
Agents5 min read
Advanced guideBind approval to a concrete action, enforce authorization at execution, make retries idempotent, and recover multi-step workflows without inventing an exactly-once guarantee.
Documentation checked↗

Azure AI5 min read
Advanced guideTrace inbound access, agent outbound traffic, hybrid DNS, and external tool destinations as independent controls, then test failure and recovery paths.
Documentation checked↗

Azure AI7 min read
Advanced guideSeparate caller authorization, backend identity, semantic-cache isolation, token budgets and private connectivity in Azure API Management.
Documentation checked↗

Detection & response5 min read
Advanced guideDesign a telemetry contract that preserves authorization and action evidence, limits prompt capture, protects trace content, and tests leakage across logging paths.
Documentation checked↗

Adversarial testing7 min read
Advanced guideTurn a threat model into repeatable Foundry adversarial tests, calibrate AI graders, protect evaluation data and define honest release criteria.
Documentation checked↗

Retrieval & data security5 min read
Advanced guideSeparate ingestion and serving authority, close Shared Key and anonymous paths, constrain SAS use, and validate Blob and Data Lake access independently.
Documentation checked↗

Governance5 min read
Advanced guideVersion the model-facing release as a complete manifest, verify artifact identity and provenance, isolate deployment authority, and rehearse rollback without trusting mutable tags.
Documentation checked↗

Identity & authorization5 min read
Advanced guideSeparate human, service-principal, managed-identity, and preview agent policy boundaries; validate token acquisition and resource enforcement independently.
Documentation checked↗

Identity & authorization7 min read
Advanced guideSeparate user delegation from application authority, validate token boundaries, and prevent an agent from turning an authorized session into an unauthorized action.
Documentation checked↗

Azure AI5 min read
Advanced guideSeparate secret replacement from cryptographic key rotation, verify consumer adoption, and recover vault dependencies without losing access to protected data.
Documentation checked↗

Agents7 min read
Advanced guideDesign per-request authorization, tool admission, downstream identity and consequential-action approval for remote MCP integrations with Microsoft Foundry.
Documentation checked↗

Identity & authorization5 min read
Advanced guideDesign PIM activation, resource scope, approval evidence, and emergency recovery around the permissions that can change models, data, identities, and telemetry.
Documentation checked↗

Microsoft 365 Copilot5 min read
Advanced guideDistinguish source permissions, label encryption, DLP processing restrictions, prompt controls, and investigation access using a workload-specific test matrix.
Documentation checked↗

Retrieval & data security7 min read
Advanced guideChoose between application security filters and native preview permissions, preserve access metadata on chunks, and enforce the same boundary across keyword and vector retrieval.
Documentation checked↗

Retrieval & data security7 min read
Advanced guideSeparate source access from content trust, preserve provenance through chunking, and verify publication, deletion, and rollback without assuming a prompt filter proves integrity.
Documentation checked↗

Detection & response7 min read
Advanced guideBuild defensible AI investigations with stable identity keys, explicit event grain, ingestion-aware scheduling, controlled joins and validated alert behavior.
Documentation checked↗

Detection & response5 min read
Advanced guideTest schema assumptions, event semantics, ingestion timing, join behavior, scheduling, entity mapping, and analyst outcomes before promoting a hunt into a detection.
Documentation checked↗

Identity & authorization7 min read
Advanced guideDesign issuer, subject, audience, and resource-permission boundaries so secretless deployment and runtime identities remain narrowly authorized.
Documentation checked↗
Each guide separates product behavior, architectural recommendations and test evidence. Check its prerequisites and preview limitations before applying an example.