---
title: Coval Integration
sidebarTitle: Coval
logo: /images/integrations/coval_icon.png
logoAppearance: dark
description: Integrate Coval with Langfuse for simulation-based evaluation of voice agents.
---

# 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](/blog/2025-01-22-evaluating-voice-ai-agents).

## Get started

<Steps>

### 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](https://langfuse.com/cloud) or [self-hosting Langfuse](/self-hosting).

### 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.

</Steps>

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/analytics/coval.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.