> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/changelog/2025.md). # 2025 All the Lleverage features, updates, improvements and fixes released in 2025 {% updates format="full" %} {% update date="2025-08-31" %} ## August 2025 #### **New Features** **Copilot 3.0 with Differential Updates** Major upgrade to our AI workflow assistant with intelligent change management and real-time collaboration features. * **Smart Diff System**: Visual representation of workflow changes with approval workflows * **Streaming Updates**: Real-time workflow modifications with live preview * **Validation Framework**: Automatic workflow validation with smart error correction * **Generation Controls**: Enhanced controls for workflow generation with stop/start capabilities
#### **Improvements** * **Activity Logging**: Comprehensive activity tracking with user attribution * **Environment Detection**: Automatic detection of workflow execution context * **Version Control**: Enhanced versioning with detailed change tracking * **Performance Analytics**: Advanced metrics for workflow optimization * **Operator Experience**: Streamlined interface for non-technical users #### **Bug Fixes** * Fixed workflow listing refresh issues after making changes * Resolved file extension handling in document processing * Improved canvas performance for complex workflow visualizations * Enhanced reliability of scheduled workflow executions * Resolved prompt editor cursor jumping issues when editing variables * Fixed workflow canvas lag after node manipulation * Improved favoriting system performance and reliability * Enhanced organization visibility and project access controls {% endupdate %} {% update date="2025-06-30" %} ## June 2025 #### **New Features** **Agent Node Integration** We've introduced powerful Agent nodes that bring advanced AI capabilities directly into your workflows, enabling more sophisticated automation scenarios. * **Intelligent Task Routing**: Agents can analyze and route tasks based on content and context * **Multi-Step Reasoning**: Execute complex logic chains within a single node * **Dynamic Tool Selection**: Automatically choose the best tools for each task * **Learning Capabilities**: Agents improve performance based on usage patterns **Enhanced Integration Support** Expanded our integration ecosystem with improved support for business-critical applications. * **Microsoft Outlook Enhancements**: Better email processing and attachment handling * **Slack Integration Improvements**: Enhanced message routing and channel management * **API Connectivity**: More robust API connections with better error handling * **Webhook Processing**: Improved webhook reliability and processing speed #### **Improvements** * **Workflow Templates**: New pre-built templates for common business processes * **Variable Management**: Enhanced variable system with better type detection * **Error Recovery**: Improved automatic error recovery and retry mechanisms * **Documentation Updates**: Comprehensive guides for all new features #### **Bug Fixes** * Resolved issues with PDF processing in UBL conversion workflows * Fixed attachment handling in Outlook integration workflows * Improved memory management for large dataset processing * Enhanced stability for long-running workflow executions {% endupdate %} {% update date="2025-05-31" %} ## May 2025 #### **New Features** **Enhanced Copilot Workflow Generation** We're excited to announce significant improvements to our AI-powered workflow generation system. The Copilot now creates more intelligent, connected workflows that better understand your business requirements. * **Smart Node Connections**: Improved logic for connecting workflow nodes automatically * **Context-Aware Generation**: Better understanding of user intent when creating complex workflows * **Validation & Error Handling**: Enhanced error detection and automatic correction during workflow generation * **Template Recognition**: Improved ability to generate workflows from natural language descriptions **Knowledge Base Integration** Introducing our new Knowledge system that allows you to define and store information within your workflows for enhanced context-aware processing. * **Dynamic Knowledge Nodes**: Store and reference important information across your workflows * **Contextual Retrieval**: Automatically pull relevant information based on workflow context * **Searchable Knowledge Base**: Quickly find and reference stored information * **Integration Ready**: Seamlessly works with existing workflow components #### **Improvements** * **Canvas Navigation**: Smoother panning and zooming experience in the workflow builder * **Node Discovery**: Enhanced node palette with better categorization and search functionality * **Performance Optimizations**: 20% faster workflow execution across the platform * **UI Polish**: Refined interface elements for better user experience #### **Bug Fixes** * Fixed issue where Copilot occasionally generated disconnected workflow nodes * Resolved canvas jumping behavior during workflow generation * Improved stability for