CreateAI Office Hours Details: Get Help and Share Feedback

We’re excited to share how you can connect directly with the CreateAI team for live support, feedback, and community learning. Our weekly office hours are designed to help both general users and our dedicated beta testers get the most out of CreateAI Builder.

Faith Timoh Abang

September 2, 2025

Wednesdays: Beta Testing & Early Feedback (12–1 PM AZ time)

Wednesdays are dedicated to our beta testers , a group of builders who help us shape the future of CreateAI. In these sessions, testers:

Try out new features before they launch
Share feedback and report bugs directly to the CreateAI team
Influence what improvements go into production

Everyone is welcome to join these sessions, but the focus will be on beta testing and product feedback. Join Wednesday Beta Office Hours

Fridays: General Support & Community Help (12–1 PM AZ time)

Fridays are open to the entire ASU CreateAI community. These sessions are perfect for anyone who wants to:

Get help with CreateAI projects
Learn tips and best practices
Connect with peers and see how others are using CreateAI
Troubleshoot issues in real time with the support team

If you’re new to CreateAI or just need a space to ask questions, Friday office hours are for you.
Join Friday General Support Office Hours

Why Office Hours Matter

CreateAI is a community-driven platform. Your ideas, feedback, and questions are what help us improve. By joining office hours, you’re not only getting support, but also helping shape the future of AI at ASU.

We look forward to seeing you at our next session whether it’s Wednesdays for beta testing or Fridays for general support.

Keep Reading

Falling words in various depths of field resembling AI code

Breakdown of RAG Model Parameters, Settings and Their Impact

Kofi Wood

January 1, 2025

Retrieval-Augmented Generation (RAG) is an advanced approach in natural language processing that integrates information retrieval and generative language modeling. Unlike traditional language models that generate responses solely based on their pre-trained knowledge, RAG combines retrieval mechanisms with generative models to enhance the relevance and accuracy of its responses. This hybrid framework works by first retrieving relevant documents or information from a predefined knowledge base (e.g., databases, documents, or PDFs) and then using a generative model (such as a transformer-based model) to synthesize a response that incorporates the retrieved context.