The root cause of every incident, in minutes.
Relay investigates incident tickets across AWS and Azure, read-only, and gives your engineers a root cause report with the evidence behind every finding.
- Read-only in customer accounts
- Every claim cites evidence
- People approve changes
- Ticket TKT-1042Checkout API returning 503s
- EnvironmentPayments production · ap-south-1
- RoutedRelay AWS Investigator · high confidence
- InvestigatingLooking for recent changes in CloudTrail
The 14:02 deploy set the service's task count to zero, so the load balancer had no healthy targets. Rolling back restores capacity.
CloudTrail
CloudWatch
Amazon ECS- Amazon Bedrock AgentCore
- AWS DevOps Agent
- Amazon CloudWatch
- AWS CloudTrail
- Amazon DynamoDB
- Amazon Cognito
Amazon Bedrock AgentCore
AWS DevOps Agent
Amazon DynamoDB
Amazon Cognito- Specialist agents
- 5
- Read-only investigation tools
- 50
- MCP integrations
- 4
- Clouds in one flow
- 2
From ticket to report, the same way every time.
The flow runs on its own for every ticket. Watch each step live, or come back to the finished report.
- 1
A ticket arrives
From DevRev or the console. Relay opens a case and starts the run in the cloud.
- 2
Relay finds where to look
It matches the ticket to the right customer environment, and asks one clear question when it cannot tell.
- 3
Specialists investigate
Read-only agents check alarms, metrics, logs and recent changes in AWS or Azure.
- 4
You get the root cause
A report with the cause, its confidence and the evidence behind every claim, posted to the ticket.
Built for the engineers who own the pager.
Relay does the first hour of an investigation and leaves the decisions to your team.
Grounded, not guessed
Every claim cites a tool result. A second pass looks for evidence against the cause before the report is posted.
AWS and Azure in one flow
The same intake, routing and report for both clouds, each case pinned to the environment it belongs to.
Managed agents on demand
AWS DevOps Agent and Azure SRE Agent take over when Relay's own investigation is inconclusive.
People stay in charge
Anything that would change production goes to an on-call approver first. Their reply resumes the run.
Every step is visible
Each tool call streams to the console as it happens, from the first check to the final report.
Quality you can measure
Engineers rate each report against the real cause, so accuracy, speed and cost are tracked per agent.
Secure by design, from the first call.
Relay reads; it does not change. Access is scoped to one environment per case, and every action leaves a record. It runs in your own AWS account.
Read-only by design
Agents use read-only roles and allow-listed tools. Nothing they call can change a customer's account.
No standing credentials
Relay assumes a role each customer deploys, per case. Secrets stay in AWS Secrets Manager.
Everything is audited
Every sign-in, change and agent action is recorded and archived with S3 Object Lock.
Enterprise sign-in
Amazon Cognito with multi-factor authentication, Microsoft sign-in and role-based access.
Give your next incident a head start.
Sign in with your work account. Your Relay admin decides what you can see and do.