Skip to main content

Lumen: AI Literature Scout Agent

Lumen is an AI literature scout that searches PubMed, bioRxiv and Consensus, separates peer-reviewed work from preprints and cites a PMID or DOI for every claim.

Last updated:

What does Lumen do?

Lumen is the Literature Scout in the xSquads Life Sciences Squad. Finds and synthesises papers and preprints with citations. It works on your own files in the xSquads desktop app, and it drafts rather than sends: anything that leaves your company waits for your approval.

Lumen at a glance

Role
Literature Scout
Squad
Life Sciences Squad (Health & Life Sciences)
Works with
Cohort (Clinical Trials Analyst), Vector (Target Discovery Scientist), Sentinel (Regulatory & Pipeline Analyst), Codon (Bioinformatician), Panel (Scientific Illustrator)
Who approves the work
You. Drafts wait for your review before anything is sent or published.
Skills and live data connectors
1 skill, 4 data connectors
Connections needed
None beyond the app

Common problems Lumen solves

Where this work usually goes wrong, and what Lumen does about it.

Literature reviews that take weeks

The problem: Searching databases, screening abstracts and reading papers for one question eats days before any thinking happens.

How Lumen handles it: Lumen searches PubMed, bioRxiv and Consensus for the question and summarises what the evidence agrees on and where it conflicts.

Preprints treated as settled science

The problem: A striking preprint ends up in a deck as if it had been peer reviewed.

How Lumen handles it: Lumen separates peer-reviewed work from preprints and rates each study's strength by design, sample size and caveats.

Citations that cannot be checked

The problem: AI summaries cite papers that do not exist, or say things the paper does not.

How Lumen handles it: Lumen gives every claim a citation with its PMID or DOI, and flags anything it could not verify.

How Lumen is tuned for the job

Lumen is not a general chatbot with a new name. It runs with a fixed role, a focus list and skills it reads before each task, so its output is consistent and on point from the first request.

What keeps it fast and accurate

  • Connects to live literature databases through plugins: PubMed, bioRxiv, Consensus and the Wiley Scholar Gateway.
  • Uses scientific-problem-selection to frame the question before it searches.
  • Provides research support only, not medical advice.

Its standing focus

  • Search PubMed, bioRxiv and Consensus for the question, then separate peer-reviewed work from preprints.
  • Summarise what the evidence agrees on, where it conflicts and how strong each study is (design, sample size, caveats).
  • Give every claim a citation with its PMID or DOI; flag anything you couldn't verify.
  • Research support only, not medical advice. Always cite the database record, PMID or NCT id behind every claim.

Skills it reads before a task

  • scientific-problem-selection

Live data connectors

  • pubmed
  • biorxiv
  • consensus
  • wiley-scholar-gateway

Rules it always works by

  • Asks one short clarifying question only when a task is truly ambiguous; otherwise it states its assumption and gets on with it.
  • Drafts, does not send: anything that leaves your company, such as an email, a post, a ticket reply or a contract, waits for you to review and approve.
  • Leads with the answer and keeps caveats to one line, with depth only when you ask for it.
  • Cites sources and never invents facts, figures, quotes or links; it says what it could not verify.
  • Keeps notes on your preferences, voice and standing decisions in memory and reuses them.
  • Reads the relevant skill before a task the skill covers, and follows it.

What you can ask Lumen to do

Requests are written in plain language. A few examples:

  • What is the evidence for GLP-1 agonists in fatty liver disease?
  • Summarise recent preprints on this target
  • Find conflicting studies on this biomarker and explain why they differ
  • Rate the strength of the main papers on this question

Lumen's teammates in the Life Sciences Squad

Add Lumen on its own, or import the whole squad so each part of the work goes to the agent built for it.

Frequently Asked Questions About Lumen, the AI Literature Scout

Which databases does Lumen search?

PubMed, bioRxiv, Consensus and the Wiley Scholar Gateway, through live data plugins. Every claim it reports cites a PMID or DOI.

Can Lumen give medical advice?

No. Lumen provides research support only, not medical advice. It summarises and cites the literature for researchers to evaluate.

How do I add Lumen to xSquads?

Open the xSquads app, go to Explore agents, find Lumen under the Life Sciences Squad and choose Add Lumen. Lumen joins your sidebar as its own chat with its skills ready. To get the whole team, import the Life Sciences Squad from Squad templates.

Put Lumen to work

Download xSquads, open Explore agents and add Lumen. Or have the xSquads team set it up for your team and tune it to how you work.

Download for Mac and Windows