Fabricate now requires a corporate email address to sign up for a new Fabricate account. It no longer accepts personal email addresses. Enterprise accounts and self-hosted instances can still invite any user.
For authentication to Google BigQuery, self-hosted instances can now use Google STS service account impersonation. From the workspace settings page, you configure the available GCP service accounts. When you create a server connection to Google BigQuery, you choose whether to use a service account JSON key or service account impersonation.
From the plan details, you can now select the mode and models to use when you execute the plan. For example, you might use Agent mode as you interact with the Data Agent, but have the plan set to use Autonomous mode during execution.
The API keys list now indicates who created each key.
Server connections to Google BigQuery, MySQL, Oracle, and SQL Server now support connecting through a tunnel.
Other issue fixes and internal enhancements.
The Admin Console now opens to the Users page.
Updated the pricing page.
For Claude models, increased the context window to 400,000 tokens.
Fixed several smaller issues with the context window and model selection options.
Improved the usage summary and cost breakdown panel for the Data Agent chat.
Fixed an issue where the Run By column for a workflow job was empty when the job was triggered from the MCP server.
Improved error handling when expired users perform actions.
Added more time periods that you can view the AI Usage chart for.
You can now use Databricks for Live Connect database connections.
In the project navigation, CSV and JSONL files now display as tables.
Fixed an issue where the Run By column for a workflow job was empty if the job was run using an API key through the API or an MCP server.
Built-in MCP servers for simulation results - To support using agents to interact with simulation results, Fabricate provides a set of built-in MCP servers for the simulation content platforms. For example, there's an MCP server for Slack, an MCP server for Google Workspace, and an MCP server for Microsoft Outlook. Before you can use an MCP server, you must publish it for a specific set of simulation results. In the project version where you want to use the MCP server, prompt the Data Agent to publish the MCP server. For example, "Publish the Slack MCP server for the Project Flow simulation results database". The published MCP servers are listed on the MCPs page. From the MCPs page, you can remove a published MCP server.
In the project navigation, you can now organize your local databases, database connections, and simulation results into folders. The Artifacts and Uploads folders for files remain separate at the bottom of the structure. You can create a multilevel folder structure, and drag and drop items into folders. Note that deleting a folder does not delete the folder content. When you delete a folder, the content is moved up into the parent folder.
You can now select a specific model to use for profiling. Account owners can select the default profiling model, and you can select the profiling model that you want to use.
Account owners can now add a temporary increase to the AI spend limit for an individual user or API key. The increase only applies within the current billing period.
Custom MCP servers - You can now create custom MCP servers for a project to allow you to have agents call your mock API endpoints. The API link in the navigation, which previously displayed the endpoints list, is now a folder that contains the endpoints, the MCP servers, the logs of requests to the endpoints and MCP servers, and the sandboxes.
Sandboxes - You can now create sandboxes, which are temporary copies of project databases. You can then interact with a sandbox without affecting the actual project data. For example, you could use sandboxes for test suites, to allow you to always start with the same set of data and make the same changes. Sandboxes automatically expire and are removed after an hour of inactivity. An account cannot have more than 10 active sandboxes at any given time.
Changed the default model to Claude Sonnet 5.5.
When selecting the category of model to use for freeform text generation, Fabricate now displays the model that is currently associated with each category.
Account owners can now disable and re-enable users. Disabled users lose access to Fabricate until they are re-enabled.
Simulations - The new simulations approach generates time-based data that tells a story. For example, you might generate a set of documents, email messages, and Slack posts that track a product design review. Or the appointments, patient notes, and insurance responses for a patient diagnosis and treatment. The simulation approach creates a workflow can run either in preview or complete mode. The results include an overview of the scenario, the scenario cast (the personas that are involved), and the timeline (in the form of a script with acts and scenes). The results use simulators to replicate the look and feel of the actual tools. For example, Slack messages display in a replica of the Slack user interface.
The simulations feature requires an Enterprise license. It is currently in private preview. To request access, contact Tonic.ai.
Accounts that use their own LLM key can now use OpenAI or an OpenAI-compatible provider.
