> ## Documentation Index
> Fetch the complete documentation index at: https://help-center.relyable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> Get your first AI voice agent tested in under 10 minutes

This guide will walk you through importing your first voice agent into Relyable, generating test cases, and running your first automated tests.

<Note>
  **Prerequisites**: You need an existing Vapi or Retell AI voice agent. If you don't have one yet, create one first in your platform of choice.
</Note>

## Step 1: Create Your Relyable Account

<Steps>
  <Step title="Sign Up">
    Visit [app.relyable.ai](https://app.relyable.ai) and create your account. You'll be taken to your workspace dashboard.
  </Step>

  <Step title="Create a Workspace">
    If you're starting fresh, you'll create your first workspace. Think of workspaces as separate environments for different clients or projects.
  </Step>
</Steps>

## Step 2: Import Your Voice Agent

<Steps>
  <Step title="Navigate to Agents">
    In your Relyable dashboard, click on **Agents** in the top navigation, then click **Create New Agent**.
  </Step>

  <Step title="Select Your Platform">
    Choose your AI provider:

    * **Vapi**
    * **Retell AI**
  </Step>

  <Step title="Get Your Credentials">
    You'll need two things from your voice platform:

    **For Vapi:**

    1. Go to your [Vapi Dashboard](https://dashboard.vapi.ai)
    2. Navigate to Settings → API Keys
    3. Copy your **Private Key**
    4. Go to your assistant and copy the **Assistant ID** from the URL or settings

    **For Retell:**

    1. Go to your Retell dashboard
    2. Get your API key from Settings
    3. Copy your agent ID
  </Step>

  <Step title="Import the Agent">
    Paste your API key and Assistant/Agent ID into Relyable. Click **Next**.

    Relyable will automatically:

    * Import your agent configuration
    * Pull in your system prompt
    * Sync your phone number (if configured)
    * Load your agent settings
  </Step>

  <Step title="Verify Import">
    You should see your agent's prompt displayed in Relyable. Review it to make sure everything synced correctly, then click **Create Agent**.
  </Step>
</Steps>

<Tip>
  You can sync your prompt at any time by clicking the **Sync Prompt** button in your agent settings. This is useful when you update your prompt in Vapi/Retell.
</Tip>

## Step 3: Generate Test Cases

Test cases are the criteria Relyable uses to evaluate whether your agent is following your instructions correctly.

<Steps>
  <Step title="Navigate to Test Cases">
    Click on **Test Cases** in your agent's navigation menu.
  </Step>

  <Step title="Generate AI Test Cases">
    Click **Generate Test Cases**.

    Relyable's AI will analyze your prompt and suggest 15-20 test cases. For example:

    * "Agent must introduce itself as Emily from Inflate Real Estate"
    * "Agent must ask for the caller's full name and spell it back letter by letter"
    * "Agent must confirm the address by reading it back to the caller"
  </Step>

  <Step title="Review and Customize">
    Go through each test case and:

    * Verify it's accurate for your use case
    * Adjust the priority level (Critical, High, Medium, Low)
    * Edit the description if needed
    * Add custom test cases for specific scenarios
  </Step>
</Steps>

<Warning>
  **Critical test cases** have the biggest impact on your score. Use this priority for must-have behaviors like emergency call routing or compliance requirements.
</Warning>

### Example Test Cases

Here are some examples of well-written test cases:

**Critical Priority:**

* "Agent must transfer emergency calls to a human operator within 10 seconds"
* "Agent must capture and confirm the customer's email address before ending the call"

**High Priority:**

* "Agent must spell back the customer's name letter by letter for confirmation"
* "Agent must follow the conversation flow step-by-step without skipping questions"

**Medium Priority:**

* "Agent should maintain a friendly and professional tone throughout the call"
* "Agent should handle interruptions gracefully and not lose context"

**Low Priority:**

* "Agent should use the caller's name at least once during the conversation"

## Step 4: Create a Persona

Personas simulate different types of callers to stress-test your agent with realistic scenarios.

<Steps>
  <Step title="Navigate to Personas">
    Go to the **Simulation** section and click on the **Personas** tab.
  </Step>

  <Step title="Generate a Persona">
    Click **Generate Personality** and describe the type of caller you want to simulate.

    **Examples:**

    * "A 65-year-old male who is frustrated and has no patience"
    * "A 28-year-old female professional who speaks quickly and is tech-savvy"
    * "A non-native English speaker with a strong accent who speaks slowly"
  </Step>

  <Step title="Review the Generated Persona">
    Relyable will create a detailed persona with:

    * Name and demographics
    * Personality traits
    * Communication style
    * Speaking patterns
    * Accent/voice characteristics

    You can edit any of these details to fine-tune the persona.
  </Step>
</Steps>

<Tip>
  Create 3-5 diverse personas representing your actual customer base. This helps you discover issues across different user types.
</Tip>

## Step 5: Run Your First Test

<Steps>
  <Step title="Create a Scenario">
    Go to the **Run** tab in the Simulation section.

    Click **Generate Tests** and:

    1. Select a persona (like the one you just created)
    2. Select which test cases to evaluate
    3. Let AI generate a realistic scenario, or write your own

    **Example AI-generated scenario:**

    > "You are Stanley Miller, a 79-year-old retired mechanic. Your kids are forcing you to sell your house you've lived in for 50 years because it's getting too hard to manage. You're calling the agency reluctantly and annoyed by the whole process."
  </Step>

  <Step title="Run the Test">
    Select your scenario(s) and click **Run Test**.

