Features
Reliable programming platform with AI reliability, workflow orchestration, and real-time events
AI Reliability Layer
Make LLM calls and AI workflows reliable with automatic retries
- Wrap AI SDK calls with retries
- Exponential backoff for LLM failures
- Monitor AI workflow health
- Perfect for agent orchestration
Workflow Orchestration
Define multi-step jobs with automatic dependency resolution
- Declare workflows with dependencies
- Automatic execution ordering
- Pass results between steps
- Retry failed steps independently
Simple API
Language-idiomatic async/await interfaces that feel natural
- JavaScript/TypeScript with full type safety
- Python with async/await support
- Ruby with idiomatic patterns
- Go support available
Request-Response Mode
Get synchronous results when you need them immediately
- Wait for job completion
- Receive job results directly
- Timeout configuration
- Perfect for API integrations
Real-time Events
WebSocket-based job lifecycle notifications for instant feedback
- Active, completed, failed events
- Retry and expiration notifications
- Cancellation events
- Low-latency updates
Batch Operations
Atomic multi-job publishing for coordinated processing
- Publish multiple jobs atomically
- Wait for batch completion
- Coordinated workflow execution
- All-or-nothing guarantees
Cron Scheduling
Built-in recurring job support with standard cron syntax
- Standard cron expression support
- One-time and recurring schedules
- Timezone-aware scheduling
- Job expiration handling
Multi-tenant Isolation
Secure queue namespacing per project with token-based auth
- Project-level isolation
- Token-based authentication
- Temporary browser tokens
- Organization hierarchy support
Reliable Execution
Automatic retries and failure handling for mission-critical jobs
- Configurable retry policies
- Exponential backoff support
- Job expiration handling
- Priority-based execution