Explore this system
Step through curated paths without changing the source diagram.
Beat
Next
ReadyChapter 01 / 01
Guided chapter
Diagram guideExplore this system
Inspecting compiled semantics
E ExportT ThemeS Style0 Reset+ Zoom in- Zoom outEsc Close
Find a node
⌕/
No matching nodes
Semantic passport
Verified source
Authored reach
Route probeChoose a start node
Pick two semantic nodes on the diagram
Choose the source, then the destination. Direction matters.
Semantic lensCompare system roles
Choose up to two semantic kinds. One reveals its real traffic; two compare only direct authored relationships.
Choose a kind to inspect its nodes and touching relationships.
Semantic radar
Building overview
Click nodeDrag to pan
Semantic radar needs more MAP space.
Voiceprints and provenance
• Local engine: vectors come back inline from the transcription task (inline_native); any other detector: services/voiceprint_extractor.py on the cpu queue
• Every step writes its own entry through services/file_provenance.record_stage: transcription, diarization, voiceprints, summary, topics, speaker_names
LLM speaker ID is a suggestion, never a write
• Gender/age detection runs first so the LLM has that context
• Confidence-scored suggestions surface for manual approval only — repo-wide rule
Independent fan-out
• Indexing, summarization, and analytics all dispatch right after finalize
• None of them block the speaker-identity chain or each other