    You can:

    * Run a single scenario multiple times
    * Run multiple different scenarios at once
    * Give your test run a descriptive name
  </Step>

  <Step title="Wait for Results">
    Relyable will make actual phone calls to your agent using the personas and scenarios. This typically takes 2-3 minutes per call.

    You can see the progress in real-time on the **Results** page.
  </Step>
</Steps>

## Step 6: Analyze Your Results

<Steps>
  <Step title="View Your Score">
    Once testing completes, you'll see:

    * **Overall Score** (aim for 70%+ for production-ready)
    * **Average Latency** (response time)
    * **Words Per Minute** (speaking speed)
    * **Test Case Results** (which ones passed/failed)
  </Step>

  <Step title="Review Failed Test Cases">
    Click on any failed test case to see:

    * The exact conversation where it failed
    * Why it failed (AI explanation)
    * Suggestions for fixing it

    For example:

    > "Agent asked 'Would you like to book a walkthrough?' but skipped the required question 'What is your timeline for moving in?' The prompt requires asking about the timeline BEFORE offering the walkthrough."
  </Step>

  <Step title="Listen to Recordings">
    Click on any conversation to:

    * Listen to the full audio recording
    * Read the full transcript
    * See which test cases passed/failed in that specific call
  </Step>
</Steps>

## Step 7: Iterate and Improve

<Steps>
  <Step title="Fix Your Prompt">
    Based on the failures, update your prompt in Vapi or Retell. Common fixes:

    * Add step-by-step numbering to enforce question order
    * Add explicit confirmation steps (repeat name, address back)
    * Add handling for edge cases discovered in testing
  </Step>

  <Step title="Sync to Relyable">
    After updating your prompt in Vapi/Retell, go to your agent in Relyable and click **Sync Prompt** to pull the latest version.
  </Step>

  <Step title="Test Again">
    Run your tests again with the same scenarios to see if your score improved. Keep iterating until you consistently score 70%+.
  </Step>
</Steps>

<Tip>
  **Pro tip:** Don't try to fix everything at once. Pick the 2-3 most critical failures, fix those, test again, and repeat. This helps you isolate which changes actually improve performance.
</Tip>

## Step 8: Enable Live Monitoring (Optional)

Once you're happy with your test scores, enable live monitoring for production calls:

<Steps>
  <Step title="Enable Call Monitoring">
    Go to your agent's **Settings** and toggle **Enable Call Monitoring**.

    This adds a webhook to your Vapi/Retell agent that sends call data to Relyable.
  </Step>

  <Step title="Monitor Real Calls">
    Every real call to your agent will now be:

    * Evaluated against your test cases
    * Scored automatically
    * Visible in your Relyable dashboard under the **Monitoring** tab
  </Step>

  <Step title="Get Alerted">
    Set up alerts for critical failures so you know immediately if your agent starts having issues in production.
  </Step>
</Steps>

## What's a Good Score?

Here's what scores typically mean:

| Score         | Status    | What It Means                             |
| ------------- | --------- | ----------------------------------------- |
| **90%+**      | Excellent | Production-ready, minimal failures        |
| **70-89%**    | Good      | Acceptable for production with monitoring |
| **50-69%**    | Fair      | Needs improvement before production       |
| **Below 50%** | Poor      | Significant issues, not production-ready  |

<Warning>
  In the demonstration from the video, an agent that worked perfectly in manual testing scored only **51-61%** in automated testing. Don't trust manual testing alone!
</Warning>

## Next Steps

<CardGroup cols={2}>
  <Card title="Deep Dive Development Guide" icon="book" href="/development">
    Learn advanced prompt engineering and testing strategies
  </Card>

  <Card title="API Integration" icon="code" href="/api-reference/introduction">
    Automate testing with the Relyable API
  </Card>

  <Card title="Best Practices" icon="lightbulb" href="/development#prompt-engineering-best-practices">
    Learn from production voice AI experts
  </Card>

  <Card title="Join Community" icon="users" href="https://x.com/relyableai">
    Connect with other Relyable users
  </Card>
</CardGroup>

## Common Issues

<AccordionGroup>
  <Accordion title="My agent won't import">
    Make sure you're using the correct API key and Assistant/Agent ID. For Vapi, you need the **Private Key** (not Public Key). Check that your agent is published in your voice platform.
  </Accordion>

  <Accordion title="Test calls aren't working">
    Verify that your agent has a phone number configured in Vapi/Retell. Relyable needs a phone number to call for testing.
  </Accordion>

  <Accordion title="Scores seem too low">
    This is normal! Most agents that seem to work fine in manual testing score 50-60% initially. This is why automated testing is so valuable - it finds issues you wouldn't discover manually.
  </Accordion>

  <Accordion title="How do I improve my score?">
    Focus on test cases marked as Critical or High priority first. Read the AI explanations for why tests failed, update your prompt, sync, and test again. It's an iterative process.
  </Accordion>
</AccordionGroup>

## Need Help?

* Check out the [full development guide](/development) for detailed prompt engineering tips
* Review the [API documentation](/api-reference/introduction) for programmatic access
* Reach out on [X/Twitter @relyableai](https://x.com/relyableai)