Skip to main content
The nao chat comes with powerful built-in capabilities that enable natural language analytics.

​
Key Features

Natural Language Queries

Ask questions in plain English and get instant answers

Data Visualization

Automatically generate charts and graphs from your data

Transparent Reasoning

See the SQL queries and logic behind each answer

Conversation History

Navigate through past queries and build on previous answers

​
How It Works

When you ask a question, the agent follows this process:
1

Context Discovery

The agent searches and reads your context files to understand your data model, business definitions, and rules.
2

Query Generation

Based on the context, the agent writes an optimized SQL query tailored to your question.
3

Execution

The query runs against your connected database and returns results.
4

Visualization

If appropriate, the agent creates charts to help visualize the data.
5

Response

The agent summarizes findings in plain language, showing its sources and reasoning.

​
Agent Tools

The nao agent comes equipped with a set of powerful tools that it uses autonomously to answer your questions:
Execute SQL queries against your connected database(s) and return structured results. The agent writes optimized queries based on your context files and business logic.
  • Supports multiple database connections
  • Returns data with column information and row counts
  • Results can be referenced by other tools (like charts)
Create visualizations from SQL query results. The agent automatically chooses the best chart type based on your data.Supported chart types:
  • Bar charts
  • Line charts
  • Pie charts
Charts are rendered directly in the chat with customizable colors and axis configurations.
List files and directories at a specified path in your context. Helps the agent navigate your project structure and understand available resources.
Read the contents of context files including SQL models, documentation, business definitions, and rules. This is how the agent understands your data semantics.
Search for text patterns across your context files using regex. Supports glob filtering, case-insensitive search, and context lines around matches.
The agent orchestrates these tools automatically based on your question. You don’t need to specify which tools to use — just ask your question naturally and the agent will determine the best approach.