complex workflow scenarios * Fixed variable completion suggestions scrolling behavior {% endupdate %} {% update date="2025-04-30" %} ## April 2025 ### New Features #### Co-pilot Editing Mode for Single Nodes We're excited to announce the latest updates to Lleverage, focused on enhancing productivity, improving the user interface, and expanding our AI model offerings. This release introduces powerful new co-editing capabilities and streamlined billing management. * Node-Level AI Assistance: Get specific help for individual nodes without regenerating the entire workflow * Contextual Suggestions: Receive recommendations based on surrounding nodes and workflow context * One-Click Implementation: Apply AI suggestions directly with a single click * Multiple Alternatives: Choose from several AI-generated options for each node configuration * Seamless Integration: Toggle co-pilot mode directly from any node for immediate assistance
#### Enhanced Home Dashboard We've redesigned the home experience to help you work more efficiently. * Personalized Workflow Overview: Easily access your most frequently used and recent workflows * Improved Analytics Visualization: Better insights into workflow performance and execution metrics * Streamlined Navigation: Redesigned interface for faster access to key platform features * Usage Highlights: At-a-glance view of your platform utilization and remaining credits * Customizable Dashboard Layout: Arrange your workspace to match your workflow
#### Payment Management Managing your subscription is now possible in the platform. * Centralized Billing Center: All payment information and history in one convenient location * Flexible Subscription Management: Easily upgrade, downgrade, or modify your plan * Automated Invoicing: Schedule and receive invoices automatically #### Expanded Model Selection We've added powerful new AI models to enhance your workflow capabilities. * OpenAI 4.1, 4.1 nano and mini: Advanced reasoning capabilities for complex workflow tasks * OpenAI o4-mini: Fast reasoning model with top tier capabilities * Gemini 2.5 Flash and Pro: New top tier models from Google. 2.5 Pro is the best out there at the moment * Improved Model Selector: Enhanced UI for comparing and selecting the optimal model for your needs ### Improvements * Performance Optimization: 15% faster workflow execution across the platform * Enhanced Error Handling: More informative error messages and troubleshooting suggestions * Workflow Analytics: Improved metrics for tracking workflow performance * Documentation Updates: Comprehensive guides for all new features ### Bug Fixes * Resolved intermittent connection issues with certain API integrations * Fixed UI rendering inconsistencies in the workflow editor * Addressed synchronization issues between workflow versions * Corrected variable handling in complex nested workflows Thank you for your continued support and feedback as we work to make Lleverage the most powerful workflow automation platform available. *The Lleverage Team* Posted: May 22, 2025\ Version: 2.8.0 #### #### {% endupdate %} {% update date="2025-03-31" %} ## March 2025 ### New Features #### Workflow Generation Co-pilot We're excited to announce our latest version of Lleverage with powerful new features that make AI workflow development faster, more intuitive, and accessible to users of all technical backgrounds. This release focuses on streamlining the workflow creation process and simplifying variable management. * Natural Language Generation: Describe what you want your workflow to do in plain language, and our AI co-pilot will build a complete, functional workflow for you * Intelligent Node Selection: The co-pilot automatically selects and configures appropriate nodes based on your description * Connected Architecture: Generated workflows include properly connected nodes with logical data flow and variable references * Best Practices Implementation: All generated workflows follow Lleverage best practices for organization and efficiency * Customization Ready: Use the generated workflow as-is or customize it further to meet your specific requirements This feature dramatically reduces the time needed to create new workflows, making AI automation accessible to team members of all technical levels. {% @arcade/embed url="" flowId="pX3cx9GoNLTpg7zfSMNY" %} #### Simplified Variable System We've completely reimagined how variables work in Lleverage, making them more intuitive and easier to use. * @ Symbol Variable Selection: Click the @ button in any input field to see and select from available variables without typing any special syntax * Visual Variable Browser: Navigate through available variables with a dropdown interface that organizes variables by their source node * Reduced Errors: Eliminate syntax errors and typos by selecting variables visually instead of typing them manually * Backward Compatibility: Traditional curly braces syntax (`{{variableName}}`) still works for users accustomed to the previous method * Contextual Awareness: The @ dropdown only shows variables that are actually