AI Assistant
The AI Assistant is a large language model (LLM) integration designed to make your data easier to understand, analyse, and work with in StackOps Elastic for Observability and Security use cases. You can interact with the AI Assistant in two ways:
- Contextual Insights — Inline guidance throughout Elastic Kibana, explaining errors, warnings, and messages, with suggested remediation steps.
- Chat — A conversational interface where you can ask questions about your data. The assistant can request, analyse, and visualise information using function calling.
What you can do with the AI Assistant
- Analyse root causes — Interpret stack traces and error logs to identify issues quickly.
- Identify performance bottlenecks — Highlight resource-heavy operations and slow searches.
- Generate reports — Create alert summaries, incident timelines, and metric-based reports.
- Build and run queries — Write Elasticsearch queries from natural language, convert Query DSL to ES|QL, and execute them directly in chat.
- Visualise data — Create time-series charts and distribution graphs from your Elasticsearch data.
How the AI Assistant uses your data
| Aspect | Details |
|---|---|
| Data processing | Handled only by the third-party AI provider (connector) you configure. Elastic does not use customer data for model training. |
| Anonymisation | Configure anonymisation rules in the AI Assistant settings. |
| Permissions | Apply the same permissions as the current user when performing searches. |
| Third-party use | May be retained or used by the provider for training or other purposes. Security and confidentiality are not guaranteed. |
| Telemetry | Collected by your AI provider during usage. Contact the provider for details. |
