# 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/v0.29.x/get-started/quickstart#explore-the-product-with-a-read-only-saas-account).
{% endhint %}

### ADK Calculator Tutorial

<figure><img src="https://content.gitbook.com/content/lUoirJaFEHofsQHmOtdL/blobs/rY2shLSKM47ocjf1AaR6/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/lUoirJaFEHofsQHmOtdL/blobs/AIKflELc2YLkHldWnQME/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

### Hyperparameter Optimization Tutorial

<figure><img src="https://content.gitbook.com/content/lUoirJaFEHofsQHmOtdL/blobs/2Mx67ldVsjMe5X7H3ykT/hpo_demo_small_opt.gif" alt=""><figcaption></figcaption></figure>

The [HPO Tutorial](https://github.com/dbnlAI/examples/tree/main/nemo_agent_toolkit_hpo_example) shows how to analyze hyperparameter impact:

* Upload traces from agents with different configurations
* Compare pre and post-optimization performance
* Use DBNL insights to validate optimization results
* Build automated optimization pipelines with DBNL feedback

## Repository

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