Agentic AI research assistant that interprets lab results and turns research questions into cited, evidence-backed briefs
Not given
Stage
Established
Not given
Founded
2018
Not given
Based in
CY
IN
Pricing model
Freemium
Free trial
Pricing
Basic (free) with monthly usage allowance; Plus €18/month with 3x the Basic allowance; Pro €75/month with 13x the Basic allowance; Team €125/month for 3 seats then €37 per extra seat with 9x the Basic allowance per seat; Organization €150 per seat per month with Pro usage limits. Paid plans can purc
Starter: $39/month (1 to 3 people asking most days); Pro: $119/month (up to 10 people asking most days); Team: $299/month (up to 30 people asking most days); Enterprise: pricing by contract, invoiced yearly. All plans include 14 days free trial with no card required.
Key features
Semantic search across 40 million biomedical papers
Full-text reading and citation tracking
Trust Index for result reliability screening
Research landscape and concept mapping
Zotero library integration
Weekly research digest and personalized feed
PDF and Word report export with citations
Mechanistic links and hypothesis generation
Saved clusters for organizing research
Works in Slack threads with real-time progress updates
Connects to Slack, GitHub, and third-party tools via APIs
Scheduled automated tasks
Learning memory of procedures and customer data
Isolated execution environment with keys kept outside
Full audit log of all actions
Granular tool access control
Bring your own AI model option
Ready-made connectors for Linear, Notion, HubSpot, Stripe, Sentry
Usage allowance shown as share, not tokens or bills
What makes it different
Reads full-text papers instead of just abstracts for comprehensive analysis
Every claim grounded in verified citations with evidence-typed sources
Monitors when literature moves on and notifies users of updates
Constrained reasoning engine reduces AI hallucinations through literature grounding
Biology-native evidence engine with knowledge graphs for semantic understanding
Learns from each task to reduce setup time on subsequent requests
No engineer required for setup—browser-based configuration
Security-first design with sandboxed execution and audit trails
Medians 20x faster than manual work for typical tasks