Speaker Topics - No Fluff Just Stuff
NFJS2025

AI for App Development

This hands-on workshop teaches developers how to build modern AI-driven applications using local LLMs, intelligent agents, and standardized tool protocols. Participants learn to move beyond simple prompting to architect production-ready AI systems that integrate reasoning, retrieval, and external data sources. The course emphasizes real-world implementation through step-by-step labs in GitHub Codespaces, requiring no local installs.

By the end of the workshop, attendees will have created functional AI agents that use Ollama for local model execution, FastMCP for standardized tool communication, and RAG (Retrieval-Augmented Generation) for context-grounded responses—all deployable to Hugging Face Spaces.

The course begins with an explanation of running models locally with tools like Ollama and LangChain. Participants progressively advance through seven structured labs covering the following topics :

1.Running Models Locally: Using Ollama to pull, serve, and query models such as llama3.2 via CLI, API, and Python integration.
2.Creating Agents: Building a reasoning agent that uses the Thought → Action → Observation loop to call weather APIs.
3.Exploring MCP (Model Context Protocol): Implementing standardized tool discovery and invocation through a FastMCP server-client setup.
4.Vector Databases: Indexing and searching local data with ChromaDB to enable semantic search and similarity matching.
5.RAG with Agents: Combining retrieval and reasoning so agents can access relevant context from external data sources.

    6.    Streamlit Web Application – Wrap the RAG agent in a modern web UI using Streamlit, complete with a memory dashboard, real-time status, and visual feedback.
  1. Deploying to Hugging Face Spaces – Publish the Streamlit app to a live, shareable web environment, learning how to authenticate, push, and auto-deploy projects for public access.

Each lab reinforces the previous one, culminating in a fully functional, classification-driven RAG agent that demonstrates multi-domain reasoning, semantic search, and modular design.


Brent Laster

About Brent Laster

Hi, I'm Brent Laster - a global trainer and book author, experienced corporate technology developer and leader, and founder and president of Tech Skills Transformations LLC. I've been working with and presenting at NFJS events for many years now and it is always exciting and interesting.

Through my decades in programming and management,I've always tried to make time to learn and develop both technical and leadership skills and share them with others Regardless of the topic or technology, my belief is that there is no substitute for the excitement and sense of potential that come from providing others with the knowledge they need to help them accomplish their goals.

In my spare time, I hang out with my wife Anne-Marie, 4 children and 2 small dogs in Cary, North Carolina where I design and conduct trainings and write books. You can find me on LinkedIn (linkedin.com/in/brentlaster), Twitter (@brentclaster) or through my company's website at www.getskillsnow.com.

More About Brent »