CapabilitiesIntegrationsDocsCatalogPricing
Sign In
Start research

Start

Docs homeChoose the right setup path.Getting startedFirst session, files, briefs, and presentations.

Product

WorkspaceChat, experiments, split panes, and artifacts.Library filesUpload and reuse PDFs, CSVs, docs, and datasets.BriefsCited, scannable research documents.PresentationsTemplated, cited stakeholder decks.DashboardsInteractive, filterable analytics views.

Admin

OrganizationsTeams, billing, roles, and account setup.Security & privacyKeys, stored data, revocation, and privacy posture.

Developers

Developer APIOpenAI-compatible and native agent endpoints.MCP serverUse Cortexa inside Claude, Cursor, Codex, and more.IntegrationsSlack, MCP, API keys, and connected workflows.Tool catalogExplore verified research tools and sources.

Documentation

Docs homeGetting startedWorkspaceLibrary filesBriefsPresentationsDashboardsOrganizationsSecurity & privacyDeveloper APIMCP serverIntegrationsTool catalog
Documentation

Getting started with Cortexa

Create an account, sign in, and turn a first research question into a cited answer, reusable analysis, and a shareable output.

Launch the agent
Your first session
Walk-through · attached file + cited answer
Live
Use the uploaded enrollment-q1.csv. What's the missingness across baseline biomarkers, and what should I prepare before training?
Tools usedLibrary: enrollment-q1.csvrun_python
Biomarker A is missing in ~7% of rows; biomarker C in ~22%. I'd impute A by median, drop or model C separately, and stratify the train/test split by enrollment quarter to keep cohort balance.
Biomarker A is missing in ~7% of rows; biomarker C in ~22%. I'd impute A by median, drop or model C separately, and stratify the train/test split by enrollment quarter to keep cohort balance.
dataset:enrollment-q1.csv
Ask anything worth knowing…

Create your account & sign in

Free to create, with a one-time grant of welcome credits so you can try real research right away.
Continue with Google
Ready immediately — no separate email verification step.
Email & password
“Create account,” 8+ char password — you're dropped straight into the agent.
Verify your email
Browse right away; verify before running metered work. Resend in-app.
Forgot password?
“Reset password” emails a one-hour link. (Google users sign in via Google.)

What you get on day one

A free plan plus a one-time grant of welcome credits. After signing in you land in the agent at /chat. Working with a team? See Organizations & workspaces.

Recommended flow

The cleanest first run is narrow: ask one question, ground it with files or sources, then turn the useful result into an artifact.
1 · Start a session
Ask a narrow first question; attach any source files that shape it.
2 · Ask for evidence
Request mechanisms, evidence tables, trade-offs, open questions — with citations.
3 · Run experiments
Python cells for cleaning, statistics, charts, or model-ready transforms.
4 · Save what persists
Send important outputs to the Library to reuse them later.
5 · Package it
Generate a brief, deck, or dashboard once the session has enough context.

A good first request

“Summarize the current evidence for X, cite primary sources, separate established findings from hypotheses, and list the next three analyses I should run.”

Prompt patterns

Good prompts tell the agent what evidence matters, which files to inspect, and what shape the answer should take.
Ask for structure + citations
Name the sections you want and request primary sources.
Name the file to use
Point the agent at a specific dataset or uploaded file.
Set the depth
Say whether you want a fast scan or a deeper investigation.
Refine with follow-ups
Critique, narrow, or convert the answer into an artifact.
Cortexa.

The agent for research teams. 2.2K+ verified tools across every research discipline, every claim cited.

Product

  • Capabilities
  • Integrations
  • Documentation
  • Tool catalog
  • Pricing

Get started

  • Launch the agent
  • Sign in
  • Developer API
  • MCP server

Support

  • Help center
  • Contact us
  • Terms of Service
  • Privacy Policy

© 2026 Cortexa. All rights reserved.

TermsPrivacy·For research context only · Not medical, legal, or financial advice.