Azure AI Foundry integration

01 — Permissions

When connected, Hyperpriors is limited to the following — declared up front, revocable at any time. Scope is granted during provisioning, not by a button on this page.

01
Route agent requests to model deployments on Azure AI Foundry through the Hyperpriors harness
02
Run evaluation suites against specific Foundry deployments and model versions
03
Enforce guardrail policies on Foundry inputs and outputs at runtime
04
Record traces, token usage, cost, and latency for every Foundry call

02 — Details

Built by: Microsoft
Website: azure.microsoft.com (opens in new tab)
Category: Cloud AI platform
Docs: learn.microsoft.com/azure/ai-foundry (opens in new tab)

03 — Notes

About Azure AI Foundry

Azure AI Foundry is Microsoft’s enterprise platform for building, deploying, and governing AI applications on Azure. Its model catalogue includes the Azure OpenAI models alongside models from Meta, Mistral AI, Cohere, and others, served through managed deployments. The platform inherits Azure’s enterprise controls — Microsoft Entra ID for identity, role-based access control, network isolation, and Azure Monitor for platform telemetry — which is why many organisations designate it as their approved route to production model access.

What the integration does

Hyperpriors treats Azure AI Foundry as a model platform behind the harness. Agent requests are routed to Foundry deployments with centrally configured retries, timeouts, and fallback behaviour, so moving between models in the catalogue is a configuration change rather than a code change.

Evaluation suites target specific deployments and model versions. When Microsoft retires a model version or a new one becomes available, you rerun the same suites and compare results before anything changes in production. Guardrails inspect prompts and responses at runtime, and every call is recorded with full trace context — agent, step, tools, cost, and latency.

Your Azure governance is unaffected. Entra ID, RBAC, and network policies continue to control access as before; Hyperpriors adds the model-level layer — evaluation gates, behavioural guardrails, and per-call traces — that sits alongside the platform’s own controls.

Get started

Connect your Azure credentials from the Hyperpriors dashboard, or contact us to talk through your deployment.