AI writing tool for character headcanons and scene ideas
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
Freemium
Not given
Pricing
Free: 50 welcome Sparks for 7 days (up to 5 standard generations). Spark Pack 500: $4.90 (up to 50 standard generations, valid 365 days). Spark Pack Plus 2,000: $14.90 (up to 200 standard generations, 24% less per Spark, valid 365 days).
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
Generate structured headcanon ideas with premise, emotional logic, and scene hooks
Reroll and rewrite generations with 3 Sparks per rewrite
Save and share headcanons through public share links
Preset prompt angles for common fandom scenarios
Control panel for tone, angles, and canon distance customization
Generate multiple tones for the same character premise
Account-based result storage with persistent access after Sparks expire
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
Templates and tone control built specifically for headcanon generation instead of generic chat
Reusable, structured output designed to be saved and shared with fandom communities
Emotional logic and expandable details for turning ideas into finished fic
Specialized for fandom writers with existing character tension and ships
Focused text-based generation rather than image generation
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