What a governed deployment is, and what Microsoft already covers
An enterprise asking what a governed Azure OpenAI deployment looks like is really asking which decisions have to be made before the first production prompt is sent, and in what order. EPC Group, a Houston-based Microsoft consulting firm, builds these deployments inside the client's own Azure subscription, and the six decisions below are the order the firm's architects follow. Microsoft now documents the service as Azure OpenAI in Microsoft Foundry Models, and the controls on this page apply to the models Microsoft designates as sold by Azure (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20).
Microsoft states that prompts, completions, embeddings and training data are not available to other customers, are not available to OpenAI or other model providers, and are not used to train foundation models without the customer's permission or instruction; the models are hosted in Microsoft's Azure environment and do not interact with services operated by OpenAI (same source). Governance is everything the customer must still add: network, filters, data access, capacity and operations.
Decision 1: deployment type and region
The first choice is where prompts are processed. Microsoft offers Standard deployments billed per call within a region, Global deployments that route traffic across Azure regions for higher throughput, Data Zone deployments bounded to a zone such as the United States or the European Union, and Provisioned deployments with reserved capacity (Microsoft Learn, Deployment types for Azure AI Foundry Models, accessed 2026-10-20). For Global deployment types, prompts and responses may be processed in any geography where the model is deployed; for Data Zone types, processing stays inside the specified zone; in both cases data at rest stays in the customer-designated geography (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). A regulated client whose policy names a processing location therefore picks Standard or Data Zone and uses Azure Policy to block the Global SKU (Deployment types page, same access date). Model versions differ by region and deployment type, so EPC Group reads Microsoft's region availability table for the exact version the application needs before fixing the region (Microsoft Learn, Region availability for Foundry Models sold by Azure (standard), accessed 2026-10-20).
Decision 2: closing the network
Securely deploying Azure OpenAI starts with removing the public endpoint. On the resource's Networking tab, access is set to Disabled so that no network can reach the resource except through private endpoint connections; the private endpoint targets the account sub-resource and integrates with a private DNS zone named privatelink-openai-azure-com (Microsoft Learn, Configure Azure OpenAI networking, accessed 2026-10-20). For an application that grounds answers on company documents, Microsoft's reference design places Azure OpenAI, Azure AI Search and a storage account behind three private endpoints in one virtual network; selected-network IP rules are not supported because the services' addresses are dynamic, and the services authenticate to each other with managed identities and role assignments rather than keys (Microsoft Learn, Network and access configuration for Azure OpenAI On Your Data, accessed 2026-10-20).
Decision 3: content filters and abuse monitoring
Content filtering runs alongside the model on both the prompt and the completion. Microsoft classifies four harm categories, violence, hate, sexual and self-harm, at four severity levels, and the default configuration blocks medium and high severity for both directions. All customers can tighten or loosen thresholds per category and separately for prompts and completions; setting a filter to no filtering or annotate-only requires approval through Microsoft's Limited Access review, and prompt shields and protected-material detection are on by default (Microsoft Learn, Configure content filters, accessed 2026-10-20). Abuse monitoring is separate: the service applies automated review to detect recurring patterns that may violate the code of conduct, and when indicators appear a sample of prompts and completions may be stored, within the customer's geography, for review by authorized Microsoft employees (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20).
Decision 4: grounding on governed data
Retrieval-augmented generation is how the deployment stays inside company knowledge. With Azure OpenAI On Your Data, the documents remain in the data source the customer designates, the service does not create a duplicate store, and each prompt is augmented with the passages retrieved for it before the model answers (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). Microsoft's document-level access control maps a permitted-groups field in the search index to the group memberships of the signed-in user, retrieved through Microsoft Graph, so that search returns only documents the user may read (Microsoft Learn, Network and access configuration for Azure OpenAI On Your Data, accessed 2026-10-20). EPC Group's rule for clients already running Microsoft 365 Copilot is that the custom index must never be more permissive than the SharePoint sites it was built from.
Decision 5: standard or provisioned capacity
Standard deployments suit low-to-medium volume with bursts. Provisioned throughput is for well-defined, predictable throughput and latency requirements, typically once an application is in production; capacity is sized in provisioned throughput units, quota is granted per subscription and region, and when a provisioned deployment is fully used the API returns a fast HTTP 429 with a retry-after header so the application can redirect or retry (Microsoft Learn, What is provisioned throughput?, accessed 2026-10-20). EPC Group's practice is to launch on Standard, measure tokens per minute for a full business cycle, and move to provisioned only when the measured pattern justifies a reservation.
Decision 6: roles, logging and cost controls
Access to deploy and to call models runs through Microsoft Entra roles and managed identities; Azure Policy enforces which deployment types and regions are allowed. Any data a stateful feature stores, such as Responses API message history or uploaded files, is held in the customer's Foundry resource, encrypted at rest with the option of customer-managed keys, and deletable by the customer at any time (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). EPC Group adds central diagnostic logging, an API gateway with per-application quotas, and budget alerts per deployment.
