Conversion Arcana is the planned extraction and transformation service for documents, HTML, Markdown, office files, and media-derived text. It grew from the need to move rich-md-html style conversion into a shared service that Verdicus, Transcribator, Datarim, and publishing workflows can reuse.
Planned capabilities
- Markdown, HTML, and rich-document conversion pipeline
- Format-preserving document extraction for translation workflows
- Shared conversion API for product backends and agents
- Batch jobs with retry classification and audit trail
- Future hooks for OCR and media-derived text
Current autonomy level
L0
Weakest link
The conversion layer is not yet a standalone service; consumers still carry local conversion code or skip rich-format support.
Roadmap to L3
- Extract the first shared conversion API from existing rich document workflows.
- Add queue-backed batch conversion with classified failures.
- Publish integration contracts for Verdicus, Datarim, and content publishing.
Next step
Review the plan and future launch gates
PLANNING does not mean availability or active development. The roadmap above is the next reference; no launch date is claimed.
Review the path to the target level