Understand your AI agents in production
See what users want, where agents break expected behavior, and what to improve next
Voxmith helps teams understand and improve AI agents using real production interactions. It shows what users are trying to accomplish, identifies where agents violate expected behavior, and connects every finding to the conversation, event, or tool call behind it.
Get started
Connect an agent and see your first interaction in Voxmith.
Why teams use Voxmith
Understand user demand
Use intents to see what users are trying to accomplish across real conversations.
Catch broken behavior
Find conversations where an agent did not follow an expected rule.
Debug the cause
Trace an outcome back to the events and tool calls that produced it.
Improve continuously
Turn production evidence into alerts and concrete improvements.
How it works
1. Connect your agent
Use the Voxmith skill, a Voxmith SDK, or OpenTelemetry with your existing framework.
2. Understand production
Analyze conversations through intents and violations, with the supporting evidence attached.
3. Take action
Monitor important conditions with alerts and turn recurring issues into improvements.
The data behind every finding
| Data | What it represents |
|---|---|
| Conversations | Complete user interactions grouped into one timeline. |
| Events | Agent turns, model generations, handoffs, guardrails, and other operations. |
| Tool calls | Tool execution details, outcomes, and latency. |
Voxmith analyzes this production data into intents and violations. You can always open the supporting conversation and inspect the underlying events before deciding what to change.
See your first interaction
Use the Quickstart for guided setup, or select your existing framework under Agent frameworks in the sidebar.
Start the quickstart
Connect an agent, trigger one real interaction, and verify that it reached Voxmith.
Next steps
- Quickstart: send your first interaction to Voxmith.
- Conversations: learn how related activity is grouped.
- Intents: organize conversations by what users wanted.