> ## Documentation Index
> Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Test your agent with Cekura simulations

> Have Cekura call your phone agent with simulated callers, then review each call with AssemblyAI's own transcript and tool calls.

[Cekura](https://cekura.ai) tests voice agents by calling them. It plays scripted scenarios as a simulated caller, then scores the conversation against the metrics you define. AssemblyAI is a built-in provider in Cekura, so there's no bridge to run: Cekura dials the phone number bound to your agent, and after the call it pulls that session from your AssemblyAI account.

```
Cekura ──phone call──▶ your number ──SIP trunk──▶ AssemblyAI ──▶ your agent
   ▲                                                                 │
   └────────── Sessions API: transcript + tool calls ◀───────────────┘
```

Each Cekura result shows the transcript as AssemblyAI recorded it, not a re-transcription of the call audio. Every HTTP tool the agent called appears inline with the arguments it sent and the response it got back, so your metrics can check what the agent actually did.

**You need:**

* An [AssemblyAI API key](https://www.assemblyai.com/dashboard/api-keys)
* An `agent_id`. Don't have one? [Create an agent](/docs/voice-agents/voice-agent-api/create-agent) first.
* A phone number bound to that agent. Don't have one? [Set up an inbound phone agent via SIP](/docs/voice-agents/voice-agent-api/connect-to-twilio).
* A Cekura account. Don't have one? Sign up at [cekura.ai](https://cekura.ai).

<Note>
  Cekura connects to AssemblyAI agents **over the phone only**. It places every call, so the agent must answer inbound calls on a number you can dial by hand.
</Note>

## 1. Check the number reaches your agent

Call the number yourself before you set anything up in Cekura. If you don't hear your agent's greeting, Cekura's test calls won't reach it either. See [If it does not work](/docs/voice-agents/voice-agent-api/connect-to-twilio#if-it-does-not-work).

<Warning>
  Agent ids aren't shared between regional hosts. Phone numbers are registered on `agents.us.assemblyai.com`, so the agent bound to the number has to live there too. That's the **US** region in Cekura, which is its default. An agent created on `agents.assemblyai.com` can't answer the number.
</Warning>

## 2. Connect the agent in Cekura

In Cekura, go to **Agents**, create an agent, and select **AssemblyAI** as the provider. If it isn't in the grid, click **More options**.

Under **Integration Settings**, fill in:

| Field | Value |
| - | - |
| **AssemblyAI Agent ID** | The `agent_id` bound to your number. Cekura only considers sessions answered by this agent. |
| **AssemblyAI API Key** | Cekura uses the key to list your agent's sessions and download each one after a test. It's stored encrypted and never shown again. |
| **Region** | **US**, the default. Phone agents live in the US region, so leave it as is. |

Under **Telephony Settings**, enter the phone number bound to the agent and leave **Inbound** on, so Cekura dials your number. Telephony is the only connection type for AssemblyAI, and it turns on by itself once the credentials are saved.

Save the agent. The key field reads **API Key Configured** once it's stored. Use **Update** to rotate the key later.

## 3. Run a test

Open an evaluator in Cekura, click **Run**, and start the run with the **Telephony** connection. Cekura dials your number and plays the scenario as the caller.

When the call ends, Cekura finds the matching AssemblyAI session:

1. It lists your recent sessions and keeps the ones your agent answered, from the number Cekura dialed from, that started within a few seconds of the test call.
2. It waits for the session's conversation record, which usually takes a few seconds after the call ends.
3. It compares call duration and conversation content to confirm the match, so parallel test calls to the same agent each pair with the right session.
4. It replaces its own transcript with AssemblyAI's and attaches the session id to the result.

In the result, your agent's turns are labeled **Main Agent** and the simulated caller's turns are labeled **Testing Agent**. Each tool call shows up as a **Function Call** entry followed by a **Function Call Result** entry.

The same call is also in your AssemblyAI account, with a stereo recording and per-turn timings. Look it up by the session id on the Cekura result. See [Recordings and transcripts](/docs/voice-agents/voice-agent-api/session-history).

## If it does not work

| Symptom | Cause |
| - | - |
| Authentication fails when saving | The key doesn't have Voice Agent API access, or **Region** doesn't match the host the agent was created on. |
| Calls never connect | The number doesn't reach the agent. Call it by hand, then recheck the [SIP trunk and the number's agent binding](/docs/voice-agents/voice-agent-api/connect-to-twilio#if-it-does-not-work). |
| The result has Cekura's transcript, not AssemblyAI's | Cekura couldn't match the call to a session. Check that **AssemblyAI Agent ID** is the agent bound to the number under **Telephony Settings**, and that the run used the **Telephony** connection. |
| Some calls in a large run fail | Each test call is one Voice Agent session on your account. Past your concurrency limit, new sessions are refused with `concurrency_exceeded`. |

## Configure through the API

To create or update the Cekura agent through [Cekura's API](https://docs.cekura.ai/api-reference/test_framework/create-agent), set the provider to `assemblyai` and pass the credentials:

```json theme={null}
{
  "transcript_provider": "assemblyai",
  "assistant_id": "7ad24396-b822-4dca-871a-be9cc4781cf9",
  "assemblyai_api_key": "<your-assemblyai-api-key>",
  "assemblyai_data": {
    "region": "us"
  },
  "contact_number": "+15551234567",
  "inbound": true
}
```

`assistant_id` is your AssemblyAI `agent_id`, and it's required whenever a key is set. `assemblyai_data.region` defaults to `us`, so you can leave it out. The response never returns the key. Check the read-only `assemblyai_api_key_configured` field to see whether one is stored.

For the rest of Cekura's setup, see the [Cekura AssemblyAI integration guide](https://docs.cekura.ai/documentation/integrations/assemblyai).

## Cost

Every simulated call is a Voice Agent session billed to your AssemblyAI API key. Your telephony provider bills the inbound minutes, and Cekura bills its own side.