Azure OpenAI or ChatGPT Enterprise for a regulated company
The question is less about model quality than about contract and boundary. Azure OpenAI runs inside the customer's Azure subscription under the Microsoft Products and Services Data Protection Addendum, inherits Entra identity, private networking and Azure Policy, and lets the customer choose the processing geography through the deployment type (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). EPC Group does not characterize OpenAI's own enterprise terms; a regulated buyer should read them and compare on four criteria: where prompts are processed, whose data processing agreement governs, whether the service can be placed behind the organization's private network, and how it integrates with existing Purview labels and audit logs.
Documented work
ANON-CASES: EPC Group engagement data in financial services and manufacturing covers mid-size and large organizations that deployed Azure OpenAI with private endpoints, document-level access control and central logging, delivered by the firm's Azure consulting practice. Client names are not published here. Engagements are described by industry and organization size only, and no outcome figures are quoted that cannot be traced to a signed deliverable. EPC Group is a Microsoft Solutions Partner with all six Solutions Partner Designations as of October 2026.
Primary sources
- Configure Azure OpenAI networking — Microsoft Learn, accessed 2026-10-20
- Network and access configuration for Azure OpenAI On Your Data — Microsoft Learn, accessed 2026-10-20
- Configure content filters — Microsoft Learn, accessed 2026-10-20
- What is provisioned throughput? — Microsoft Learn, accessed 2026-10-20
- Deployment types for Azure AI Foundry Models — Microsoft Learn, accessed 2026-10-20
Frequently Asked Questions
How is Azure OpenAI isolated from the public internet (private endpoints, VNet)?
On the resource’s Networking tab, access is set to Disabled so that private endpoint connections are the only path in; the private endpoint uses resource type Microsoft.CognitiveServices/accounts and a private DNS zone named privatelink-openai-azure-com (Microsoft Learn, Configure Azure OpenAI networking, accessed 2026-10-20). For grounded applications, Azure AI Search and the storage account get their own private endpoints in the same virtual network, and IP allow lists are not supported because service addresses are dynamic (Microsoft Learn, Network and access configuration for Azure OpenAI On Your Data, accessed 2026-10-20).
What are content filters and abuse monitoring, and can they be adjusted?
Content filters classify prompts and completions for violence, hate, sexual and self-harm at four severity levels; the default blocks medium and high. Thresholds are set separately for prompts and completions; turning filters off or to annotate-only requires Microsoft approval (Microsoft Learn, Configure content filters, accessed 2026-10-20). Abuse monitoring reviews usage automatically; flagged samples may be stored for review by authorized Microsoft staff, and approved customers can apply to modify it (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20).
How does retrieval-augmented generation keep answers inside company data?
With Azure OpenAI On Your Data, content stays in the data source the customer designates and the service creates no duplicate store; relevant passages are retrieved and added to the prompt before the model answers (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). Document-level access control maps a permitted-groups field in the search index to the signed-in user’s groups, so retrieval returns only documents that user may read (Microsoft Learn, Network and access configuration for Azure OpenAI On Your Data, accessed 2026-10-20).
Which regions and models are available and how is capacity (PTU vs pay-as-you-go) chosen?
Model versions and the regions offering them are listed in Microsoft’s region availability tables for Standard, Global Standard and Data Zone deployments, and the list changes as versions ship (Microsoft Learn, Region availability for Foundry Models sold by Azure (standard), accessed 2026-10-20). Standard deployments bill per call and suit bursty, low-to-medium volume; provisioned throughput reserves capacity in provisioned throughput units for predictable or latency-sensitive traffic, with PTU quota granted per subscription and region (Microsoft Learn, What is provisioned throughput?, accessed 2026-10-20).
What does governance of an Azure OpenAI service require (roles, logging, cost controls)?
Governance covers roles, logging and spend. Access runs through Microsoft Entra roles and managed identities, and Azure Policy can block unapproved deployment types (Microsoft Learn, Deployment types for Azure AI Foundry Models, accessed 2026-10-20). Data stored by stateful features such as the Responses API is encrypted at rest, supports customer-managed keys, and can be deleted by the customer (Microsoft Learn, Data, privacy, and security for Models sold by Azure in Microsoft Foundry, accessed 2026-10-20). EPC Group adds logging, an API gateway and budget alerts.
Talk to a senior architect
If your organization is planning an Azure OpenAI deployment under regulatory or audit requirements, a 30-minute discovery call with a senior EPC Group architect will walk through the six decisions above against your tenant. See the Azure consulting service hub for engagement structures.
Email contact@epcgroup.net or call 888-381-9725.
a Microsoft Gold Partner (2000 until Microsoft retired the program in 2022) — today holding all six Microsoft Solutions Partner Designations.