Coval Integration
Coval.dev is a simulation and evaluation platform for AI voice and chat agents. It helps developers build reliable agents faster by enabling testing, monitoring, and optimization of AI agents at scale. It also provides tools to create custom metrics and run thousands of scenarios, accelerating AI agent development with seamless simulation and evaluations.
Coval integrates natively with Langfuse, enabling direct trace transmission for advanced voice agent debugging. This integration provides deeper insights into your voice AI applications, helping you improve performance and reliability through detailed message analysis.
Learn more about evaluation of voice agents in our shared blog post.
Get started
Get your Langfuse credentials
First, you’ll need your Langfuse credentials:
- Secret Key
- Public Key
- Host URL
You can obtain these by signing up for Langfuse Cloud or self-hosting Langfuse.
Add Langfuse credentials
Log in to your Coval dashboard and navigate to Menu → Organization → Manage → Langfuse Integration. Enter your Langfuse credentials and click Save to update them.
Launch an evaluation on Coval and see traces in Langfuse
Now, every time you launch an evaluation on Coval, Coval logs your traces in Langfuse.
To view your results, navigate to your run results page and select Integrations. While Coval helps you review your metrics in the context of the conversation, you can visit Langfuse to debug specific messages or iterate on your prompts.