Know which headline wins before you spend traffic on it.
Stage
Not given
Not given
Founded
2023
Not given
Based in
Not given
Not given
Pricing model
Freemium
Not given
Pricing
Free: $0 forever. Starter: $39 per month ($468 billed yearly). Growth: $99 per month ($1,188 billed yearly). Scale: $279 per month ($3,348 billed yearly). All paid plans include a 14-day free trial of Growth. Founding customers: 50% off first year on paid plans.
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
Drafts help centre articles from code
Flags stale articles on merged pull requests
Generates changelog from merged PRs
Publishes API reference without OpenAPI spec
AI answers on help centre
Imports existing documentation
Integrates with Claude and Cursor via MCP
Links claims back to source code
Draft review before publishing
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
Writes documentation directly from your code, not manual files
Keeps docs accurate by flagging stale articles on each merged PR
Captures real screenshots of your app rather than generic mockups
Generates API reference automatically without an OpenAPI spec
Works with apps built using no-code tools like Lovable, Bolt or v0
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