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

# Bluejay AI

> Ask Bluejay AI why your calls fail.

Bluejay AI is the assistant inside the Bluejay app. Ask it about your runs and calls, and it can also make the change for you.

<video controls muted playsInline preload="metadata" src="https://mintcdn.com/bluejay/eKcFBkjZX47pI8Ss/videos/bluejay-ai-demo.mp4?fit=max&auto=format&n=eKcFBkjZX47pI8Ss&q=85&s=9513a76ea7bc4eab6aaeb5312962f474" />

## What you can do

* **Find why calls fail.** It reads the run or calls you have open and tells you why they failed.
* **Create and run a simulation.** Describe the callers you want, and it makes the Digital Humans and offers to start the run. See [Create a Simulation](/test/simulations/create.md#let-bluejay-ai-do-it).
* **Add a test for a failure.** It creates Digital Humans that repeat the failure. See [Digital Human Reference](/test/simulations/digital-humans.md).
* **Measure a failure.** It creates a [custom metric](/test/metrics.md) that grades the failure on every call.
* **Fix the prompt.** It rewrites your agent's prompt for one failure pattern and saves it as a new prompt version when you approve. This does not change the prompt on your voice platform.
* **Start Self-Improve.** It shows a preview and starts the run when you confirm. See [Self-Improve](/improve/self-improve.md).
* **Build a dashboard.** It creates a dashboard or changes its widgets. See [Dashboards](/monitor/dashboards.md).
* **Import a workflow.** Attach a document, and it drafts the agent's workflow for you to approve. This works only for an agent that has no workflow provider.

## Open Bluejay AI

Click the round Bluejay logo at the bottom right of the app, or press `Cmd+J` (Mac) or `Ctrl+J` (Windows). Open the run or the Logs page first, because Bluejay AI reads the page you are on. Your question can then say "this run" or "these calls".

## Example questions

**Test**

* "Why did the failed calls in this run fail?"
* "Which Digital Humans failed, and what do they have in common?"
* "What should I fix first on my agent?"

**Monitor**

* "Why did my calls fail this week?"
* "What percent of inbound calls failed today, and which agent is worst?"
* "Show me example calls where the caller asked for a human."

## Related

* [Self-Improve](/improve/self-improve.md)
* [Read the results](/test/simulations/create.md#read-the-results)
* [Logs](/monitor/logs.md)
* [Metrics](/test/metrics.md)
* [Dashboards](/monitor/dashboards.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.