Explore Using Dremio's AI Agent
Understanding your data quickly using Dremio's AI Agent, an interface built into the Dremio console that allows users to converse with their data using natural language.
The AI Agent accesses data and entities that the logged in user has privileges on to address the prompt.
The AI Agent is currently optimized for the following tasks:
- Discover & Explore: Learn about the data that is available to you to answer your business question.
- Analyze: Ask questions using business terms using natural language and get insights instantly. The AI Agent goes beyond basic analysis to detect patterns in the data and return actionable insights.
- Visualize: Quickly visualize the patterns and trends in your data within the Dremio console.
- Explain and Optimize SQL: Ask the agent to review SQL queries, identify bottlenecks, and suggest optimizations.
- Analyze and Improve Job Performance: Ask the agent to review past jobs, identify performance issues, and suggest ways to improve them.
As Dremio's AI Agent reasons through your questions and requirements, you're able to see the actions it is taking directly in the interface so you can review, audit, and understand how the response is generated. Generative AI can make mistakes; therefore, you should verify all output.
Use Dremio's AI Agent
To use Dremio's AI Agent, you can access it by:
- Selecting the AI Agent icon in the SQL Runner.
- Use the shortcut keys ⌘+Shift+G on a Mac or Ctrl+Shift+G on Windows to open the agent.
Discover and Explore
Dremio's AI Agent will help you discover available data and provide a detailed breakdown of schema, as well as offer guidance on what tables and views you may want to use. The AI Agent will use wikis and labels as well as perform sampling or other simple analysis on the datasets to determine relevance and interesting patterns. The more detailed the question, the better the insight that the AI Agent can provide.
| Okay Prompt | Great Prompt |
|---|---|
| What tables can I use? | Which tables or views have customer location data? |
| How can I analyze time series data? | Which tables or views can I use to do a time series analysis on customer activity? |
What is the customer_activity table? | How is the customer_activity table structured, and what other tables does it relate to? |
Analyze
Dremio's AI Agent will write and execute SQL on your behalf based on your natural language input and the information available from the semantic layer. From within the chat, you can further audit the SQL by expanding the tool calls in the chat window.
| Okay Prompt | Great Prompt |
|---|---|
| I want to see analysis of customer activity | I want to see an analysis of customer purchase activity by region, by customer type for each month of the year. |
| Which customers are the most valuable? | Which customers have spent the most with us over the lifetime of the relationship? |
Visualize
Dremio's AI Agent will visualize insights on your behalf based on your natural language input. The details you provide, including the chart type, axis requirements, grouping, or trendlines, will be considered by the LLM. The visualization will be accompanied by insights that serve as a narrative for the chart that the AI Agent generated. Once a visualization has been created, you can toggle between the visualization and a grid representation of the data that is used to back the visualization.
The AI Agent can return the following types of visualizations: Bar, Line, Area, Scatter, Pie, Heatmap
| Okay Prompt | Great Prompt |
|---|---|
| Visualize the data | Visualize the data as a bar chart with month on the x asis and sum of purchase value as the y axis |
| Create a visual trendline showing me the activity | Create a visualization with a trendline showing customer activity by month? |
Explain SQL
Use the Explain SQL option in the SQL Runner to analyze and optimize your SQL queries with assistance from the AI Agent. In the SQL Runner, highlight the SQL you want to review, right-click, and select Explain SQL. This prompts the AI Agent to examine the query, datasets, and underlying architecture to identify potential optimizations. The AI Agent uses Dremio’s SQL Parser—the same logic used during query execution—to identify referenced tables, schemas, and relationships. Based on this analysis, the Agent provides insights and recommendations to improve query performance and structure. You can continue interacting with the AI Agent to refine the analysis and iterate on the SQL. The AI Agent applies SQL best practices when suggesting improvements and may execute revised queries to validate quality before presenting recommendations.
Explain Job
Use the Explain Job option on the Job Details page to analyze job performance and identify opportunities for optimization. From the Job Details page, click Explain Job to prompt the AI Agent to review the job’s query profile, planning, and execution details to compare with the AI Agent’s internal understanding of optimal performance characteristics. The AI Agent generates a detailed analysis that highlights key performance metrics such as data skew, memory usage, threading efficiency, and network utilization. Based on this assessment, it recommends potential optimizations to improve performance and resource utilization. You can continue the conversation with the AI Agent to explore the job in greater depth or reference additional job IDs to extend the investigation and compare results.