Version 3.7.2 - Comments, Code and Chat Update
Agent
- Fix Button: Objects with resolution Errors will now have a “Fix Error” button that sends the error to the Agent to be fixed. Users can accept or reject the proposed fix
- Send to Agent Button: Objects with TBD resolution status will now have a “Send to Agent” button which will add that object to the chat. Users should then provide the Agent with context for how to resolve the TBD
- The Davinci Agent now has a new look, occupying one section of the new Right Panel
- Davinci can now generate code in any specified language. The Agent will default to Python if no language is provided. Be explicit if you want Davinci to generate code that is not Python
New Features
Revised Right Panel
The Right Panel is now not only for Agent Chat. We’ve added a few new features here to improve usability and model awareness for users- Agent View: This is where Chat lives. Users can now paste images (png/jpg/webp) from their clipboard into chat to provide the Agent with extra visual context
- Error View: The new error view in the Right Panel shows all Model Objects with resolution Errors and all TBD Objects. Users can click on each card to view the Object and manually resolve, or select “Fix Error” or “Send to Agent” to resolve. Filter by Errors or TBDs using the buttons at the top of the view
- Search View: A new way to search your model! Instead of relying on the top bar to search, users can now have a more persistant search area here. Search by Object name, key values, Tags, and more. Search will even show you everywhere an Object is referenced in the model
- Comments View: Read more about comments below! The Comments view allows users to manage all comments in the model from one central view. See all comments posted by you in the “My Comments” tab. Easily see a list of all comments in which you are directly mentioned in the “Mentions” tab. Or simply view all comments in the model in the “All Comments” tab.
Comments
- Added Model Object Comments
- Users can now leave comments on Model Objects with notes for the future, requests for review, or any other use case
- Collaborators can be directly mentioned within comments using the @ search feature within comments
- Other Model Objects can be directly mentioned within comments as well
- Comments can be marked as “Resolved”, which will remove them from being tracked in the “All Comments” tab of the Comment View
Other Updates
- Cleaned up Index right click menus
- Added ability to paste images from clipboard into chat for one-time context to the Agent. Pasting unsupported file types in chat will offer to upload them as a Reference Object instead
- Better constrained Select All Functionality (CTRL+A/CMD+A) to be more focused on appropriate content
- Improved copy/paste from chat output, allowing Object references to be rich-copied within Davinci and converted to text outside. Formatting between messages is maintained
- Added support for arbitrary code language generation and storage within the Model. Code execution is still limted to Python (for now)
- Code block output in chat and Code Objects can now be copied easily with one button click
Bug fixes
- Fixed issues with running Python code
- Fixed issues with unit resolution in Attributes
- Fixed an issue with some tooltips in the interface
- Fixed a layout issue with sending pasted text to the Agent via chat
Previous Releases
These release notes incorporate key features from these previous releases, along with new improvements and bug fixes- 3.7.1 - October 14 2025
- 3.7.0 - October 8 2025
Version 3.6.2 - Task, Resource and Risk Update
Agent
- Davinci can now create Task Objects, allowing you to define timelines, due dates, meetings and more, right in your Model
- Davinci can create Risk Objects, automatically analyzing the model for potential risk and identifying them into new, customizable risk categories
- Davinci can create Resource Objects, letting you quantify cost, usage and man-hours for any task, program or event. Resource Objects can keep track of both money and inventory of materials
New Features
- Task, Resource and Risk Objects added as Object types
- Task, Resource and Risk Object unique views, such as Gantt chart, Resource Pie Chart, and Risk view
- Added exporting for all new unique views
- Added Risk category editor inside Project View
Bug fixes
- Fixed bugs related to right clicking multiple objects in the Index
- Redesigned some chat bubble styles for spacing considerations
- Fixed issue related to restoring first message of chat after session reload
- Fixes related to documents and tables
Previous Releases
These release notes incorporate key features from these previous releases, along with new improvements and bug fixes- 3.6.1 - September 26 2025
- 3.6.0 - September 18 2025
Version 3.5.2 - Tags and Matrix Update
Agent
- Davinci can now create Tags when generating or updating model objects. Automatically organize your model using these Tags
New Features
- Tagging has been added to Objects. You can now add custom tags to categorize model objects and create custom Matrix views
- Matrix Object: Create dynamically populated tables using Matrix objects. Create rules for how to populate the tables programatically
- Tooltips have been added in many places and improved in others to increase function discoverability. Most buttons should now have a tooltip appear on mouse hover
Bug fixes
- Fixed several bugs related to the Index
- Fixes for bugs in Table objects
Previous Releases
These release notes incorporate key features from these previous releases, along with new improvements and bug fixes- 3.5.1 - August 26 2025
- 3.5.0 - August 20 2025
Version 3.4.1 - Multimedia Update
New Features
- Davinci now has a built in video and audio player
- Your workspace state is now saved and restored between sessions
Bug fixes
- Several key bug fixes for documents and Tables
- Improved loading of chat and other consistent
- Other small bug fixes and performance improvements
Version 3.3.0 - Multi-Workspace Redesign
Agent
