Level 1: Beginner — Foundations

This level is for people with zero or minimal AI experience. No technical background needed. By the end, you’ll have a mental model for what AI tools are, how they work at a high level, and the confidence to start using them.

1.1 What Is AI?

AI tools like ChatGPT, Claude, and Grok are large language models (LLMs) — systems trained on vast amounts of text that can generate human-like responses to prompts. They’re powerful for drafting, summarizing, brainstorming, and analyzing — but they don’t “know” anything. They predict useful text based on patterns.

Key concepts:

• Prompt — What you type in. The quality of your prompt determines the quality of the output.
• Context window — How much information the AI can consider at once. Think of it as working memory.
• Hallucination — When AI generates plausible-sounding but incorrect information. This is why verification matters.

Exercise 1.1: First Conversation

Open any AI tool (ChatGPT, Claude, or Grok — all free):

Prompt: "Explain what a large language model is in two paragraphs. 
Use an analogy that would make sense to someone with no technical 
background."

Then iterate:

Follow-up: "Now explain the limitations. What should someone know 
about what AI gets wrong?"

Industry variant (healthcare): Try the analogy prompt with “Use an analogy that would make sense to a nurse or clinic administrator.”

Reflect: How did the second response change? What did the AI add when you asked it to focus on limitations? This is the beginning of prompt iteration — a skill you’ll build throughout this program.

1.2 Why AI at Work?

AI isn’t replacing workers. It’s eliminating the repetitive, time-consuming tasks that pull you away from higher-value work. Think of it as a drafting assistant that works instantly.

Where AI adds value (non-sensitive tasks):

• Drafting communications (emails, newsletters, customer-facing materials)
• Summarizing long documents (policies, guidelines, meeting notes)
• Research and synthesis (industry data, best practices)
• Brainstorming and planning (program design, workflow improvements)

Where AI does NOT belong:

• High-stakes decisions without human review
• Anything involving real personal or confidential data
• Final-version documents without human review

Exercise 1.2: Identify Your Use Cases

Prompt: "I work in [your industry] as a [your role — e.g., 
operations, administration, IT, marketing]. What are 10 ways I 
could use AI to save time on routine tasks? Be specific and 
practical."

Industry variant (healthcare): “I work in healthcare administration. What are 10 ways I could use AI to save time on non-clinical tasks?”

Reflect: Which of these could you try this week? Pick one and note it — you’ll come back to it in the Capable level.

1.3 Your First Useful Output

Time to produce something you’d actually use. Pick one of the exercises below — whichever matches your role:

Exercise 1.3a: Draft a Communication

Prompt: "Draft a professional email to staff announcing a new 
initiative. The tone should be encouraging but not preachy. Keep 
it under 200 words. Include a clear call to action."

Iterate: Ask the AI to adjust tone, length, or audience. Try: “Make it more casual” or “Rewrite for a technical audience.”

Industry variant (healthcare): “Draft an email announcing a new wellness initiative for clinical staff.”

Exercise 1.3b: Summarize a Document

Find a publicly available document relevant to your work (a government guideline, industry report, or published policy). Paste the text and prompt:

Prompt: "Summarize this document in 5 bullet points. Focus on 
what's actionable for my organization."

Industry variant (healthcare): Summarize a publicly available CMS fact sheet or Joint Commission standard. Focus on what’s actionable for compliance.

Exercise 1.3c: Research a Topic

Prompt: "What are the current best practices for employee 
onboarding? Summarize the top 5 recommendations from recent 
industry literature."

Industry variant (healthcare): Research best practices for patient safety culture or staff wellness programs in healthcare settings.

Compliance note: Verify the output. Check at least one claim against a real source. This builds the verification habit early.

1.4 Checkpoint

Before moving to Capable, you should be able to answer yes to these:

• I can explain what an LLM is in my own words
• I understand why AI outputs need verification
• I’ve used an AI tool to produce something useful
• I’ve iterated on a prompt at least once to improve output
• I’ve read and understood the Safety Guidelines

Fluency slope check: How has your perception of AI changed from before this level? What would you try next?

Ready to apply what you’ve learned? Try the Expense Report Builder capstone project.