Script Intelligence

Predict screenplay flop or hit before a frame is shot.

Score unproduced screenplays against 14 years of theatrical and streaming outcomes. Quantify structural risk, audience fit, and comparable performance before greenlight.

Start free with Script IntelligenceSee pricing

How it works

The exact thing your team is trying to call.

Probability the finished film clears its production budget on first window release, with confidence intervals and the five most predictive script-level drivers.

  • Structural scoring across pacing, conflict density, and act balance
  • Cast-fit projection conditioned on the attached lead and director
  • Genre-conditioned analog search across 18,000 produced scripts
  • Risk-driver explanations grounded in SHAP values, not vibes
  • Greenlight memo export ready for studio committees

Signal sources

What feeds the script intelligence model.

  • 01TMDB and IMDb production metadata
  • 02Box Office Mojo theatrical history
  • 03YouTube trailer reaction signal
  • 04X mentions weighted by author audience
  • 05News RSS coverage volume and sentiment
  • 06Letterboxd and Rotten Tomatoes early reviews
Sample entities tracked:Untitled Nolan 2027Project IrisEchoes of Madurai

Use cases

What teams actually do with Script Intelligence.

  • Greenlight reviews for script intelligence

    Run scoring on a portfolio of candidates and surface the ones whose script intelligence signals diverge most from their internal narrative.

  • Continuous monitoring

    Subscribe via webhook and receive a payload only when the score crosses a threshold you defined. No dashboards required.

  • Cross-vertical analysis

    Pull the same entity into other verticals to see whether the signals agree or disagree. Disagreement is often where the alpha is.

  • Backtesting before commitment

    Score the last 24 months of decisions against the model and compare hit rates. The calibration_bucket field tells you how much to trust the model in the bands you care about.

API

Calibrated, explainable, ready for production.

Every prediction ships with a confidence interval, the top feature drivers explaining the score, and the five nearest historical analogs the model leaned on.

Available via REST and a typed TypeScript SDK.

See full API reference
GET /v1/predictions/script-intelligence/{entityId}
{
  "entityId": "scr_8af21",
  "verdict": "lean_hit",
  "pFlop": 0.18,
  "ci95": [
    0.11,
    0.27
  ],
  "drivers": [
    {
      "feature": "act2_pacing",
      "contribution": -0.09
    },
    {
      "feature": "lead_q_score",
      "contribution": -0.07
    },
    {
      "feature": "genre_saturation_q4",
      "contribution": 0.05
    },
    {
      "feature": "trailer_engagement_index",
      "contribution": -0.04
    },
    {
      "feature": "budget_to_genre_median",
      "contribution": 0.03
    }
  ],
  "analogs": [
    "tt0114369",
    "tt1375666",
    "tt2543164",
    "tt6751668",
    "tt7286456"
  ]
}

Compared to

How Script Intelligence differs from what is already out there.

VendorHow SignalGrid is different
Largo.aiWe expose driver-level explanations and analog films, not just a green or red light.
CinelyticOur model is conditioned on the full open public signal, not only structured studio data.
ScriptBookWe ship calibrated confidence intervals on every prediction.

Try Script Intelligence on your own entities.

Start free during the public beta. We will pre-select script intelligence for you on signup.

Start freeTalk to us

Other verticals