- Image Processing: Improved detection and extraction of data from images in PDFs
- Table Editing: Resolved problems with editing large Tables and targeting correct rows for changes
- Object Movement: Fixed AI-assisted Object movement
New Features
- Text within PDFs is now selectable
- Refinements to the new Index, including better Package collapsing
- Implemented “safe triangels” to right click menus in the Index
- Added Markdown support for Davinci Chat and Agent responses
Bug fixes
- Fixed bug related to adding References to Objects
- Fixed bug related to Search functionality
- Fixed image file size bug
- Fixed a bug preventing Tags from being opened from within Chat
- Stability improvements to both frontend and backend
Version 3.2.0 - Markdown Support
Agent
- Image Processing: Improved detection and extraction of data from images in PDFs
- Table Editing: Resolved problems with editing large Tables and targeting correct rows for changes
- Object Movement: Fixed AI-assisted Object movement
New Features
- Text within PDFs is now selectable
- Refinements to the new Index, including better Package collapsing
- Implemented “safe triangels” to right click menus in the Index
- Added Markdown support for Davinci Chat and Agent responses
Bug fixes
- Fixed bug related to adding References to Objects
- Fixed bug related to Search functionality
- Fixed image file size bug
- Fixed a bug preventing Tags from being opened from within Chat
- Stability improvements to both frontend and backend
Version 3.1.0 - Agent Toolboxes
New Features
Davinci Toolboxes
Toolboxes allow Davinci Agents to execute custom, user defined instructions- Davinci Agents can now use Toolboxes to assist with tasks
- Toolboxes allow Davinci Agents to execute custom, user defined instructions
- Users can create custom Toolboxes within Davinci
- Toolboxes are created using Python scripts
- Toolboxes can be exported as MCP Servers
- Users can test Toolbox functionality before allowing Agent use
- Agents will automatically choose appropriate Toolboxes when performing tasks
- Toolboxes can be deactivated to prevent automatic Agent use as desired
- Toolboxes and custom Code Objects can save files to the Project as Reference Objects
- Toolboxes and custom Code Objects can update existing Attribute Object values
Index Redesign
The Index has been reworked to add new functionality and a higher level of polish on existing functions- Rearranging Elements within the Index is now smoother and more consistent
- Redesigned the Drop Indicators when moving Index Elements
- Known Bug: Drop Indicators for Index Elements sometimes do not adhere to parent/child restrictions and will show invalid drop locations
- Redesigned the Drop Indicators when dragging external Files into the Index
- Files will now be uploaded to the nearest parent Package object
- File destinations are now indicated by a light box surrounding the Package that will contain the Reference Object after File upload
- File uploading now adheres to the parent/child restrictions imposed on Reference Objects
- Index Elements can now be dragged into the Workspace to open new Tabs
- Known Bug: If multiple Index Elements are dragged into the Workspace at once, only the first Object will be opened
Improvements
- Better overlay and feedback when dragging Files into Davinci
- Files can be dropped anywhere on the Workspace or Chat when in the Model Area to upload them directly to the Library
- Files can be dropped in the Index to upload them directly to a specific Package
- Inactive Files can now all be cleared at once with a new button in the Files Tab
- Note: Clearing inactive Files may cause compatibility issues with Snapshots that use them
- Read more about Inactive Files here
- Stability and Reliability improvements to Snapshots
- Known Bug: If a Snapshot takes more than 5 seconds to apply, the User may be redirected back to the Home screen until the Snapshot is fully applied. Re-open the Project once the Snapshot is fully applied.
- Improvements to Agent Display
- Agent Tool Inputs and Responses are now viewed directly in chat instead of a separate window
- Removed the split view previously used for Agent Responses
- Added a Checkpoint system to Agent Conversations
- Added ability for the User to Undo individual Agent Actions
Changes
- Removed ability to duplicate Reference Objects
Bug fixes
- Fixed a bug related to deleting multiple Model Objects at once
- Fixed a bug related to client-side Model Database traversal
- Fixed a bug related to resizing Workspace Panes via double clicking Tab headers
- Fixed a bug that allowed Reference Objects to be children of other Reference Objects
- Several fixes to internal command routing and AI performance
- Several backend fixes for performance and stability
Version 3.0.0 - Agents
Agent Capabilities
- Introduced Design Agent capabilities
- Added multi-agent support with concurrent agent execution
- Added agent tool calling
- Temporarily removed AI ability to create geometries and assemblies
Code & Output
- Improved AI generation of code
- Drastically improved code execution reliability
- Added ability to save figures from output as images
Document Features
- Improved AI document generation
- Overhauled manual editing in documents
- Added ability for AI to create documents with images
Table Features
- Substantial improvements in AI table creation and editing
- Tweaked manual table interactions
Presentation Features
- Added slide object
- Added ability for AI to create slides
File Management
- Added ability of agent to save files from a URL
- Added ability of agent to extract images from PDF files
- Added ability of agent to save figures from code output as images
Action System
- Rebuilt action definitions
- Added sequence view to actions
- Improved management of three.js instances
Project Area
- Added relationships to project area
- Tweaked project area views
- Tweaked project area file table
- Added upload file button to file tab
UI Improvements
- Enhanced collaboration features
- Improved right click menus