This pitch may have been removed or is no longer available.
We use essential cookies to run PitchSpark and, with your consent, analytics cookies to improve it. See our Privacy Policy.
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.
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 .