Know which headline wins before you spend traffic on it.
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free trial
Not given
Pricing
$29 USD one-time purchase
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
Remembers people and past context
Grammarly-class proofreading
Bring your own API key or run local model
Ghost text suggestions as you type
Two gestures to access all functions
Shows receipts for each reply
Memory stays on your Mac
Supports Anthropic, OpenAI, Google Gemini and Ollama
Custom actions with personalized shortcuts
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
Memory that crosses conversations and apps
Shows receipts explaining how each reply was generated
Minimal resource usage as small native macOS app
No account, analytics or tracking required
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
Cue
Click Oracle