available at that point in your workflow This update makes working with data between nodes significantly more intuitive, especially for new users. ### Improvements * Enhanced Performance: Optimized workflow execution with up to 30% faster processing times * UI Refinements: Cleaner interface with improved visual feedback during workflow building * Expanded Documentation: Comprehensive guides for the new co-pilot and variable features * Better Error Handling: More informative error messages when workflows encounter issues ### Bug Fixes * Fixed an issue where certain document types weren't properly processed in the document parser node * Resolved a timing problem that occasionally caused workflow version conflicts * Corrected variable scope issues in complex branching workflows * Fixed several UI rendering glitches in the workflow canvas for large workflows ### Looking Ahead We're continuing to enhance the Lleverage platform with upcoming features focused on: * Expanded integrations with popular enterprise services * New specialized AI models for industry-specific use cases * Advanced workflow analytics and monitoring tools * Enhanced collaboration features for team-based workflow development Thank you for your continued support and feedback. We look forward to seeing what you build with these new capabilities! *The Lleverage Team* Posted: March 21, 2025\ Version: 0.9.0 #### {% endupdate %} {% update date="2025-02-28" %} ## February 2025 ### New Features #### Knowledge Base System We're excited to announce significant improvements to Lleverage that enhance document processing capabilities and workflow usability: * Replaced Vector Stores with new Knowledge Base system * Intelligent AI-powered document chunking * Automatic Weaviate vector store integration * Improved document processing pipeline #### New Search Capabilities * Added Web Search node for real-time internet searches * Enhanced search configuration options * Integrated search results processing ### Workflow Improvements * Introduced Output Chips for easier output visualization and copying * Improved node output management * Enhanced workflow debugging capabilities These updates significantly improve document handling capabilities while making workflows more intuitive and easier to develop. The new Knowledge Base system provides a more streamlined approach to document processing, while Web Search and Output Chips add powerful new tools to your workflow building toolkit. *The Lleverage Team* Posted: February 11, 2025\ Version: 0.8.0 {% endupdate %} {% update date="2025-01-31" %} ## January 2025 ### Enhanced Tools and Nodes #### Improved Web Scraper Node We're excited to introduce significant improvements to Lleverage that enhance workflow creation, user interface experience, and expand our tools for working with different types of content. Here's what's new: We've revamped our web scraper node (based on Firecrawl) to make data extraction more intuitive: * Streamlined Interface: Simplified configuration options for faster setup * Enhanced Preview: Better visibility of extracted data during configuration * Improved Error Handling: Clearer feedback when issues arise during scraping #### New OCR Node We're introducing Optical Character Recognition (based on Google Vision) capabilities to help you work with image-based text: * Text Extraction: Convert text from images into machine-readable format * Multi-format Support: Process various image formats including PNG, JPEG, and scanned PDFs * Layout Preservation: Maintain original text formatting and structure where possible ### Workflow Apps #### Form and Chat Interfaces Transform your workflows into interactive applications with our new app creation features: * Form Apps: Create structured input forms for your workflows: * Custom field configuration * Responsive design * Easy sharing via unique URLs * Chat Interface: Build conversational experiences: * Natural dialogue flow * Context preservation * Real-time response streaming #### App Customization * Branding Options: Customize the look and feel to match your organization * Access Control: Set up password protection and user authentication * Flexible Deployment: Choose between public and private access ### UI Improvements We've made several updates to enhance the overall user experience: * Cleaner Interface: Refreshed design for better visual hierarchy * Improved Navigation: More intuitive workflow building experience * Enhanced Performance: Faster loading times and smoother interactions These updates make it easier than ever to create, deploy, and share your AI workflows. The new app creation capabilities, in particular, open up new possibilities for making your workflows accessible to end-users through intuitive interfaces. We're excited to see how you'll use these new features to build even more powerful and user-friendly AI solutions. *The Lleverage Team* Posted: January 14, 2025\ Version: 0.7.0 {% endupdate %} {% endupdates %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.lleverage.ai/changelog/2025.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.