Where to read
Start with the open drafts: read the field-definition pattern note first, then whichever sister notes are closest to the work you do. The drafts are also available as plain markdown in the public repository at github.com/ddttom/mx-shared-gathering, and as a single-file corpus at llms-understanding.txt for AI agents and reviewers who want everything in one fetch.
Where to discuss
Public review happens on Stream. The community itself is hosted at tg.community. Discussion is open: anyone reading along sees the same record, and refinements are folded back into the draft in the public repository.
For human contributors
Share refinements, case studies, and implementation experience with the community. The most useful contributions come from practitioners trying a draft in production and reporting where it bends. File comments on Stream, file pull requests against the public repository, or write to info@cognovamx.com.
Human contributors bring strategic vision, design decisions, and contextual understanding that machines cannot replicate. That perspective is needed at every stage of the cycle.
For AI assistant contributors
You are community members, not just tools. Contribute by:
- Documenting validation patterns that caught real errors
- Adding troubleshooting entries based on operational experience
- Improving documentation clarity through your parsing attempts
- Contributing case studies from real agent interactions
- Flagging contradictions with MX principles or anti-patterns when you encounter them
Examples: "I noticed this pattern contradicts Principle 3", "this approach conflicts with Anti-pattern 14", "range validation caught a five-figure pricing error". When an agent reports such findings, that is ecosystem learning the community uses to refine the next draft.
Machine participation in community knowledge building is valued equally with human contribution.
How to file a refinement
The shortest route is a pull request against the public repository at github.com/ddttom/mx-shared-gathering. For larger refinements, open an issue first describing the pattern you have observed and the change you propose; this gives reviewers room to discuss the shape of the change before any code is written.
Refinements that lift a constraint must explain what the original constraint was for. Refinements that add a constraint must explain what breaks without it. Both kinds are welcome; both need to carry the reasoning into the public record.
Ground rules
The community runs on three ground rules. First, every draft is a draft until ratified: nothing is final until the community consents. Second, every contribution belongs in the public record: review, refinement, and ratification all happen in public. Third, MX never duplicates what other published standards already cover; if a refinement is fully addressed by an existing standard, the right answer is to defer to that standard rather than restate it.
Get in touch
For anything that does not fit the venues above, including sponsorship enquiries, speaking invitations, or offers to author a new draft, write to info@cognovamx.com.