# Tutorials

This section contains examples demonstrating how to use DBNL in various scenarios. Each example includes [working code](https://github.com/dbnlAI/examples), detailed explanations, and guidance on when to use each approach.

{% hint style="success" %}
All of these tutorials can be previewed in our [Read Only SaaS environment](https://docs.dbnl.com/get-started/quickstart#explore-the-product-with-a-read-only-saas-account).
{% endhint %}

### ADK Calculator Tutorial

<figure><img src="https://content.gitbook.com/content/yx9NXaWRjaOtW8ILLJQO/blobs/zuvfEZu6POoQkHDjYZDn/calc_demo_small_opt.gif" alt=""><figcaption></figcaption></figure>

The [ADK Calculator Tutorial](https://github.com/dbnlAI/examples/tree/main/adk_calculator_tutorial) provides a comprehensive walkthrough of building an end-to-end analytics pipeline:

* Generate OTEL traces from a Google ADK calculator agent
* Convert and augment trace data with computed metrics
* Upload multi-day trace data to DBNL
* Analyze agent behavior over time

### A/B Testing Tutorial

<figure><img src="https://content.gitbook.com/content/yx9NXaWRjaOtW8ILLJQO/blobs/beCxysOzeR7VcJlkKQwF/ab_demo_small_opt.gif" alt=""><figcaption></figcaption></figure>

The [A/B Testing Tutorial](https://github.com/dbnlAI/examples/tree/main/ab_test_example) demonstrates how to compare agent versions:

* Upload traces from multiple agent versions with cohort labels
* Add comparison metrics like accuracy and error rates
* Use DBNL segmentation to analyze version differences
* Validate improvements before full rollout

## Repository

All example code is available in the [dbnlAI/examples](https://github.com/dbnlAI/examples) GitHub repository.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.dbnl.com/examples/tutorials.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.