AI-powered analytics platform to gain insights, build dashboards, and generate reports for decision-making. Includes a chatbot for deeper analytics and running code.
Provides self-service data insights with AI, allowing users to gain instant insights, build dashboards, and generate reports.
A new chatbot that offers deeper analytics capabilities and can execute code for enhanced data interaction.
The capabilities of AI agents are determined by the type of databases they access. Different SQL dialects affect agent capabilities, e.g., an agent with MySQL access cannot calculate correlations like one with PostgreSQL.
AI agents can interact with Excel or CSV files similarly to how they handle a PostgreSQL database.
AI agents can interact with multiple APIs simultaneously and join data across them, providing capabilities similar to a PostgreSQL database.
Connect Turbular with Google BigQuery to access data from projects. Follow a series of steps to set up service accounts and grant permissions.
Create and manage service accounts within the Google Cloud Platform console to enable secure connections between Turbular and BigQuery.
Generate a JSON credential file from the Google Cloud Platform to authenticate and connect Turbular to BigQuery.
Set up connections to databases, Excel files, or APIs through an intuitive interface for data analysis and visualization in Turbular.
Use Excel files to import and analyze sample order data from online stores.
Interact with Kepler AI to generate customer lifetime value analysis based on order value, calculate averages, and visualize data.
Create line charts to visualize average lifetime value by order month using Kepler AI.
Convert visualizations to bar charts to better illustrate data insights.
Allows you to connect your database with Turbular by collecting necessary credentials such as type of database, host address, port, username, password, and database name.
Optionally allows you to connect to your database using SSH by entering your SSH credentials including host address, port, username, and private key.
A feature where you can test your database or SSH connection settings before saving to ensure the credentials are correct.
After testing the connection, this feature lets you save the connection settings for future use.
Provides instant, AI-driven insights to help businesses make better-informed decisions.
Enables users to build custom dashboards for visualizing data.
Allows for the creation of detailed reports based on company data.
A new chatbot named Erlang that provides deeper analytics capabilities and can run code.
Displays the distribution of users by region, with details on popular countries and cities.
Allows searching and managing the list of users, including names and email addresses.
Allows users to sign up or log in using their Google account for convenience and quick access.
Allows customers to use a chat feature powered by a language model to ask business-related questions and get responses based on connected data sources.
Provides a tool for customers to edit and customize dashboards to analyze business data.
Helps customers with writing tasks by providing suggestions and responses based on connected applications and business data.
Enables customers to connect to various data sources like databases, data warehouses, and more, integrating their data with the Turbular platform.
Allows connecting to databases such as MySQL, PostgreSQL, Oracle, Microsoft SQL Server, SQLite, and BigQuery for setting up a data source.
Supports uploading Excel and CSV files for data source setup, with a requirement to ensure correct data types and absence of password protection.
Integrates with APIs such as AWS, Stripe, Mailchimp, Shopify, Salesforce, Trello, LinkedIn, Zendesk, Jira, HubSpot, and ClickUp for data source synchronization.
Encourages proper naming conventions for columns and tables to ensure accurate data interpretation by Turbular's AI, highlighting good and bad examples.
Currently supports only English for database schemas and files, ensuring high performance and accurate data processing.
The AI Data Analyst agent can connect to your data source, allowing it to use and retrieve the necessary information for analysis.
The agent can retrieve data from your data source and visualize it in various formats for easy interpretation.
The agent can respond to messages by analyzing data and generating responses based on your queries.
Allows you to inspect the message generated by the agent by pressing the 'Message Details' button, which provides insights into the SQL statements and data used.
You can provide feedback on the agent's answers using thumbs up or down, helping improve future responses.
Displays tags to inform you which data sources were used for generating the agent's reply.
Kepler Small is designed for efficiency with API credits, excelling in processing straightforward data sets with limited columns. It provides desired charts with specific instructions and is best in English, German, French, and Spanish.
Kepler Medium balances affordability and capability, interpreting complex data sets and selecting appropriate visualizations. It provides well-constructed responses and is best in English, German, French, and Spanish.
Kepler Large tackles intricate data sources with ease, identifying the best chart for any data set. It offers detailed insights and supports multiple languages, operating at the forefront of technology.