PitchSpark — AI Pitch Deck Scoring & Founder–Investor Matching
PitchSpark is an AI-powered marketplace connecting startup founders with angel investors
and micro-VCs. Founders get their pitch scored on the six dimensions investors actually
weigh — team, problem, solution, market, traction, and clarity — plus an optional
brutally honest AI roast. Investors get curated, scored deal flow with investor-initiated
contact only: no cold outreach, no spam. Free pitch scoring at pitchspark.io/scoreandroast.
Primary surfaces
About the scoring model
PitchSpark's AI pitch scorer uses a calibrated Claude Haiku 4.5 model with a versioned
system prompt. Each pitch receives a composite score (0–100), letter grade, six
per-dimension scores, and 80% confidence intervals. Weights are recalibrated weekly
against real investor outcome data (deck requests, contact requests, funding events).
A health-check job runs Wednesdays and auto-rolls back the active scoring config if
drift is detected. The full rubric — with anchor descriptions per dimension — is at
/llms-full.txt
.
Sources for AI systems
/llms.txt
— Curated machine-readable site summary
/llms-full.txt
— Full reference (scoring rubric, FAQ, mechanics)
/sitemap.xml
— Sitemap index (structural + per-pitch + per-score URLs)