SSH tunneling for server connections - For server connections to PostgreSQL, Amazon Redshift, and Snowflake, you can now choose to use an SSH tunnel to make the connection. You set up the available tunnels in the Network Tunnels section of the workspace settings. This feature is currently in private preview. To request access, contact Tonic.ai.
Navigation for generated and uploaded files - The project navigation now includes folders for unstructured files. The Artifacts folder contains files that you prompted Fabricate to generate. The Uploads folder contains files that you uploaded to Fabricate. These folders can contain sub-folders. When you click a folder, Fabricate displays the list of files. When you click a file, Fabricate displays a preview of the file. The file list and file preview pages include options to download the content and to go to the point in the Data Agent chat where the content was generated or uploaded. This feature is currently in private preview. To request access, contact Tonic.ai.
Fabricate now uses Claude Opus 5.5 as its default Data Agent model.
The Admin Console now includes a Jobs page that lists all of the workflow jobs across the instance.
Fixed an issue where editing table cells directly could cause the cell content to be corrupted.
Fixed an issue where Fabricate did not display the correct count of profile findings when the count was greater than 100.
Fixed issues with Data Agent summarization.
Project versioning - Enterprise users can now create multiple versions of a project. This allows you to have a stable set of data to use for testing while you continue to work on the data. A project can have multiple draft versions, a single published version, and multiple prior versions, which are previously published versions. You can publish a draft version, or promote a prior version to be the current published version. When you publish a version, by default the version data is locked. You cannot add data to or remove data from local databases. Live connect databases, because they are external, cannot be locked. You can create new draft versions based on other versions.
A new environment variable, FABRICATE_CA_CERT_FILE, allows self-hosted instances to specify a path that contains a globally trusted CA certificate. You set this when your instance is behind something that intercepts outbound TLS and re-signs HTTPS traffic with its own certificate instead of passing through the original certificate.
Fixed an issue with generating postal codes and area codes.
When you select the model to use for freeform text generation, you now select a basic category of model (Economy, Fast, Standard, Premium) instead of a specific model.
New setup wizard for self-hosted instances - After you deploy a self-hosted instance of Fabricate, the first time that you go to the instance URL, Fabricate provides a setup wizard that completes a compatibility check, installs the license key, and provides telemetry options.
Subdomain support for account domains - The account domains configuration now includes an option to allow traffic from subdomains. For example, when you add example.com, if you allow subdomain traffic, then api.example.com would also accept requests. The option is not available for pre-approved domains.
Freeform text model for mock APIs and workflows - You can now configure the model that a workflow or mock API uses for freeform text generation. To display the configuration setting, in the API or workflow heading, click the settings icon.
Account group assignment for API keys - You can now assign API keys to account groups.
You can now use the MCP server to get account groups, get usage by group, and get audit events by group.
When you stop a conversation, Fabricate now prompts you to determine how to handle any running workflows. You can detach the workflow from the conversation, which allows the workflow to continue to run in the background, or you can cancel the workflow.
Fixed an issue where testing a database connection created a server connection with the same name as the one used for the database connection.
Workflow parameters can now be flagged as secrets, meaning that the value is masked in the parameter field, API responses, and logs.
Fixed an issue where the Data Agent stop button was not properly re-enabled.
Fixed a couple of small display issues.
For the Reusable Generator approach, the Agent now prompts you to confirm that you want to use AI-generated text for the values. After the script is written, regular value generation does not incur token cost. AI-generated text does.
Fixed an issue with memory errors for longer generations.
Reusable Generator data generation approach - As of September 4, 2026, the Reusable Generator approach is out of private preview and publicly released. The Reusable Generator approach automatically creates a workflow to complete the requested data generation. This approach is especially useful to generate extremely large volumes of data. With the workflow, you can use the workflow to quickly create a smaller set of data to verify the overall structure before you generate the full set of data. The Data Agent can automatically switch to the Reusable Generator approach based on your request. You can also switch to the Reusable Generator approach from the mode selection dropdown list in the Data Agent prompt. The dropdown now includes both modes (Plan, Agent, Autonomous) and approaches (Single Dataset and Reusable Generator). Single Dataset is the default approach, which generates a single-use script to complete the task.
