 / mo (billed annually)
• Team$15 / person/mo (billed annually)
• EnterpriseCustom

See current pricing on undermind.ai ↗Compare Undermind alternatives →

Undermind review

Undermind is the discovery-focused entry in this category: instead of screening papers you already found against inclusion criteria (Elicit's job) or answering an open-web question (Perplexity, Manus, GC AI's different domains), it tries to find the papers a conventional keyword search misses, by reading full texts and following citation trails, and it tells you roughly how complete that search was via its "discovery curve" model. An independent peer-reviewed review backs the core pitch — it genuinely surfaces papers others miss — but the same review is equally direct about the trade-offs: no reproducible search strategy (its self-described "Achilles heel"), an 8-10 minute turnaround too slow for point-of-care use, and no MeSH integration. It also has no API today, unlike Elicit. Pick Undermind when the job is exploratory discovery or a novelty check on a niche or cross-disciplinary question; pick Elicit instead when you need a documented, repeatable screening process for a formal systematic review.

The discovery-focused pick in this category — genuinely finds papers a keyword search misses, per independent peer review, but trades away a reproducible search strategy and any API.

Frequently asked questions