Jamdesk Workflow
How to run docs-as-code for Assistiv in Jamdesk, including what can be automated and what still needs authoring.
This page answers two practical questions:
- What does Jamdesk automate today?
- What should our team automate next for full-stack Assistiv docs?
What Jamdesk Automates Now
- Build and deploy on push to the connected branch
- Validation of
docs.jsonand MDX pages during build - AI-ready outputs like
llms.txtand markdown-source page access (.mdURL suffix) - OpenAPI endpoint page generation when an OpenAPI spec is configured
What Is Not Fully Automatic Yet
- End-to-end conceptual documentation generated from all repos with no guidance
- Full architecture narratives and business-context explanations
- Guaranteed accurate cross-repo change logs without a workflow layered on top
Practical Automation Pattern for Assistiv
- Keep this repo as the published source of truth.
- Add a lightweight "docs update required" checklist to each product PR.
- Use AI agents (Codex/Cursor) to draft MDX updates from code diffs.
- Review docs changes in the same PR as code changes whenever possible.
- Introduce OpenAPI specs for backend and Aurora to auto-generate endpoint docs.
Codex-Based Automation Option
Jamdesk documents a Codex workflow using:
- project-level writing rules in
AGENTS.md - optional MCP endpoint config for docs retrieval
- optional
/update-jamdeskskill for automated doc updates
This is currently the fastest path to partial automation without building a custom doc generation pipeline.
Suggested Near-Term Improvements
- Add an OpenAPI export step in CI for backend and Aurora.
- Generate route inventory artifacts on each merge and include doc diff checks.
- Add ownership metadata to docs pages so each section has a maintainer.