# Overview - DBNL

## What is DBNL?

DBNL is an [Adaptive Analytics](https://docs.dbnl.com/workflow/adaptive-analytics-workflow) platform designed to discover and track hidden behavioral signals in production AI logs and traces so that product owners can confidently know exactly where and how to improve their AI products over time. The platform gives a detailed snapshot of agent behavior - the interplay and correlations between users, context, tools, models, and metrics. Patterns in behavioral signals are automatically surfaced as [Insights](https://docs.dbnl.com/workflow/insights) that can be investigated and tracked. This empowers AI teams to accelerate the AI data flywheel by pinpointing the signals and specific examples they can use to improve their products with confidence.

<figure><img src="https://content.gitbook.com/content/rsm4qOLTbARYHG7ZikPw/blobs/6Gmk93hCEZWX8atbHyiT/DBNL-high-level-flow.png" alt=""><figcaption><p>DBNL turns raw trace data into actionable insights to continuously improve your agents</p></figcaption></figure>

### Why DBNL?

The AI data flywheel promises better agentic performance over time through post-training optimization on real production data, *but not all data is created equal*. DBNL helps AI product owners fill the critical gap between high level monitoring tools (focused on aggregate performance through evals, logging, and tracing) and low level debugging tools (focused on single-trace observability) to pinpoint hidden behavioral signals and relevant example data for post-training optimization. This allows AI product owners to better understand agent and user behavior to know exactly where and how to improve AI products in production.

{% hint style="info" %}
Start analyzing right away with the [Quickstart](https://docs.dbnl.com/get-started/quickstart)
{% endhint %}

{% embed url="<https://www.youtube.com/watch?v=DfL-FcB5W6Q>" %}

### Who is DBNL for?

Distributional is built for AI product teams looking to understand and improve their AI agents that have

* **Scale**: More than 1,000 traces or logs per day (too many to manually inspect)
* **Data**: Access to full spans from OTEL trace data or similarly rich data for analysis (See our [Semantic Convention](https://docs.dbnl.com/configuration/dbnl-semantic-convention))
* **Value**: Quantifiable business metrics to track and improve
* **Understanding**: You already monitor aggregate performance (but need richer analysis to know where and how to improve and fix your AI agents)

### How do I deploy DBNL?

DBNL is openly distributed and free to [deploy](https://docs.dbnl.com/platform/deployment) within your cloud or on-premises environment, keeping your data safe, secure, and always under your control. Head over to our [Quickstart](https://docs.dbnl.com/get-started/quickstart) to get started right away.

## Analytics-Driven AI Data Flywheel

DBNL integrates with your existing AI tools to easily and securely perform analytics for any AI product. The [DBNL Data Pipeline](https://docs.dbnl.com/configuration/data-pipeline) ingests, enriches, and analyzes production AI logs and traces, surfacing behavioral signals. These signals are published to [Dashboards](https://docs.dbnl.com/workflow/dashboards) and as [Insights](https://docs.dbnl.com/workflow/insights), allowing users to discover, investigate, and track them as part of the [DBNL Analytics Workflow](https://docs.dbnl.com/workflow/adaptive-analytics-workflow). This gives you concrete signals and relevant data to power improvements to your agent as part of an AI data flywheel.

<figure><img src="https://content.gitbook.com/content/rsm4qOLTbARYHG7ZikPw/blobs/E21pYi6aL9hGfG8Qtekf/DBNL-Analytics-Flywheel.png" alt=""><figcaption><p>DBNL Accelerates the AI Data Flywheel by pinpointing behavioral signals and relevant production log data that can be used to optimize the underlying agent.</p></figcaption></figure>

{% stepper %}
{% step %}
**Ingest**

Production log data from AI products is published continuously via [OTEL Trace Ingestion](https://docs.dbnl.com/configuration/data-connections/otel-trace-ingestion) or pushed in batches via [SDK Log Ingestion](https://docs.dbnl.com/configuration/data-connections/sdk-log-ingestion).
{% endstep %}

{% step %}
**Enrich**

Data is augmented with LLM-as-judge, NLP, and other [Metrics](https://docs.dbnl.com/workflow/metrics) provided by DBNL or customized by the user to create a vector of rich behavioral information for every log line or trace, capturing the interplay and correlations between users, context, tools, models, and metrics. These behavioral vectors define a high-dimensional distributional fingerprint of behavior for the AI product rich with behavioral signals.
{% endstep %}

{% step %}
**Analyze**

Unsupervised learning and statistical techniques are applied to the distributional fingerprint daily to discover [Insights](https://docs.dbnl.com/workflow/insights); patterns in behavior related to filtered subsets of logs.
{% endstep %}

{% step %}
**Publish**

[Dashboards](https://docs.dbnl.com/workflow/dashboards) are updated and new [Insights](https://docs.dbnl.com/workflow/insights) are generated to represent newly observed and discovered behavior from the latest production data.
{% endstep %}

{% step %}
**Discover**

Product owners review generated Insights and Dashboards for greatest potential product impact.
{% endstep %}

{% step %}
**Investigate**

Product owners explore and refine evidence-based behavioral signals through exploration of metrics and inspection of the raw [Logs](https://docs.dbnl.com/workflow/logs).
{% endstep %}

{% step %}
**Track**

Once specific behaviors have been identified, understood, and refined they can be used to create custom [Metrics](https://docs.dbnl.com/workflow/metrics) or be tracked as filtered [Segments](https://docs.dbnl.com/workflow/segments).
{% endstep %}

{% step %}
**Optimize and Repeat**

The signals discovered and the relevant examples surfaced can be used to perform post-training optimization like fine tuning, reinforcement learning, prompt/context engineering, hyperparameter optimization, or any other improvements to the underlying agent as part of an Analytics-Driven AI Data Flywheel.

As improvements to the agent are made and new production data is ingested, the workflow adapts automatically by using tracked Metrics and Segments to guide deeper and more customized analysis over time.
{% endstep %}
{% endstepper %}

<figure><img src="https://content.gitbook.com/content/rsm4qOLTbARYHG7ZikPw/blobs/RUzxxoO7uTPlIjQwD0Nh/calc_demo_small_opt.gif" alt=""><figcaption><p>Dive into the product right away in the <a href="quickstart">Quickstart</a> or <a href="../examples/tutorials">Tutorials</a>. The above is part of the <a href="../../examples/tutorials#adk-calculator-tutorial">Google ADK Calculator Tutorial</a>.</p></figcaption></figure>

### Next Steps

* **Ready to start using DBNL?** Head straight to our [Quickstart](https://docs.dbnl.com/get-started/quickstart) to get set up on the platform and start testing your AI products right away for free.
* **Want to learn more about the workflow?** Check out the [Adaptive Analytics Flywheel](https://docs.dbnl.com/workflow/adaptive-analytics-workflow).
* **Want to understand more about the platform?** Check out the [Architecture](https://docs.dbnl.com/platform/architecture), [Deployment](https://docs.dbnl.com/platform/deployment) options, and other aspects of the [Platform](https://docs.dbnl.com/platform/platform).