Relay
Durable execution for AI agents that take real actions.The runtime behind our agent deployments. Relay runs multi-step agents reliably: tool calls, retries, human approvals and full traces, even when a run takes minutes or days.
- run startedworkflow support.resolve_damaged_item
- ✓ orders.lookup182 ms
- ✓ shipments.track240 ms
- ✓ policy.check replacement_eligiblepassed
- ⏸ approval.request refund ¥12,800 > ¥10,000 limit#support-leads
- ✓ approval grantedafter 3m 12s
- ✓ payments.refundidempotency key r_8f21c:5
- run complete7 steps · 4.1 s active · ¥2.7
- run completion rate
- 99.7%
- run completion rate
- duplicated side effects on retry
- 0
- duplicated side effects on retry
- of actions policy-checked before execution
- 100%
- of actions policy-checked before execution
- registered production tools
- 40+
- registered production tools
Overview
Why we built Relay.
Most agent demos break in production. A tool times out, a model returns something unexpected, a step needs a manager’s approval and the process dies. Relay treats every agent run as a durable workflow. Each step is checkpointed, so runs can pause, resume and recover without repeating side effects such as refunds or emails.
Tools are registered with typed schemas, permissions and rate limits. Policies are enforced outside the model, so an agent cannot act beyond its permissions, regardless of what the model generates. Every run produces a complete trace for debugging, audits and evaluation.
Capabilities
Core capabilities.
Durable workflows
Checkpointed steps with idempotent tool execution, automatic retries and resume-from-failure.
Human-in-the-loop
Approval gates that pause a run, notify the right person in Slack or email, and continue once they decide.
Typed tool registry
Schema-validated tools with per-agent permissions, rate limits and spending caps.
Policy enforcement
Business rules checked outside the model before every action. Violations are blocked and logged.
Tracing & replay
Step-by-step traces of prompts, tool I/O, tokens and latency. Any run can be replayed against a new version.
Model-agnostic
Route between model providers per step, with fallbacks when one is degraded.
Architecture
System architecture.
A simplified view of the principal layers and components.
Built with
Interfaces
REST & webhooksSlack & TeamsLINEHelpdesk appsOrchestration
Workflow enginePlannerApproval gatesSchedulerExecution
Tool registryPolicy engineModel routerSecrets vaultObservability
TracesCost meteringReplayAlerts
In production
Client projects built on Relay.
Contact
Have an AI product in mind?
Share what you would like to build, and we will help turn the idea into a production-ready product.
No technical specification required.
What happens next
- 1
Share your idea
Describe the problem, the users and the outcome you need.
- 2
Discovery call
We review your requirements together and clarify scope and constraints.
- 3
Proposal
You receive a clear scope, technical approach and delivery plan.