v1 — public beta

Predict outcomes before they happen.

Calibrated against real evidence, not vibes. SignalGrid scores catalogue entities with 40 realistic KPIs (each with a confidence chip) and scores unseen screenplays with a 200-parameter predictive engine. Two engines, one entity graph, ten verticals.

Start free Watch demo

10verticals

19source connectors

40realistic KPIs

200predictive parameters

GET /v1/catalogue/script-intelligence/film_kj91 — 40 realistic KPIs

{
  "entityId": "film_kj91",
  "title": "Soorarai Pottru",
  "vertical": "script-intelligence",
  "kpiCountScored": 40,
  "kpis": [
    { "id": "theatrical_roi",         "value":  2.40, "confidence": "high",   "citations": 3 },
    { "id": "critic_audience_delta",  "value": -0.18, "confidence": "high",   "citations": 12 },
    { "id": "controversy_index_30d",  "value":  0.07, "confidence": "medium", "citations": 4 },
    { "id": "comparable_film_lift",   "value":  0.31, "confidence": "medium", "citations": 6 },
    { "id": "music_director_lift",    "value":  0.22, "confidence": "low",    "citations": 2 }
  ],
  "decodeReportRef": "report_v2_film_kj91",
  "asOf": "2026-05-10T00:00:00Z"
}

POST /v1/predict/script-intelligence — 200-parameter prediction

{
  "entityId": "scr_8af21",
  "vertical": "script-intelligence",
  "verdict": "lean_hit",
  "parameterCountScored": 200,
  "pFlop": 0.18,
  "ci80": [0.12, 0.25],
  "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_idx", "contribution": -0.04 },
    { "feature": "budget_to_genre_median", "contribution":  0.03 }
  ],
  "analogs": ["tt0114369", "tt1375666", "tt2543164", "tt6751668", "tt7286456"],
  "asOf": "2026-05-10T14:00:00Z"
}

Catalogue calls return 40 realistic KPIs with a confidence chip per KPI (high / medium / low / unknown) so thin-evidence entities surface honestly. Upload calls add a 200-parameter predictive score with confidence intervals, top drivers, and nearest historical analogs.

Trusted by teams making decisions on incomplete information

Ten verticals, one platform

One signal layer. Ten domains where predictions move money.

How it works

Ingest signals. Resolve entities. Predict outcomes.

Step 1

Ingest signals

Continuous ingestion across news RSS, social platforms, video, search trends, and public marketplaces. Deduped, enriched, and timestamped at the edge.

Step 2

Resolve entities

Every signal is grounded to a stable entity in our knowledge graph: a film, a candidate, a SKU, a creator. Cross-source coreference happens before scoring.

Step 3