Integrations
Inside your cloud. Plugged into what you run.
Vidai runs on the cloud or servers you already use, and governs the AI calls between your apps and your models. Your security, sign-in, finance and data tools keep working, with Vidai's records added.
Cloud and infrastructure
Runs where you run.
AWS
EKS or ECS with RDS for PostgreSQL. Bedrock models, in your region.
AWS →Azure
AKS or Container Apps. Azure OpenAI and Foundry models, in your region.
Azure →Google Cloud
GKE or Cloud Run with Cloud SQL. Vertex AI and Gemini, in your region.
Google Cloud →Your data centre
Standard containers and PostgreSQL on servers you own.
Your data centre →Air-gapped
Fully offline. The licence is checked offline and nothing phones home.
Air-gapped →Your tools
Plugs into what you already run.
Security monitoring (SIEM)
Blocks, refusals and changes stream as signed events to the SIEM your team already watches.
Security monitoring (SIEM) →Company sign-in (SSO)
People sign in with your identity provider, and their teams and roles follow.
Company sign-in (SSO) →Finance and billing
Cost exports, markups and locked billing periods your finance systems can check.
Finance and billing →Data platform and monitoring
Calls, cost and the audit log to your warehouse; metrics to your dashboards.
Data platform and monitoring →SDKs, frameworks and tools
OpenAI, Anthropic and Gemini SDKs, agent frameworks, MCP-enabled apps, coding tools, notebooks and chat clients connect with one configuration change. With MCP, the tools an app offers a model, and what they return, are checked like any other content.
How we start together
Start with one team, on your own AI traffic.
- 01
Pick one app or team
Point it at the Control room. One configuration change; nothing else changes.
- 02
Watch for two weeks
Every call priced, checked and recorded. Rules start in observe mode.
- 03
See the evidence
What it cost, what it caught and what it would have stopped, from your own traffic.