SYSTEM ARCHITECTURE

Inside the engine.

Multi-agent · orchestrator · explainability · audit · learning

PACCS is a layered intelligence architecture. Specialised agents operate in parallel; the orchestrator resolves divergence; the explainability engine surfaces reasoning; the audit trail makes every decision permanently traceable; the learning loop folds operator feedback back into the corpus.

LAYER 1 · INTAKE
SOURCE

Submission Pipeline

Films arrive through partner festival channels and direct submissions. Metadata, poster, trailer, synopsis ingested.

SIGNAL EXTRACTION

Multi-modal Encoder

Visual language profile, narrative pacing classification, dialogue density, score signature — all captured at ingestion.

CORPUS LOOKUP

Comparable-Film Index

The new submission is positioned in 4,726+ corpus space — identifying nearest neighbours by signal, outcome, and territory.

LAYER 2 · AGENT MESH
AGENT · 01

Narrative Agent

Story structure, dialogue quality, thematic depth, narrative voice. Produces narrative-tier signal with explicit reasoning trace.

AGENT · 02

Visual Language Agent

Cinematography, visual grammar, art direction signature. Compares against 4,726+ visual language vectors in the corpus.

AGENT · 03

Festival Alignment Agent

Programming-pattern matching across 22 anchor festivals, scaling to 200+ through PIFF 2026 partnerships. Submission-window aware. Tier-graded fit signals.

AGENT · 04

Marketability Agent

Audience modeling, distributor fit, territorial release positioning, multi-scenario revenue forecast.

LAYER 3 · ORCHESTRATION
CORE

Consensus Orchestrator

Resolves inter-agent variance. Weights agent signals against historical accuracy. Produces single programming-grade recommendation with confidence.

EXPLAINABILITY

Reasoning Surface

Every score component traces to its source. Every divergence is reported. Every decision is replayable.

OVERRIDE

Human Channel

Always open. Operator decisions are logged, attributed, and folded back into the learning loop.

LAYER 4 · GOVERNANCE
PERMANENT

Audit Trail

Every analysis, override, and learning event recorded. Permanent retention. UK/EU region-locked.

CONTINUOUS

Learning Loop

Operator feedback flows back as labelled training data. Model versioning is staged and roll-backable.

PROVENANCE

Source Citations

Every score traces back to specific corpus records, comparables, and partner-supplied signals. View →

SEE IT RUN

The architecture, in motion.

Live Intelligence Console