AI research assistant that grounds every claim in real, peer-reviewed citations
Know which headline wins before you spend traffic on it.
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Not given
Pricing
Student plan: $9.99/month (verified academic email); Pro annual: $12.99/month billed annually ($155.88 once a year); Pro monthly: $25.99/month. Citation Finder is free.
Free: $0/month with 5 rankings and 60 Claude-written options monthly. Creator: $19/month with 100 rankings and 2,500 options. Pro: $49/month with 600 rankings and 6,000 options. Agency: $149/month with 3,000 rankings and 20,000 options.
Key features
Search-first methodology across 200M+ peer-reviewed academic papers
Verifiable DOIs on every citation
Transparent paper list per draft
Multi-language drafting in 11 languages including Arabic RTL
Support for APA, MLA, Chicago, Harvard, IEEE citation styles
Export to DOCX, Markdown, and LaTeX formats
Live retrieval across 200M+ academic papers
Real-time access to latest research
Intent Analysis and Deep Scholarly Query
Head-to-head comparison of up to 200 variants
Bradley-Terry model ranking with calibrated odds
Honest uncertainty verdicts: Clear, Lean, Too close to call
Brand profiles to calibrate accuracy on your audience
Works for YouTube titles, subject lines, ad headlines, and article headlines
Accuracy measured on 9,841 held-out A/B tests
What makes it different
Uses search-first methodology to query live academic databases before writing, avoiding hallucinated citations
Every citation includes a clickable DOI link for immediate verification
Supports 11 languages with automatic citation formatting across different language styles
Designed specifically for academic integrity with transparent source auditing
Exports ready-to-submit documents with formatted citations in multiple styles
82% accuracy on clear calls, trained on thousands of real A/B tests never seen during tuning
Honest about uncertainty instead of always crowning a winner
56 times cheaper than Claude Sonnet while maintaining comparable accuracy
Custom calibration to your audience's behavior via brand profiles
Compare versions in both orders to cancel out model bias