Hands-On Workshop: Building Advanced AI Applications and Agents in One Hour

ACM Distinguished Speaker Series
Title: A Hands-On Workshop: Building Advanced AI Applications and Agents in One Hour
Speaker: Mehdi Bahrami – Santa Clara, CA, United States
Date/Time: Friday | 11:30 AM – 1:00 PM

AI systems are rapidly evolving from simple prompt-based tools to autonomous agents capable of perception, reasoning, and action. But how do you move from concept to deployment responsibly and efficiently?

In this ACM Distinguished Speaker Series session, we shift from discussion to construction.
This interactive workshop will guide participants through the design and implementation of advanced AI applications and AI agents using state-of-the-art Large Language Models (LLMs) and Vision Language Models (VLMs). Together, we will explore how modern AI systems are architected, tuned, and deployed in real-world environments.
Rather than focusing on hype, this session emphasizes architecture, design tradeoffs, scalability, and ethical deployment.

***

Distinguished Speaker
Mehdi Bahrami
Santa Clara, USA
Dr. Bahrami brings deep expertise across Artificial Intelligence, Machine Learning, Human-Computer Interaction, Computer Vision, Natural Language Processing, Information Systems, Search & Retrieval, Data Mining, and Applied Computing.

***

What We Will Build and Explore
Participants will work through core components of advanced AI application design:

• Selecting and working with open-source models
• Understanding Python package requirements and development environments
• Leveraging LLMs and VLMs for: Natural Language Understanding (NLU); Text and image generation; Decision-making workflows; Task automation
• Designing AI agents (language agents vs. vision agents)
• Integrating external data sources
• Fine-tuning and parameter optimization
• Architecture design for scalability and efficiency
• Ethical and responsible deployment considerations

The workshop adapts to audience background, ensuring relevance whether you are an engineer, researcher, product leader, or systems architect.

***

Format
This is a guided, hands-on technical workshop.
Technical Framing (15 mins)
AI application architecture and model selection
Live Build + Guided Implementation (45 mins)
Agent design, model integration, tuning, and deployment considerations
Architecture & Ethics Discussion (15 mins)
Scalability, efficiency, and responsible AI tradeoffs
Q&A and Closing (15 mins)

***

What to Expect
You will leave with:

• A working mental model for building full-stack AI applications
• Practical understanding of LLM/VLM integration and agent design
• Clarity on tuning, deployment, and scaling considerations
• Insight into responsible AI architecture decisions

***

About Responsible Tech
Responsible Tech is an ACM-sponsored forum for practitioners examining how AI systems are designed, deployed, and governed in real-world contexts where trust, safety, and accountability matter.

This event is virtual and will be held from 11:30 AM to 1:00 PM US Central Time (CST).