Skip to main content

Cohort: AI Clinical Trials Analyst Agent

Cohort is an AI clinical trials analyst that maps the trial landscape for a condition or drug, with the NCT id for every trial, and drafts and critiques protocol elements.

Last updated:

What does Cohort do?

Cohort is the Clinical Trials Analyst in the xSquads Life Sciences Squad. Maps the trial landscape, designs and critiques protocols. 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.

Cohort at a glance

Role
Clinical Trials Analyst
Squad
Life Sciences Squad (Health & Life Sciences)
Works with
Lumen (Literature Scout), 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, 2 data connectors
Connections needed
None beyond the app

Common problems Cohort solves

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

Landscape reviews built by hand

The problem: Pulling phase, status, sponsor and endpoints for every relevant trial means hours of registry searches.

How Cohort handles it: Cohort maps trials for a condition or drug with phase, status, sponsor, endpoints, enrolment and sites, and the NCT id for each.

Protocols designed in isolation

The problem: Endpoints and comparators get chosen without checking what comparable trials used.

How Cohort handles it: Cohort drafts and critiques protocol elements, including population, endpoints, comparators and sample size logic, against comparable trials.

Missing the white space

The problem: Teams enter crowded areas or miss open ones because the landscape was never laid out.

How Cohort handles it: Cohort calls out landscape gaps and crowded areas in a short table.

How Cohort is tuned for the job

Cohort 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

  • Pulls trial data through live clinical trials and Medidata plugins.
  • Uses the clinical-trial-protocol skill for protocol structure.
  • Cites the NCT id behind every claim, and provides research support only, not medical advice.

Its standing focus

  • Map trials for a condition or drug: phase, status, sponsor, endpoints, enrolment and sites, with the NCT id for each.
  • Draft and critique protocol elements (population, endpoints, comparators, sample size logic) against comparable trials.
  • Call out landscape gaps and crowded areas in a short table.
  • Research support only, not medical advice. Always cite the database record, PMID or NCT id behind every claim.

Skills it reads before a task

  • clinical-trial-protocol-skill

Live data connectors

  • clinical-trials
  • medidata

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 Cohort to do

Requests are written in plain language. A few examples:

  • Map all phase 2 and 3 trials in atopic dermatitis
  • Critique the endpoints in this draft protocol
  • Which mechanisms are crowded in MASH trials?
  • Compare enrolment and sites across these trials

Cohort's teammates in the Life Sciences Squad

Add Cohort 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 Cohort, the AI Clinical Trials Analyst

Where does Cohort get trial data?

From live plugins for clinical trial registry data and Medidata. Every trial it reports carries its NCT id.

Can Cohort write a full trial protocol?

Cohort drafts and critiques protocol elements such as population, endpoints, comparators and sample size logic against comparable trials. Clinical and regulatory experts own the final protocol.

How do I add Cohort to xSquads?

Open the xSquads app, go to Explore agents, find Cohort under the Life Sciences Squad and choose Add Cohort. Cohort 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 Cohort to work

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

Download for Mac and Windows