Playbook · Azure AI Foundry11 min read

Azure AI Foundry Security & Compliance: The complete enterprise configuration guide

Azure AI Foundry inherits Azure's enterprise security posture, but production AI deployments require deliberate configuration across six distinct security layers. The platform gives you the controls — this guide tells you exactly how to configure each one for enterprise compliance. Skipping any layer leaves gaps that will surface in a security audit.

Written by Kovil AI engineers · Updated May 2026

Identity & Access: Managed Identity configuration

The most impactful security decision in any Azure AI deployment is authentication method. API keys stored in environment variables or Key Vault references are auditable but still represent a credential that can be leaked, rotated incorrectly, or shared across environments. Managed Identity eliminates the credential entirely — the Azure runtime handles identity, and access is controlled through Entra ID RBAC.

API key approach (avoid in production)

  • Key stored in Key Vault or environment variable
  • Single key shared across application instances
  • Manual rotation process with deployment risk
  • No per-identity audit trail
  • Key compromise requires immediate rotation across all consumers

Managed Identity (correct approach)

  • Zero credentials stored anywhere
  • System or user-assigned identity per service
  • Automatic rotation — no key management overhead
  • Per-identity audit trail in Azure Monitor
  • Compromise of one identity does not affect others

The RBAC role assignments that matter for a typical Azure AI Foundry deployment are precise. Assigning too broad a role (Contributor at subscription scope) is a common shortcut that fails security audits. Assign the minimum required role at the minimum required scope:

Azure OpenAI

Resource level (not resource group)

Cognitive Services OpenAI User

Allows inference calls; does not allow model deployment or resource configuration.

Azure AI Search

Resource level

Search Index Data Reader

Read-only access to indexes. Use Search Index Data Contributor only for indexer identity.

Azure Storage

Container level

Storage Blob Data Reader

Scoped to the specific container holding your documents, not the entire storage account.

Azure Key Vault

Secret level where possible

Key Vault Secrets User

Allows reading specific secrets. Never assign Key Vault Administrator to an application identity.

Azure ML Workspace

Workspace level

AzureML Data Scientist

For Prompt Flow evaluation runs. Does not allow compute provisioning or workspace configuration changes.

Network isolation: Private endpoints

Private endpoints are the network-layer control that prevents any AI traffic from traversing the public internet. Every Azure service in your AI stack — Azure OpenAI, Azure AI Search, Azure Storage, Azure Key Vault — should be deployed with a private endpoint for production workloads handling sensitive data. This is a non-negotiable control for HIPAA, PCI DSS, and most enterprise security frameworks.

Architecture principle

Every AI service should be deployed with “Public network access: Disabled”. Traffic flows: Application (ACA/AKS/VM) → Private Endpoint → Azure Service. No traffic takes a public path. DNS resolution for service endpoints is handled by a Private DNS Zone linked to your VNet — not the public DNS records that resolve to public IP addresses.

Azure OpenAI

  1. 1.Create private endpoint in your VNet subnet
  2. 2.Associate with Private DNS Zone: privatelink.openai.azure.com
  3. 3.Set public network access to Disabled on the resource
  4. 4.Update application to use the private FQDN

Azure AI Search

  1. 1.Create private endpoint for search service
  2. 2.Associate with Private DNS Zone: privatelink.search.windows.net
  3. 3.Disable public access on the search service
  4. 4.Configure indexer to run within the VNet using Shared Private Link

Azure Storage (documents)

  1. 1.Private endpoint per storage service (Blob, File separately)
  2. 2.Private DNS Zone: privatelink.blob.core.windows.net
  3. 3.Disable public blob access at account level
  4. 4.Storage firewall: deny all, allow VNet subnet

Azure Key Vault

  1. 1.Private endpoint in same subnet as application
  2. 2.Private DNS Zone: privatelink.vaultcore.azure.net
  3. 3.Key Vault firewall: deny all public access
  4. 4.Allow Azure Monitor service tag for diagnostic logs

Data governance: What Azure AI logs

Understanding exactly what Azure AI services log — and where those logs go — is a prerequisite for data governance compliance. The default logging configuration is not always appropriate for regulated data, and several logging capabilities require explicit opt-in or opt-out decisions.

ServiceWhat is logged by defaultPII riskAction required
Azure OpenAIRequest metadata (timestamp, token counts, model, latency)Low — prompt content NOT logged by defaultEnable diagnostic logs to Log Analytics; verify content logging is off
Prompt FlowFlow run metadata, step-level latency, evaluation scoresMedium — flow inputs/outputs can be capturedReview trace settings; mask PII fields before trace capture
Azure AI SearchQuery text, result count, latencyHigh — query text may contain PIIEnable slow query logging to Log Analytics with appropriate retention
Azure MonitorAggregated metrics only by defaultLowConfigure resource-level diagnostic settings explicitly

Azure OpenAI content logging opt-in

Microsoft offers an opt-in “abuse monitoring” feature that logs prompt and completion content for safety review. This is OFF by default for most enterprise agreements but should be verified explicitly — especially in HIPAA or data residency-sensitive contexts. Check your Azure OpenAI resource under “Abuse monitoring” in Azure AI Foundry.

Content Safety configuration

Azure AI Content Safety filters inputs and outputs for four harm categories. Default thresholds are generic — production deployments for regulated industries require explicit threshold configuration per deployment, and the configuration must be documented and defensible to auditors.

Hate & Fairness

Default: MediumRecommended: Medium–High

For customer-facing agents, keep at Medium. Internal tools may use High threshold if content policy permits.

Violence

Default: MediumRecommended: Medium–High

Adjust to High for general business use. Health/insurance deployments may require Medium to handle clinical content.

