New project layer to group workspace databases and database connections - All workspaces now contain one or more projects. A project contains local databases (data generated to Fabricate) and, for Enterprise customers, database connections (live connections to external databases). Note that database connections are no longer in private preview, and are available to all Enterprise customers.
The left navigation now contains:
- A tree structure of the databases and connections in the current project. You can expand and collapse the list of tables for each database and connection.
- The lists of workflows and plans for the project.
The Mock API entry shows the count of endpoints across the project. The API page includes the endpoints for all of the databases or connections in the project.
The Data Agent chat also applies across the entire project and can refer to any of the databases and connections in the project.
When you clone a local database, you can clone it to any project in any workspace that you have access to.
For your existing databases, Fabricate creates a new project for each database. The project uses the same name as the database.
Account groups - Fabricate now supports account groups. A group contains one or more users. Customers who use single sign-on can synchronize their SSO groups with their Fabricate groups, and set a filter to limit the groups to synchronize. When the groups are synchronized, Fabricate automatically creates account groups to match corresponding SSO groups. The groups are created the first time an SSO user that belongs to a group logs in. You can assign workspace roles to groups.
Snowflake data connections - You can now create database connections that are linked to Snowflake databases.
OpenAPI spec for mock APIs - Mock APIs now include an OpenAPI spec.
Autonomous mode - In addition to the Agent mode (the default) and Plan mode, Fabricate now supports Autonomous mode. In Autonomous mode, the Data Agent plans and executes the action completely independently, without any clarification or prompts. Autonomous mode is useful for extremely large, long-running workflows, where you might not want to or even be able to respond to prompts or questions from the Data Agent.
You can now clone a database into a different workspace.
Fixed an Admin Console display issue where the Search and New Account buttons were not visible without horizontal scrolling.
Fixed an issue where the page did not reset when users navigated to a different table.
Azure AI Foundry support - You can now use Azure AI Foundary as your LLM provider for the Data Agent.
Connection string for server connections - For setting up a server connection, you can now paste in a connection string. Fabricate parses the string and uses the results to populate the configuration fields.
Agent skills - Within a workspace, you can now configure a set of Agent skills, which provide instructions for specific uses cases. For example, if you publish content to a REST API, you might configure a skill that specifies the authentication and endpoint to use. You can create and manage skills from the Skills dropdown in the Agent prompt, or from the Agent instructions panel.
Improved Data Agent handling of timestamps.
Enterprise users can now add database connections to databases that are not specifically live connection databases. You can use a database connection as a resource to guide the structure of a database or as a source of data to incorporate into the generated data. You can also generate data directly to a database connection. This feature is currently in private preview. To request access, contact Tonic.ai.
Improved the deployment of the US instance of Fabricate.
Fixed several issues.
Data Agent configuration- Added configuration options for the Data Agent behavior. In your user profile settings, you can set the Agent verbosity (how much explanation the Agent provides) and autonomy (how often the Agent asks for confirmation). In the user profile settings, workspace settings, and account settings, you can also provide Agent instructions, a set of context rules for the Agent to remember across sessions and databases. The most specific configuration has the highest priority - the profile configuration has a higher priority than the workspace configuration, which has a higher priority than the account configuration.
Redesigned the Account Settings page to group the settings into pages.
Export to Amazon S3 - From the Agent chat, you can now export data to an S3 bucket. Before you can do the export, you must configure the S3 bucket as an available domain for your account, and configure AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY as available secrets for each workspace that uses the S3 bucket.
Database selection - The database dropdown to switch between databases now includes a search field to allow you to search for a database by name. It also lists recent databases.
Database profile - The Data Agent now maintains a profile of each database. You can also prompt the Agent to generate or update a database profile. The Data Agent consults the profile whenever it needs to understand the content or structure of a table, such as when it adds data.
The profile for each table displays on the Findings view for the table, and includes:
- A description of the table.
- The DDL for the table.
- Correlation of columns. For example, a transaction date and transaction identifier are likely to be tightly correlated.
- Cardinality of column values.
- Constraints on columns.
- Distribution of column values.
Live connection databases-From the Data Agent, you can now create live connections databases. For a live connection database, Fabricates generates the data directly to an external database. You configure the available server connections for the account. When you create the database, you identify the server connection and the database to use. In a live connection database, you cannot:
- Directly edit the data
- Revert Data Agent actions
- Import static data
- Export data
- Clone the database
The user menu is now always located at the bottom left of the Fabricate application. Previously, on pages such as account settings and workspace settings, it moved to the top right.
The user menu now includes a Workspace Settings option to allow you to configure settings for the current workspace. Also renamed the My Profile and My Account options to User Settings and Account Settings.
Added a create database icon next to the database dropdown list. This replaces the New Database option that was previously in the dropdown list.
You can now rename a Data Agent chat. To rename the chat, double-click the chat name.
Fixed an issue where an error occurred when the Data Agent attempted to overwrite a file that required extensive changes.
You can now import data from and export data to .xslx files.
Single sign-on SSO - Fabricate now supports SSO for Enterprise accounts. Fabricate supports any OIDC provider that supports the Authorization Code Flow mode. The allowed domains configuration for an account now includes allowed email address domains for SSO.
Fabricate now uses Opus 4.6.
For additional security, Fabricate now limits the number of password reset requests.
Mock APIs for Data Agent databases (Private Preview) - You can now prompt the Data Agent to create a mock API based on an uploaded Swagger file. This is to accommodate products or features that need to interact with an API instead of directly with a database. Fabricate produces a details page that shows the available routes. The mock API feature for Data Agent databases is currently in private preview. To request access, contact Tonic.ai.
You can now prompt the Data Agent to send feedback to Tonic.ai. This performs the same function as the feedback option that is available in the user menu. Based on the chat, the Data Agent can also ask if you want to send feedback.
Fixed a tooltip display issue.
Fixed an issue with not being able to download a generated file.