How do documents enter the SaSame Knowledge Platform?
This workflow makes document intake visible, reversible and consistent across the website, Search API, Knowledge API, MCP and Markdown.
- Collection
- documentation
- Updated
- 2026-07-28
- min read
- 2
- Version
- v1
Documents enter through reviewed CMS edits, provider-neutral AI drafts or controlled migrations, then pass validation, CAS versioning, Markdown projection and receipt generation before public release.
Purpose
This workflow makes document intake visible, reversible and consistent across the website, Search API, Knowledge API, MCP and Markdown.
Method
An operator selects or creates a canonical JSON record. AI-originated input is forced to draft. Reviewers validate content, references, relations, locale and lifecycle state, then publish against the current expected version. The runtime atomically updates external state, writes the Markdown projection and emits a hashed receipt.
Boundary and limitations
No AI provider can publish directly, drafts never enter public HTML, search, sitemap or MCP, and stale expected versions fail with a conflict instead of overwriting newer work.
Examples
1- 01
An AI suggests a research summary; Studio stores version 1 as draft, a reviewer corrects citations, and reviewed publication creates version 2 plus a new receipt.