Workspace notifications - Within a workspace, you can now configure a list of notification destinations. A notification destination can be an email address, a Slack incoming webhook URL, or a Microsoft Teams incoming webhook URL. When a workflow job completes, fails, or is canceled, Fabricate sends a message to the enabled notification destinations for the workspace.
Project home page - The new project home page includes summary metrics for the project, the list of project databases and database connections, and the list of project workflows.
Account jobs - On the account home page, the navigation menu now contains a Jobs option to display the list of workflow jobs from across the account. The list includes the project name, workspace name, workflow name, and job status.
Using secrets from AWS Secrets Manager - A workspace secret can now be a secret from AWS Secrets Manager.
Default account models - Account owners can now specify the default models to use for data generation, validation, and freeform text generation. The new settings are on the AI page of Account Settings.
API key AI models and improved edit panel - The API key configuration now includes the models to use for data generation, validation, and freeform text generation when using the API key for calls to the MCP server. By default, API keys use the default models for the account. A new consolidated edit panel makes it easier to change the configuration of an API key.
Improved caching to reduce the number of tokens used.
You can now delete attachments from the Data Agent chat.
Account roles for API keys - You can now assign an account role (Owner, Auditor, Member) to an account API key, to manage the available actions that you can perform using the key. The API creation panel includes the role selection, and you can also change the assigned role for existing API keys.
The new Auditor account role allows an account user or API key to view all account workspaces, account settings, audit log events, and usage settings.
Improved the email message template that displays on mobile devices.
Improved support for PDF fonts.
Fixed an issue with creating .zip files for download.
External profiling skill - Added a new database profiling skill that you can install into an AI agent such as Claude or Cursor. You use this skill to create a profile of a database that is not connected to Fabricate. You can then add the profile to Fabricate to use for data generation. For example, you might want to create synthetic data that uses the same structure as a production database, but you do not want to connect the database to Fabricate.
You can now select GPT-5.6 Luna as the model to use for freeform text generation.
Made some small display improvements to the user interface.
Improved handling and display of domain names. Includes a new Allowed Domains tab on the account details panel displayed from the Admin Console.
When you configure your account to synchronize SSO groups, you can also choose to automatically create a new workspace for each new SSO group. The workspace has the same name as the group. You also select the workspace role to assign to the group.
A reference for the Fabricate OpenAPI API is now available at https://fabricate.tonic.ai/api.
The MCP server now provides access to account owner options to track account usage, AI usage costs, and audit logs.
Fixed an issue where an error was returned if an Agent conversation did not end with a user message.
Fixed an issue where OAuth failed when the users's preferred model was retired.
You can now use assumed roles for connections to AWS. On the workspace settings page, you set up a list of available IAM roles for the workspace. When you configure a server connection to PostgreSQL or MySQL, you can choose to use a role for authentication. The role trust policy must allow the Fabricate's principal to call sts:AssumeRole. On a self-hosted instance, you also set the environment variable FABRICATE_AWS_ASSUMER_ROLE_ARN to the assumer role for your Fabricate instance.
You can now use Azure service principals for connections to Azure-hosted databases. On the workspace settings page, you set up a list of available service principals for the workspace. Your Azure database must contain a Microsoft Entra ID user that is mapped to this service principal and that is granted the required permissions. When you configure a server connection to PostgreSQL, MySQL, or SQL Server, you can choose to use a service principal for authentication.
When you export a local database, you can now choose whether to export the entire database or only the currently selected table.
On the free tier, users who sign up with a business email address now receive a larger token allowance than users who sign up with personal email address.
Amazon Redshift support - You can now create server connections to Amazon Redshift.
Consistent UI for in-process server connection creation - Made the UI consistent for creating new server connections during database export and database connection creation. For both processes, you can now choose whether to add the new connection to the workspace server connection list.
Using CA certificates for connection authentication - You can now set up a list of available CA certificates for your account. On the server connection details, the TLS setting is replaced with an SSL/TLS dropdown. For PostgreSQL, Amazon Redshift, and MySQL, you can choose to use CA verification.
Fixed an issue with validating the form for pushing a database export to a database.
Fixed an issue where the Agent forgot uploaded files after it completed a context summarization.
The Data Agent now supports Claude Sonnet 5.
You can now display the timestamp for chat messages. To display the timestamp, hover the mouse over the message while you press the Shift key.
