Product Release Notes - February 2025

• Seamless Navigation Across CreateAI Apps: Users can now seamlessly click on links within MAB to access other CreateAI Lab apps like Model Comparison and ASU GPT.
• Updated all tooltips/help messages to user-friendly language including publishing project, enabling knowledge base. 
• Enabled LLM API output to a structured format for models that support it.
• Enhanced MyAI Builder interface with improved user guidance on how to build an AI project. 
• Added new models to the platform: Gemini 2.0. Deprecated Gemini 1.0.
• Fixed error with file upload toggle not saving.
• Fixed errors with displaying math symbols in AI input/output.

Product Release Notes - January 2025

• Improved Access Control for Private Bots: Private bots are now hidden from unauthorized users, and access is denied if permissions are not granted. 
• Enhanced Collaborator Management: Users can now search, filter, sort, and bulk-select collaborators in the Share Panel, making it easier to manage access and permissions efficiently. 
• Dynamic Model Management: Model configurations are now fetched from the backend, eliminating hardcoded constants and reducing manual updates for a smoother, more reliable experience.
• Starred projects appears at the top of project list. 
• Automated Welcome Emails for New Users: New users now receive a welcome email upon gaining access to any CreateAI Toolkit product, providing login details, access links, and support resources for a seamless onboarding experience.

Product Release Notes - December 2024

MyAI Builder Updates:

• AI Help Button: Rolled out an in-app AI-powered Help Button for easier support and navigation assistance.
• File Metadata Tracking: Enabled metadata extraction for up to 36 file formats, including DOCX (page numbers), PPTX (slide numbers), and CSV (row numbers).
• Document Upload for Conversations in ASU GPT and MAB: Introduced the ability for users to upload documents or images exclusively for a single conversation. These uploads are temporary and do not persist in the Knowledge Base.
• Skills & Jobs Matching: Introduced the ability for students to upload their resumes via the ASU Pockets API in the mobile app to receive a list of relevant skills based on their qualifications and experience.
• Dynamic User Role Management: Launched an API for updating user roles via an intuitive dropdown interface, simplifying team role management.
• Improved Sharing Management in MyAI Builder: Introduced a dedicated and easily accessible "Share" button in the app header, allowing users to efficiently manage project sharing permissions. Users can invite collaborators or viewers via ASURITE IDs, view existing permissions, and delete multiple accounts with confirmation prompts.
• Improved Security Controls: Introduced stricter access controls to prevent unauthorized users from accessing ASU GPT environments.

Product Release Notes - November 2024

CreateAI Platform Updates

• Completed Lambda function for Skills API integration, vectorizing 32,000 skills with automated weekly updates (finalized in December).
• Updated API Key Management infrastructure for key generation, revocation, and enhanced authentication.
• Resolved workflows for Lightcast Skills API, ensuring seamless taxonomy metadata updates (finalized in December).
• Released Multi-Function Calling in the Agentic Framework, supporting complex API workflows with caching and rate limiting.
• Enhanced MyAI Builder interface with improved modal design, advanced/basic tab navigation, and clearer text.
• Expanded ASU GPT with all AI models for broader usage and better model selection.
• Optimized HR Document Vision for improved paper document extraction in BFIT projects.

Product Release Notes - October 2024

MyAI Builder Updates

• Role-Based Access Controls: Simplified user permissions and improved collaboration workflows.
• Content Ingestion: Flexible content ingestion and extended data integration capabilities.
• Released Gemini Pro 1.5

CreateAI Platfom:

• Improvements to system observability across all AI services for resilience under high-demand conditions.
• Upgraded monitoring tools to ensure resilience and reliability under high-demand conditions.

Beta Access Management

• Released advanced tools for managing beta requests, enabling precise team alignment and streamlined onboarding.

Product Release Notes - September 2024

MyAI Builder Enhancements

• Improved usability for both Basic and Advanced settings management.
• Launched version 1.1 with new Knowledge Base and URL ingestion capabilities, providing flexible content integration options.

CreateAI Toolkit Upgrades

• Introduced automated role-based access controls, simplifying user permissions and improving collaboration workflows.

AI Model Updates

• Added new models to the platform: OpenAI O1, OpenAI O1 Mini, and Gemini Pro 1.5.
• Enhanced the Model Comparison beta feature, allowing side-by-side testing of different AI models for better evaluation.

Platform-Wide Observability Improvements

• Upgraded system monitoring and observability tools to ensure resilience and reliability under high-demand conditions.
• Enhanced infrastructure visibility across LLM services for improved performance and stability.

MyAI Builder Release Notes - August 2024

• Multimodal Support: Easily send prompts by uploading images and text, enabling richer, more engaging interactions with the AI.
• Voice-to-Text: Conveniently send prompts using voice commands for a hands-free experience. 
• Prompt Mode: Users can now choose to use their own data exclusively or combine it with the system's language model knowledge for more advanced prompting capabilities. This provides greater flexibility and control over the input data used for AI projects.
• Advanced Fields Support: New, advanced configurations provide greater flexibility and control over your data, enabling you to tailor your AI projects to specific requirements. 
• Semantic Caching: Enjoy quicker response times thanks to optimized LLM usage, reducing redundant calls and enhancing overall performance.
• Search Type: Choose how you want your search results—either as detailed chunks or full documents.
• Increased user load capacity: Improved LLM throughput capacity and backend infrastructure to support thousands of concurrent users across all models.
• Improved Source Citations Accuracy: Enhanced precision in source citations allows users to locate original data sources more quickly, including direct links to websites and specific page references in lengthy documents.

ASU GPT Release Notes - August 2024

• Voice-to-Text: Conveniently send prompts using voice commands for a hands-free experience. 
• Prompt Mode: Users can now choose to use their own data exclusively or combine it with the system's language model knowledge for more advanced prompting capabilities. This provides greater flexibility and control over the input data used for AI projects.
• Whitelist Access Control: Implemented strict security measures allowing only authorized users on the whitelist to access and use the app, ensuring maximum protection of sensitive data and resources.
• Sustainability Information: Display leaf icon next to models to add visibility to sustainability/impact related to model

Model Comparison Release Notes - August 2024

• Whitelist Access Control: Implemented security measures allowing only authorized users on the whitelist to access and use the app, ensuring maximum protection of sensitive data and resources.

CreateAI Platform Release Notes - August 2024

• Multimodal Support: Seamlessly integrate various media formats like images, audio, and text into your AI projects. Upload multiple images alongside text input to enable image analysis and generation capabilities. Additionally, handle audio data for audio input and output, opening up possibilities for voice interactions.
• Scalable Backend: Improved LLM throughput capacity and backend infrastructure to support thousands of concurrent users across all models. Includes load testing and collaboration with AWS and GCP to validate token limits and load
• Ethical AI Evaluation: Assess the performance and ethical standards of your AI models and applications with our comprehensive Ethical AI Engine. This powerful tool utilizes advanced language models to evaluate factors like response accuracy, processing speed, and hallucination tendencies, bias, discrimination, and handling of sensitive content.