Adaptive Analytics Workflow

The Adaptive Analytics Workflow is the core mechanism for discovering, investigating, and tracking hidden behavioral signals from your production AI log data.

1. Discover: New signals are displayed as Insights and Dashboards within a Project.

2. Investigate: Signals can be triaged and refined through population and temporal comparisons with the Explorer or dive directly into the evidence with the corresponding subset of enriched Logs.

3. Track: Codify signals that are meaningful through specific filtered Segments and new custom Metrics.

4. Repeat: Future analysis and Insights are impacted by all tracked signals.

1

Discover

Signals from production log data can be discovered through:

• Dashboards: Graphical and tabular displays of product state, monitored columns, tracked Segments, and generated Metrics for independent analysis.

• Insights: Human readable explanations of patterns found in signals generated from unsupervised analysis of enriched logs. Insights are clustered subsets of log data representing temporal shifts, segments of interesting behavior, or outliers from expected behavior.

2

Investigate

Signals can be triaged and refined through:

• Explorer: Graphical and statistical comparison of subsets of log data corresponding to filters from Insights. Population and Temporal Comparison allows for rapid triage and refinement of filters for Segment creation.

• Logs: The raw ingested data and all generated Metrics associated with a filter from an Insights. This is the direct evidence from production data that led to the Insight.

3

Track

Once specific behaviors have been identified, understood, and refined they can be codified by creating:

• Segments: Saved filters on Log data corresponding to a specific behavior discovered from an Insight.

• Metrics: Custom functions, evals, and judges that are applied to ingested log data in all future enrich steps.

4

Repeat

Future analysis and Insights adaptively improve based on all tracked signals.

Next Steps

• Ready to start using DBNL? Head straight to our Quickstart to get set up on the platform and start testing your AI products right away for free.

• Want to understand more about the platform? Check out the Architecture, Deployment options, and other aspects of the Platform.