Agentic AI in Python - A Code Walkthrough

Curious how to bring agentic AI to life using Python? Want to see how Semantic Kernel can orchestrate real-world AI behavior?

In this hands-on session, we’ll walk through the code necessary to build a Python-based product Q&A chatbot that goes beyond basic RAG implementations. You’ll see how to give your AI agent the ability to:

Pull product data from a vector store
Enhance RAG answers with live web search
Evaluate hallucination risk
Respond with a trust score for transparency

We’ll explore how Semantic Kernel enables agentic behavior; and, along the way, you’ll learn how to ground responses in multiple data sources and implement an evaluation loop to keep your AI honest.

If you're a developer looking to move from experimentation to real-world AI applications, this session will give you the tools, patterns, and confidence to build smarter, more reliable agents in Python.

Frontiers of Large Language Model-Based Agentic Systems Construction, Efficacy and Safety (Oct '24)

Large Language Models (LLMs) have recently demonstrated remarkable potential in achieving human-level intelligence, sparking a surge of interest in LLM-based autonomous agents. However, there is a noticeable absence of a thorough guide that methodically compiles the latest methods for building LLM-agents, their assessment, and the associated challenges. As a pioneering initiative, this tutorial delves into the intricacies of constructing LLM-based agents, providing a systematic exploration of key components and recent innovations. We dissect agent design using an established taxonomy, focusing on essential keywords prevalent in agent-related framework discussions. Key components include profiling, perception, memory, planning, and action. We unravel the intricacies of each element, emphasizing state-of-the-art techniques. Beyond individual agents, we explore the extension from single-agent paradigms to multi-agent frameworks. Participants will gain insights into orchestrating collaborative intelligence within complex environments. Additionally, we introduce and compare popular open-source frameworks for LLM-based agent development, enabling practitioners to choose the right tools for their projects. We discuss evaluation methodologies for assessing agent systems, addressing efficiency and safety concerns.

Tutorial initially delivered October 2024 at ACM CIKM ‘24, proceedings for which can be found here: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (https://dl.acm.org/doi/pdf/10.1145/3627673.3679105). See https://frontiers-of-ai-agents-tutorial.github.io/ for more information.

United Way Women Leveraging AI for Good at Work and Home (Oct '24)

Can the possibility of AI positively support women to take new opportunities, reduce burnout, build confidence, and give you more time to spend on the 'big rocks' of your day? Microsoft says yes! The key is using new generative AI tools intentionally in your work and home life to create more efficiency, reduce workload pressure and deadlines, and enhance your ability to manage time in a way that works for you.

See https://events.unitedway.org/website/76458/agenda/ for a recap of the conference agenda.

Agentic AI Introduction (Global AI Community, NJ Chapter, 07/25)

What exactly is agentic AI, and why is it reshaping how we think about intelligent systems?

In this introductory session, we’ll demystify the concept of agentic AI—AI systems that can reason, plan, and act autonomously within defined boundaries. Whether you're a developer, architect, or tech leader, this session will help you understand what’s possible today and how to start building agentic systems yourself.

We’ll cover:

* Understanding Agentic AI: What it is, how it differs from traditional AI, and why it matters
* Exploring the Art of the Possible: Real-world use cases and emerging patterns
* Getting Technical: Key components like orchestration, memory, planning, and grounding
* How to Get Started: Tools, frameworks (like Semantic Kernel), and practical next steps

If you're curious about the future of AI and want a clear, actionable introduction to agentic systems, this session is your launchpad.