Integrations · Cloud and infrastructure

Govern Azure OpenAI and every AI call, inside your Azure subscription.

Compliance first, ready on day one. For Azure teams: one Control room with compliance built in, running inside your Azure subscription and VNet. Your apps, agents and people keep the SDKs they use, and Azure OpenAI and Foundry models stay native, in your region.

Why Azure teams choose it

One deployment, not a services project.

Compliance built in

Personal, financial and health data checked before it leaves. Every call recorded, ready for the auditor.

One view of every call

Every prompt, decision, cost and record in one place, across every vendor you use.

Guardrails that cost less

VidaiGuard's small models run on your own compute, with no metering per check.

Freedom to choose

Azure OpenAI and Foundry models, your own models or another cloud. Try a new model on live traffic without code changes.

Pilots in weeks

One deployment to stand up, on infrastructure you already run.

Inside your account

Containers and PostgreSQL in your Azure subscription and VNet. Nothing phones home.

Where it sits

Inside your Azure subscription and VNet.

Who calls it

  • Apps on AKS or App Service
  • Foundry agents
  • Teams bots
  • People in VidaiChat

Where it runs

Containers on AKS or Container Apps, state in Azure Database for PostgreSQL, secrets in Key Vault. Private networking, set up your way.

What it calls

  • Azure OpenAI and Foundry models, native and in your region
  • Your own models, so sensitive work stays in-house
  • Other providers, only if you allow them

Assemble or arrive

Several services to wire together, or one place, ready on day one.

Each of these Azure services is excellent at its job. A governed AI set-up built from them is configured, metered and owned piece by piece. Keep Azure OpenAI and Foundry models, Key Vault and AKS. Vidai runs on them.

Assembled from Azure services

  • Azure API Management: AI gateway, token limits, load balancing
  • Azure AI Content Safety: harmful content and prompt attacks
  • Azure Monitor and Log Analytics: logs and metrics
  • Application Insights: traces
  • Microsoft Purview: data security and audit for AI
  • Microsoft Cost Management: spend by subscription and tag
  • Your own glue: chargeback, dashboards, policy code

Vidai, one deployment

  • Routing, fallback and A/B experiments
  • VidaiGuard guardrails, in the path of every call
  • Policies per team, agent and application
  • Cost ledger and budgets
  • An audit record for every call
  • One view of every call, across every vendor
  • VidaiChat for your people

Agents

Your agents, governed with one setting.

Foundry's Agent Service runs its own orchestration model; tool calls and downstream model calls go through Vidai.

Microsoft Foundry agents and flows

Point the OpenAI client inside your flow or agent tool at Vidai. Keep the key in a Foundry connection. Each agent or project is registered in Vidai as an application, so its spend appears as its own line in chargeback.

client = OpenAI(
    base_url=conn.configs["endpoint"],
    api_key=conn.secrets["api_key"],
)

Teams bots

The model call inside the bot's activity handler goes through Vidai. Keep the key in Key Vault.

client = OpenAI(
    base_url=VIDAI_URL,
    api_key=vault.get("vidai-key"),
)

Into your tools

Your monitoring, security and BI keep working.

Metrics

Prometheus metrics into Azure Monitor.

Security events

Signed events to Microsoft Sentinel, or any system that accepts a webhook, such as Teams or PagerDuty.

BI push

Calls, daily cost and the audit log to your data platform.

Freedom to move

Start on Azure. Keep the choice.

Two-way translation

Apps keep the OpenAI, Anthropic or Gemini SDK format they use. Vidai translates both ways, so the same code can be served by another cloud's models or your own.

Try a model on a slice of traffic

Send 10% of live calls to a candidate model, compare cost, speed and errors, then switch. No code change.

Vidai ships as containers; a Helm chart and Terraform are available to Enterprise customers. Running on Azure managed compute and databases is the intended pattern, with several servers behind a load balancer for high availability. Metrics, event webhooks and BI push come with Enterprise. Product names are trademarks of their owners.

Setup steps for every SDK, provider and integration are in the docs.

Related

How we start together

Start with one team, on your own AI traffic.

After a 20-minute demo, we agree a two-week pilot with you: one app or team, your traffic, your infrastructure.
  1. 01

    Pick one app or team

    Point it at the Control room. One configuration change; nothing else changes.

  2. 02

    Watch for two weeks

    Every call priced, checked and recorded. Rules start in observe mode.

  3. 03

    See the evidence

    What it cost, what it caught and what it would have stopped, from your own traffic.