Skip to main content

C4 Model - Level 1: System Context

System Context Diagram

System Context Narrative

Primary Actor: Content Creator

The Content Creator is the main user who initiates the pipeline by providing a video URL. This could be:

  • A software engineer wanting to document technical talks
  • A researcher processing lecture videos
  • A technical writer generating documentation from demos

Secondary Actors

Knowledge Worker

Consumes the generated artifacts (executive summaries, glossaries) for:

  • Quick understanding of video content
  • Research compilation
  • Knowledge base building

Developer

Uses technical artifacts (SDD, TDD, ADR, C4 diagrams) to:

  • Understand system architecture
  • Implement similar patterns
  • Generate project documentation

External System Relationships

External SystemPurposeData Flow
YouTube/VimeoVideo sourceOut: URL, In: Video file + metadata
OpenAI APISpeech-to-text transcriptionOut: Audio, In: Transcript
Anthropic APIVision analysis, LLM generationOut: Images/Prompts, In: Analysis/Text
Serper APIWeb search for context expansionOut: Queries, In: Search results

System Boundary

The Video-to-Knowledge Pipeline encapsulates:

  1. Video download and preprocessing
  2. Audio extraction and transcription
  3. Frame sampling and deduplication
  4. Vision-based content analysis
  5. Content synthesis and chunking
  6. Multi-format artifact generation
  7. Document inventory management

The system does NOT include:

  • Long-term video/audio storage (ephemeral processing)
  • User authentication/authorization
  • Real-time collaboration features
  • Custom ML model training

Key Scenarios

Scenario 1: Technical Talk Processing

  1. User provides YouTube URL of conference talk
  2. System downloads video (15 min, 1080p)
  3. Extracts audio → transcribes to 2,500 words
  4. Samples 450 frames → deduplicates to 120 unique
  5. Analyzes unique frames for diagrams/code
  6. Generates SDD, TDD, ADR, C4 diagrams
  7. Outputs structured documentation package

Scenario 2: Tutorial Video Processing

  1. User provides Vimeo URL of software tutorial
  2. System processes video with screen recordings
  3. Higher deduplication threshold for static screens
  4. Emphasizes UI component detection
  5. Generates step-by-step outline + architecture docs

Data Sensitivity

Data TypeSensitivityHandling
Video contentMediumEphemeral, deleted after processing
TranscriptsLowStored as output artifacts
API keysHighEnvironment variables only
Search queriesLowMay be logged for debugging