Integrations · Cloud and infrastructure

Govern Bedrock and every AI call, inside your AWS account.

Compliance first, ready on day one. For AWS teams: one Control room with compliance built in, running inside your AWS account and VPC. Your apps, agents and people keep the SDKs they use, and Amazon Bedrock models stay native, in your region.

Why AWS 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

Amazon Bedrock 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 AWS account and VPC. Nothing phones home.

Where it sits

Inside your AWS account and VPC.

Who calls it

  • Apps on EKS or ECS
  • Bedrock Agents
  • Lambda functions
  • People in VidaiChat

Where it runs

Containers on EKS or ECS, state in Amazon RDS for PostgreSQL, secrets in Secrets Manager. Private networking, set up your way.

What it calls

  • Amazon Bedrock 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 AWS services is excellent at its job. A governed AI set-up built from them is configured, metered and owned piece by piece. Keep Bedrock models, Secrets Manager and EKS. Vidai runs on them.

Assembled from AWS services

  • Amazon API Gateway: front door, keys and throttling
  • Amazon Bedrock Guardrails: content filters, sensitive data, prompt attacks
  • Bedrock invocation logging: prompts and responses to S3 or CloudWatch
  • Amazon CloudWatch: logs, metrics and alarms
  • AWS CloudTrail: API activity for audit
  • AWS Cost Explorer: spend by tag and inference profile
  • Your own glue: routing, chargeback, dashboards

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.

Bedrock Agents run their orchestration model on Bedrock; action-group Lambdas and downstream model calls go through Vidai.

Bedrock Agents

The model call inside each action-group Lambda goes through Vidai. Keep the key in Secrets Manager. 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=os.environ["VIDAI_BASE_URL"],
    api_key=os.environ["VIDAI_API_KEY"],
)

Apps on Lambda, ECS and EKS

Any service that calls a model points its SDK at Vidai. Same code, one setting.

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

Into your tools

Your monitoring, security and BI keep working.

Metrics

Prometheus metrics into Amazon Managed Service for Prometheus.

Security events

Signed events to your SIEM, or any system that accepts a webhook, such as Slack or PagerDuty.

BI push

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

Freedom to move

Start on AWS. 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.

The Amazon Bedrock provider is in alpha: tested end to end, with known gaps. Vidai ships as containers; a Helm chart and Terraform are available to Enterprise customers. Running on AWS 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.