For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Atoms PlatformProduct OverviewDeveloper GuideAPI ReferenceMCPIntegrationsDeveloper ToolsChangelog
Atoms PlatformProduct OverviewDeveloper GuideAPI ReferenceMCPIntegrationsDeveloper ToolsChangelog
  • Get Started
    • Quickstart Crew CLI
    • Overview
    • Error Handling
  • Build
  • Operate
      • Overview
      • Logging & Observability
      • Common Issues
  • Examples
    • Examples
  • Migrate
    • From ElevenLabs
LogoLogo
Voice AgentsModels
Voice AgentsModels
On this page
  • Why It Matters
  • Key Capabilities
  • What’s Next
OperateTesting & Debugging

Testing & Debugging

||View as Markdown|
Was this page helpful?
Previous

Running Campaigns

Next

Logging & Observability

Built with

Testing and debugging is how you ensure your agent works correctly before deploying to production. The SDK provides tools for local testing, logging, and diagnosing common issues.

Why It Matters

Voice agents are harder to debug than web apps—you can’t just refresh the page. Problems with latency, interruption handling, or tool execution only surface during real conversations.

The SDK gives you visibility into what’s happening at every step.

Key Capabilities

CapabilityDescription
Local TestingRun agents on your machine with the CLI chat interface
LoggingTrace events, LLM calls, and tool executions
Error HandlingGraceful recovery from failures mid-conversation
PerformanceMonitor latency and optimize response times

What’s Next

Logging

Trace execution flow and debug issues.

Common Issues

Troubleshooting FAQ and fixes.