ReferenceStrong architectural inferencev1.22.1

In plain English

This page is reference material: definitions, schemas, catalogs, templates, and implementation records.

  • Why this matters: AI risk can come from the whole arrangement, not one obvious model.
  • What to look for: data, memory, routes, adapters, tools, evaluators, updates, and rollback paths.
  • Technical version below: the expert terminology remains available and is linked through the glossary.

Reference

schematic · .uai dogfood memory

The package memory points to the evidence, not around it.

AGENTS.md points the receiver into .uai. Long-term memory points into /docs. Source reports remain preserved as reports, while .uai records what was used, where, and why.

The reference section turns the site’s argument into reusable engineering artifacts: terms, threat catalog entries, controls, metrics, schemas, review templates, release history, source integrity, editorial method, and maturity maps.

Core references

Added memory and source-reference guides

New concept map

v1.8.0 report-driven reference

publication-integrity reference

v1.21.4 controlled-evolution reference

v1.21.9 architecture/resource references

v1.22.0 risk-side reference