docs(architect): weekly KB update — 52 files refreshed (2026-04)

Key content changes:
- MLOps: MLflow 3 scorers expanded (RetrievalRelevance, Fluency, multi-turn judges)
- MLflow 3 A/B eval: mirror_traffic GA confirmed, new scorer catalog
- CI/CD: OIDC auth replaces deprecated --sdk-auth (Azure ML GitHub Actions)
- Agent framework A2A: updated SDK patterns (A2ACardResolver, BearerAuth)
- AG-UI backend tool rendering: accurate TOOL_CALL_* event shapes
- Computer Use agents: US region requirement, credentials patterns
- Purview governance: bulk term edit, expire/delete workflows
- CAF AI Secure: 3-phase structure confirmed current
- Copilot Studio: Claude Sonnet 4.5/4.6 GA, new orchestration controls
- M365 manifest: v1.26 GA (April 2026), copilotAgents node
- Power Platform: agent flow capacity enforcement corrected
- Azure Monitor: Simple Log Alerts GA, AMBA for policy-based alerting
- Security Copilot: SCU capacity model (400 SCU/1000 users)
- EU Data Boundary: all EU + EFTA countries confirmed
- gateway-multi-backend: added 4th topology, subscription-level quota note

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md

@@ -1,6 +1,6 @@
 # A/B Testing and Experimentation for AI Models
 
-**Last updated:** 2026-02
+**Last updated:** 2026-04
 **Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps
@@ -455,14 +455,15 @@ az ml online-endpoint update --name my-endpoint --traffic control=90 challenger=
 # Use RelevanceToQuery, Correctness, custom business scorers
 ```
 
-**MLflow 3 A/B evaluation pattern**:
+**MLflow 3 A/B evaluation pattern** — Verified (MCP 2026-04):
 - Use `mlflow.genai.evaluate()` on traces from each variant
-- Compare scorers: `Correctness`, `RelevanceToQuery`, `ToolCallEfficiency`
+- Compare scorers: `Correctness`, `RelevanceToQuery`, `RetrievalGroundedness`, `ToolCallEfficiency`, `Fluency` — expanded scorer set in MLflow 3
+- Multi-turn scorers available: `ConversationCompleteness`, `UserFrustration` for conversational AI A/B testing
 - Statistical significance: MLflow tracks Cohen's Kappa against human baseline
 - Aliases in Prompt Registry: `@control` and `@challenger` for prompt A/B testing
 
-**Azure ML safe rollout progression**:
-1. **Shadow testing**: Mirror X% of traffic to new model (no user impact)
+**Azure ML safe rollout progression** — Verified (MCP 2026-04):
+1. **Shadow testing**: Mirror X% of traffic to new model (no user impact) — natively supported via `mirror_traffic` property on managed online endpoints
 2. **Canary**: Route 10% live traffic, monitor bake time (hours/days)
 3. **Progressive**: 10% → 50% → 100% with health gate at each step
 4. **Rollback trigger**: Automatic halt on health signal degradation