AI Foundations for Everyone – Part 2

Local AI, Private Workflows, and Practical Agent Systems

AI Foundations for Everyone – Part 2 is happening.

This follow-on course builds on AI Foundations for Everyone – Part 1 and moves into the next step in applied AI: running useful AI systems locally, protecting sensitive information, and building practical workflows that people can understand and control.

Part 1 focused on safe, effective AI use. Part 2 focuses on how AI systems can be connected, deployed, automated, and managed in more private, local, and realistic environments.

For registration, scheduling, or questions, please contact Workforce Development:

smccworkforcereg@mainecc.edu

Why Part 2?

Many people are now asking an important question:

How can we use AI while keeping more control over privacy, data, and infrastructure?

Part 2 answers that question by moving beyond cloud-hosted chat tools and introducing local-first AI concepts, including:

Local AI inference
Private document search
Retrieval-Augmented Generation, or RAG
Agent tools and tool-connected workflows
Lightweight model customization
Practical AI system design

The goal is not to turn everyone into an AI engineer. The goal is to help participants understand how modern AI systems can be used more safely, privately, and intentionally.

What Participants Will Explore

This course emphasizes practical, local-first AI architecture using affordable hardware, modern AI tools, and hands-on labs.

Participants will explore:

Running local language models
Using Ollama for local model access
Understanding inference servers
Building small RAG pipelines over private documents
Understanding when RAG is better than fine-tuning
Exploring LoRA and lightweight model customization
Using agent tools to inspect, reason, search, summarize, and assist with tasks
Understanding how AI agents connect to files, APIs, code, and workflows
Comparing local AI systems with cloud-based AI services
Thinking critically about trust, privacy, permissions, and human oversight

Participants will learn the difference between simply using AI and understanding how AI systems are actually connected, deployed, and controlled.

Hands-On Learning

A key part of this course is hands-on experience.

Lab work will include:

Running a local AI model on a Raspberry Pi 5
Using SSD storage instead of microSD for better reliability
Creating a simple private chatbot over local files
Building a local workflow that summarizes, classifies, or searches documents
Connecting AI to tools, files, and repeatable tasks
Exploring what agent tools can do safely — and where human judgment is still required
Understanding the strengths and limits of small local systems

The hardware is not the point by itself. It gives participants a real system they can inspect, manage, and understand.

Why This Matters

AI is moving quickly from simple chat into systems that can use tools, inspect files, write code, search data, call APIs, and assist with real work.

That makes AI more powerful — and also makes it more important to understand how these systems operate.

This course is especially valuable for people and organizations interested in:

Privacy-conscious AI use
Controlled local processing
Reduced dependence on external services
Better understanding of where data goes
Practical AI literacy beyond consumer chat tools
Agent-aware security and human oversight
More informed AI deployment decisions

For many organizations, this is the difference between using AI casually and understanding how AI can be deployed responsibly.

Intended Audience

This course is appropriate for:

Technical and non-technical professionals
Government and contractor staff
Educators and trainers
IT support and operations personnel
Analysts, builders, and curious professionals
Anyone who wants a deeper understanding of practical AI systems

No advanced coding background is required. Participants with technical experience will have room to go further, but the course is designed to remain approachable.

Expected Outcomes

By the end of the course, participants should be able to:

Explain the difference between cloud AI and local AI
Describe the role of inference, retrieval, agents, and tools in modern AI systems
Run and test local AI tools in a controlled environment
Build simple private AI workflows
Understand the purpose of RAG, LoRA, and lightweight customization
Explain how agents can connect to tools, files, APIs, and workflows
Identify basic risks around agent permissions, privacy, and automation
Make more informed decisions about privacy, infrastructure, and AI deployment

Registration

AI Foundations for Everyone – Part 2 is being offered as a follow-on course for people who want to go deeper into private, local, and practical AI systems.