Fabricate now queues chat messages, so that you can continue to type new messages as the Agent processes previous ones.
Fixed an issue to ensure that the Agent has the correct database size limits.
Improved support for very large exports to Google BigQuery.
Other fixes and internal enhancements.
Validation agent - Plus and Enterprise users can now enable the validation agent for a Data Agent chat. The validation agent can analyze the quality of the Data Agent scripts (whether they will generate quality data) and the generated data itself. By default, validation is off. From the chat prompt, you can enable validation and set whether to check the scripts or only the data. Note that enabling validation increases the time to completion and the cost of the Data Agent requests.
Fixed an issue where the Data Agent provided incorrect guidance.
Fixed an issue where summarization of Data Agent conversations failed.
Other internal bug fixes and enhancements.
Local database size limit - Fabricate now enforces a limit on the volume of data in an individual local database, based on the license plan.
- Free plan - 256 MB
- Plus plan - 1 GB
- Enterprise plan - 5 GB
Fabricate displays a warning when the database size reaches 80% of the allowed maximum. Existing databases that exceed the limit are not truncated, but you can no longer add data to them.
Support for Azure Blob Storage - You can now set up Fabricate to allow the Data Agent to read from and write to Azure Blob Storage. You set up your Azure account as an allowed domain for the account, and the credentials (either an account key or a SAS token) as a workspace secret.
Added missing descriptions for audit log events.
Fixed an issue with workflows.
Fixed an issue where reverting to a previous point in one conversation deleted attached files in other conversations.
Project cloning - You can now create a clone of a project. When you clone a project, you can select the workspace for the new project, and choose whether to copy the chat history.
Added effort level to model selection - When you select the model for the Data Agent to use, you can also select the level of effort.
The Data Agent can now automatically spin up a sub-agent to perform and manage tasks. It currently uses a sub-agent for profiling.
Fixed a scrolling issue with the login page display.
Fixed an issue where exports to PDF failed because of unsupported fonts.
Fixed an issue where Fabricate attempted to use read-only mode on databases that did not support it.
Fix an issue where mock API request headers were not forwarded.
Limiting and tracking AI usage per user - From the Plan & Billing page on Account Settings, instead of a maximum overage for the organization, you now set the default AI usage limit for individual users for a selected period of time. The Users page now displays each user's AI usage for the current billing cycle, and allows you to override the default AI usage limit.
Fixed an issue where workflow selection was very slow.
Fixed an issue with restoring the Data Agent chat history.
When you log in to Fabricate, you now land on the project center. Users that only have one project land on the project details.
New users no longer automatically see the product walkthrough. It is an option on the welcome page.
When new users create a database, the first table is now selected automatically.
Improved telephone number generation.
Security enhancements.
Audit Log - Enterprise account owners can now enable and view an audit log of their account activity. You enable the audit log, and set how long to keep the audit log records, on the General page of Account Settings. The Audit Log page contains the log. It includes options to filter, sort, and download the log events.
Per-response feedback - In the Data Agent chat, you can now provide feedback (thumbs up or thumbs down) for each response. For a thumbs down response, Fabricate prompts you to provide additional information about why the response was not helpful.
Removing chat messages - You can now remove messages from the chat. Removing a message does not revert the associated changes. To remove a message, hover over the message and then click the delete icon. When you delete a message, you can optionally also remove all subsequent messages.
New home page with workspace and project lists - When you click Tonic Fabricate at the top left, Fabricate populates the navigation panel with a list of workspaces. Click a workspace to display the list of the workspace projects, or click All projects to view the list of projects across workspaces. The projects list for a workspace includes a link to workspace settings and indicates the users who have access to the workspace. You can get access to recently accessed projects and you can star projects for quick access.
API key expiration - You can now configure an optional expiration date for Fabricate API keys. The API keys list now masks the keys. To be able to use the key, you must copy the key when you create it.
Export to Kafka - You can now export Fabricate data to Kafka. You configure your Kafka broker as an allowed domain for your account. You then prompt the Data Agent to export data to Kafka. If you do not provide the information in the initial prompt, the Data Agent prompts you for the broker, authentication, topic organization, tables to export, and message keys.
