AI-101 · Foundations

AI Fluency — Prompting, Evaluation, and Workflow Integration

Required for all majors →

Teaches students to work effectively with AI tools across all professional contexts. Covers prompting techniques, critical evaluation of AI output, building AI-augmented workflows, understanding the AI tool landscape, AI ethics and responsible use, and code/technical literacy for non-developers. This is the foundational course that every other Core and Domain course builds on.

30 Hours
10 Learning objectives
Create Bloom's ceiling (?)
6 Competencies

Learning Objectives

Objectives

Depth
  • Apply structured prompting techniques to generate useful first drafts for professional documents, code, and analysis Apply
  • Evaluate AI-generated output for hallucination, factual errors, logical flaws, and tone mismatches using systematic verification methods Evaluate
  • Design reusable prompt templates for recurring professional tasks, incorporating role context, output format, and quality constraints Create
  • Analyze when AI assistance adds value vs. introduces friction for a given task, documenting decision criteria Analyze
  • Use AI as a just-in-time tutor to rapidly acquire unfamiliar domain knowledge, verifying accuracy against authoritative sources Apply
  • Assess a new AI tool's capabilities, limitations, pricing, and data handling practices within 30 minutes Evaluate
  • Identify ethical concerns in AI usage: bias in output, disclosure obligations, privacy risks, and responsible deployment boundaries Analyze
  • Read AI-generated code at a conceptual level, verifying it accomplishes the stated task without executing unintended operations Understand
  • Interpret error messages, stack traces, and technical outputs well enough to describe problems to technical colleagues Understand
  • Explain the current AI tool landscape — coding assistants, writing tools, image generators, analysis tools — and articulate how it is likely to evolve Understand

Levels: Remember · Understand · Apply · Analyze · Evaluate · Create — highest demands most original thinking.

10 sessions. Here’s what you’ll do.

  1. 01

    What AI Is Actually Doing (and Why That Matters)

    Free trial

    Real examples of how LLMs generate through pattern completion. Map the AI landscape and capture your baseline thinking before AI influence.

    Exercise: First Map
  2. 02

    Your First Real Prompt — Build Something You’ll Actually Use

    Free trial

    Learn prompt construction using five components. Choose your tool, build a reusable prompt, and test it with different inputs.

    Exercise: Build a Real Prompt
  3. 03

    Making AI Output Useful — Documents, Analysis, and Code

    Prompt for documents, analytical reasoning, and code. Learn the document editor workflow — generate, paste, edit, and annotate.

    Exercise: Three Output Types
  4. 04

    AI Output Evaluation — Detecting Hallucination and Factual Errors

    Systematic method for evaluating AI output: mark claims, verify against sources, identify errors, and write a corrected version.

    Exercise: Red Team a Response
  5. 05

    AI Output Evaluation — Logic, Tone, and Contextual Judgment

    Beyond factual errors: evaluate logic flaws, tone mismatches, and context blindness across three dimensions.

    Exercise: Evaluation Practice
  6. 06

    Your Portfolio Site — Tool Evaluation Through Building Something Real

    Learn a 30-minute tool evaluation framework. Evaluate hosting platforms and AI tools by capabilities, limitations, pricing, and data handling. Build and deploy your portfolio site.

    Exercise: Tool Evaluation + Portfolio Build
  7. 07

    AI Ethics — Real Decisions, Not Philosophy

    Practical ethics through scenarios: disclosure norms, bias detection, privacy in AI use, and responsible deployment boundaries.

    Exercise: Ethical Scenarios
  8. 08

    Building AI Into Your Real Life

    When to use AI, when not to. Map AI integration into three real tasks — heavy use, selective use, no use — with verification and risk assessment.

    Exercise: AI Integration Map
  9. 09

    Reading What AI Writes — Technical Literacy

    Minimum viable technical literacy: read AI-generated code, spot problems, interpret errors, and ask for help — without being a developer.

    Exercise: Code Reading Workshop
  10. 10

    Portfolio Completion and Course Synthesis

    Complete your AI Workflow Audit portfolio artifact. Review your First Map from Session 1, document growth, and assemble the final portfolio piece.

    Exercise: AI Workflow Audit

What You'll Master

AI Prompting & Iteration

Crafting effective prompts, multi-turn refinement, context management, output format specification.

AI Output Evaluation

Detecting hallucination, verifying facts against sources, assessing quality and completeness.

Workflow Integration

Knowing when, where, and how to insert AI into professional workflows; calibrating AI use by task type.

AI Tool Landscape

Evaluating new tools, building a personal tool stack, adapting as tools evolve, tracking emerging capabilities.

AI Ethics & Responsible Use

Bias recognition in AI output, disclosure norms (when to tell stakeholders AI was used), data privacy (never paste PII/PHI without safeguards), responsible deployment boundaries.

Technical Literacy

Reading code at a conceptual level, understanding AI-generated code output, interpreting error messages, understanding version control concepts as a collaborator.

What You'll Build

AI Workflow Audit — Document your AI-assisted workflow for a real task from your life or target career: the prompts used, output evaluation decisions, corrections made, ethical considerations, and a reflection on where AI helped vs. hindered. Includes a comparative evaluation of 2-3 AI tools for the task with a recommendation.

Industry Tools, Not Toy Projects

Claude

Anthropic's AI assistant for writing, analysis, coding, and research tasks with strong reasoning capabilities.

ChatGPT

OpenAI's conversational AI for drafting, brainstorming, and general-purpose assistance across professional tasks.

GitHub Copilot

AI coding assistant integrated into code editors. Used in demonstration mode to understand AI-generated code output.

Midjourney / DALL-E

AI image generation tools. Used in demonstration mode to understand the AI creative tool landscape.

Google Sheets

Spreadsheet tool used for data tasks, analysis exercises, and organizing AI evaluation results.

Code Editor

Read-only exploration of code environments to build conceptual understanding of AI-generated code.

Prerequisites & What's Next

Prerequisites

  • None — this is an entry course

Ready to start learning?

Your first 2 sessions are free. No credit card. Start building AI fluency today.

Start Session 1 Free
Free · 30 seconds to set up · No commitment