System Workflows

This document outlines the vital data pipelines and chronological component interactions driving the Wordloop platform.

1. Asynchronous Meeting Transcription

The primary async pipeline: triggering when a user uploads audio, terminating when semantic models output transcriptions.

[!IMPORTANT] The ML service updates state linearly via PATCH /transcriptions/:id callbacks back to the Core. The Core remains the ultimate source of truth.

2. Real-Time WebSocket Streaming

The synchronous, real-time audio pipeline used for native platform recording.

3. Voice Context Pipelines

Workflows for orchestrating speaker identity, embeddings, and context.

[!NOTE]
Vector matching operations are computationally intensive. The frontend must expect varying latency when querying nearest neighbors.

4. AI Chat Context Orchestration

Retrieving meeting context for intelligent conversational RAG queries.