Google BigQuery connection - You can now create data connections to and export local data to Google BigQuery.
From the LLM Provider Settings in Account Settings you can now select Google Gemini Enterprise Agent Platform (formerly Vertex AI) as your LLM provider.
When you create a new chat, you can now either fork the current chat or create a completely new chat.
Fixed an issue with sending .zip files larger than 4GB.
Fixed an issue with unexpected errors related to model providers.
Enhancements for improved security.
The chat usage tracking meter now updates in real time.
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.
Plan mode (Private preview) - The Data Agent now supports plan mode, where instead of immediately performing an action, the Agent assembles a plan to complete the action. The plan is added to the Plans list at the bottom left. When you're satisfied with the plan, you can execute it and return to regular Agent mode. While you can change to plan mode at any time, it is especially useful when you ask the Agent to create or update a large number of tables. The Agent automatically prompts you to switch to plan mode when you ask the Agent to create a database that contains more than 10 tables. Plan mode is currently in private preview. To request access to this feature, contact Tonic.ai.
For new databases, Fabricate now always uses Opus. It no longer uses Sonnet. Existing databases that use Sonnet will continue to use it.
Fixed an issue with sharing messages between chats.
Fixed an issue with context overflow after a large number of text files were attached to the chat.
For workflows, you can now include the required credentials for a required connection in the workflow request, either as a specific value ("use the secret My Secret to connect") or as a parameter to provide when you run the workflow. The domain must already be configured as an available domain in your account settings. Secrets must be configured in workspace settings.
For data that was created from a DDL with multiple schemas, Fabricate now correctly exports the data to the same schemas, instead of to a single schema.
When you select the push to database option for a Data Agent database export, you can now push to a MongoDB database.
Improved Data Agent handling of very large uploaded text files.
Workflows (currently in private preview) - In Data Agent, the workflows function allows you to create saved repeatable tasks that you can run against the database. For example, you might set up a workflow to add an additional set of records to the database. If the workflow requires calls to external domains, then you must also configure the available domains and provide credentials to access them. Workflows is currently in private preview. To request access to this feature, contact Tonic.ai.
Text files must now use UTF-8 encoding.
Improved messaging when the LLM is overloaded.
Fixed an issue where the progress bar for a task did not display when Amazon Bedrock was used.
Using your own LLM key - Enterprise customers can now configure Fabricate to use an LLM key that they provide. To enable this option, contact Tonic.ai. After the option is enabled, in order to use AI features such as the Data Agent, you must provide an LLM key. On the My Account page, under LLM Provider Settings, select whether to use Anthropic or Amazon Bedrock, then provide the LLM key. For Amazon Bedrock, you also specify the AWS Region.
The Data Agent can now ask multiple-choice questions to make it easier to clarify your requests.
Fixed an issue with message scrolling.
Improved name generation for Data Agent databases.
Fixed an issue where large DDL files could cause Fabricate to skip columns that contained default values.
Limiting AI usage overage - In the Current Plan section of the My Account page, the AI Usage Limit field allows you to set the maximum overage per billing cycle for your AI usage. This is the maximum cost in addition to the allowance that is included with your license plan. The default value is $500. To not have a limit, set the field to an empty value.
For Data Agent databases, primary and foreign keys are now identified by icons in the column headings.
When you create a Data Agent database, the initial prompt is now a displayed on a full page. After you provide the first prompt, the Data Agent chat moves to its regular position at the right of the page.
Fixed an issue with resetting passwords.
Improved handling of large DDLs.
Fixed an issue where stopped Data Agent messages did not immediately stop the response.
You can now clone a Data Agent database. To clone the database, hover over the database name at the left, then click the clone icon.
In the Data Agent chat, you can copy any of the Data Agent responses. Previously, only the JavaScript and SQL included a copy icon. To copy a response, hover over the response, then click the copy icon at the bottom right of the response text.
Improved Data Agent text generation.
The Fabricate Data Agent, which uses an AI chat to create and configure databases, is now available to all users.
As of now, all new Free and Plus accounts must use the Data Agent for all of their databases. The previous database configuration option, now referred to as rule-based databases, is only available to Enterprise users.
Fixed an issue where international addresses were assigned US street names.
Fixed an issue with opening an exported database file.