Autocomplete and AI assistant for Mac and Windows, built on a private account of your work
Know which headline wins before you spend traffic on it.
Stage
Startup
Not given
Founded
2026
Not given
Based in
AU
Not given
Pricing model
Freemium
Not given
Pricing
Not given
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
Autocomplete with Tab to accept drafts
Error detection and fact-checking
Cross-app integration
Source attribution for every suggestion
Context-aware AI assistance
One-click pause and privacy control
Encrypted data storage
Read-only app connections
Natural writing style matching
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
Finishes sentences from your actual work history and connected files, not generic AI
Shows source for every suggestion so you can verify it before accepting
Catches mistakes and contradictions between what you're writing and your work history
Works inline in the apps you already use without installation
You stay the author with full control over what gets written
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
Opsis
Click Oracle