Sexual Content

Default: MediumRecommended: High for enterprise

Enterprise business applications should use High threshold. Adult content platforms require Azure content filtering waiver.

Self-Harm

Default: MediumRecommended: Low for consumer-facing

For any consumer-facing deployment, configure Low threshold and route flagged content to appropriate resources.

Beyond the four harm categories, two additional controls matter for enterprise deployments. Jailbreak detection (Prompt Shield) blocks adversarial prompt injection attempts — this should be enabled on all production deployments. Groundedness detection flags AI responses that make claims not supported by the retrieved context — critical for any compliance or regulated-content use case where hallucination is a business risk.

enable

Prompt Shield (jailbreak detection)

Enable on all deployments. Adds ~30ms latency.

configure

Custom blocklist

Define for domain-specific prohibited terms (competitor names, restricted topics, internal product codes).

enable

Groundedness detection

Enable for any RAG-based agent where factual accuracy is a compliance requirement.

enable

PII entity detection

Enable for customer-facing agents. Configure redaction mode (substitute vs. mask) based on downstream processing needs.

Compliance frameworks

Azure AI Foundry inherits compliance from the underlying Azure services. Each certification has different implications for what you need to configure versus what Microsoft has already done. Understanding these boundaries is critical for audit preparation.

HIPAA

BAA available

What's covered: Azure OpenAI, Azure AI Search, Azure Storage, Azure Monitor are all covered under Microsoft's HIPAA BAA when deployed in a compliant Azure subscription.

Your responsibility: You must sign the BAA (available in Azure portal under Compliance), configure all services with private endpoints (no public access), and ensure PHI is not captured in diagnostic logs. The BAA covers the platform — your application-level PHI handling (logging, caching, display) is your responsibility.

SOC 2 Type II

Covered

What's covered: All Azure AI services are SOC 2 Type II audited. Microsoft publishes the audit report under NDA via the Service Trust Portal.

Your responsibility: Your application code and deployment processes are not in scope of Microsoft's SOC 2. You need your own controls for application-layer access management, change management, and incident response.

ISO 27001

Covered

What's covered: Azure OpenAI and Azure AI Search are ISO 27001 certified. Certificates are available on the Service Trust Portal.

Your responsibility: ISO 27001 requires a complete ISMS covering your organisation. The Azure certification covers the infrastructure layer — you need to demonstrate controls for the application, process, and people layers.

PCI DSS

Qualified

What's covered: Azure is a PCI DSS Level 1 service provider. Payment card data can be processed within Azure boundaries when configured correctly.

Your responsibility: Cardholder data must never enter Azure OpenAI prompts or AI Search indexes. Architect your solution so payment data is tokenised or detokenised outside the AI layer. The Azure PCI attestation does not cover AI workloads that process raw card data.

FedRAMP Moderate

Authorized (Azure Government)

What's covered: Azure Government regions have FedRAMP Moderate authorization. Azure OpenAI is available in Azure Government with FedRAMP coverage.

Your responsibility: Standard Azure commercial regions are not FedRAMP authorized. If your use case requires FedRAMP, you must deploy to Azure Government — verify service availability as not all AI Foundry features are available in Azure Government regions.

Audit & monitoring checklist

This 12-point checklist represents the production security baseline we verify on every Azure AI deployment before go-live. Each item is either a direct audit finding or a prerequisite for passing one.

01

All service-to-service authentication uses Managed Identity — zero API keys in application code or environment variables.

02

RBAC assignments follow least privilege: minimum required role, at minimum required scope (resource level, not subscription).

03

Private endpoints deployed for all AI services (OpenAI, AI Search, Storage, Key Vault). Public network access disabled on each resource.

04

Private DNS Zones configured for each service and linked to the application VNet. Public DNS records resolve to private IPs within the VNet.

05

Azure AI Content Safety thresholds configured explicitly per deployment — not relying on defaults.

06

Prompt Shield (jailbreak detection) enabled on all customer-facing and internal deployments.

07

Azure Monitor diagnostic settings configured for all AI services. Logs route to a dedicated Log Analytics workspace with appropriate retention (90 days minimum; 1 year for regulated industries).

08

PII is identified in the data flow and either masked before it enters LLM context or explicitly confirmed to be compliant with retention requirements.

09

Azure OpenAI content logging (abuse monitoring) opt-in status verified and documented.

10

Prompt Flow evaluation pipeline with a representative test dataset deployed and running on every code deployment. Evaluation scores tracked and alerted on regression.

11

Incident response runbook documented: who is alerted on content safety violations, what the escalation path is, how the agent is disabled if needed.

12

HIPAA BAA (or relevant compliance agreement) signed for the Azure subscription if regulated data is processed. Verified in Azure portal Compliance section.

Key takeaways

  • Managed Identity is not optional for production — it eliminates credential management risk and provides a complete identity-level audit trail.
  • Private endpoints are the baseline network control for any regulated industry deployment. Configure them at the start of the build, not during a security review.
  • Azure AI Content Safety requires explicit threshold configuration — default settings are not a compliance posture.
  • HIPAA BAA, SOC 2, ISO 27001, and FedRAMP coverage applies to the Azure infrastructure layer. Your application controls (logging, access, incident response) are your responsibility.
  • The 12-point audit checklist is the minimum bar. Regulated industries should layer additional controls: immutable audit storage, automated compliance scanning (Defender for Cloud), and quarterly access reviews.
  • Groundedness detection and PII detection should be enabled for any deployment where AI-generated content is consumed by end users without further human review.

Security architecture review

Need a security-first Azure AI deployment?

We configure Managed Identity, private endpoints, Content Safety, and the full compliance stack from day one — so your deployment passes the audit the first time.