Course Preview with Generative AI

Objective: Preview the major topics of the course by working through a set of Generative AI prompts, and practice using AI as a tutor that tests your understanding instead of doing the work for you. Estimated time: 2-3 hours. Due with the Info Sheet at the start of class 3.

This is the first assignment of the course, and it sets the pattern for the semester: you direct the AI, the AI helps you learn, and you curate the evidence of what you learned into a short report. AI assistance is welcome on homework, labs, and reports (with disclosure); it is not permitted on quizzes taken for a grade or on exams. You are the engineer of record for everything you submit.

Step 0: Set Up Your Tools

Choose a Generative AI assistant you will use this semester (e.g., ChatGPT, Claude, Gemini, or Copilot). A free tier may not be sufficient for a full semester of use.
Install the course TA skill in your assistant (instructions for Claude, ChatGPT/Codex, and Gemini are in the GitHub archive). It turns your AI into a course-aware TA that knows the schedule, the homework and special problems, the temperature control lab, the simulation lab, and the course AI policy. The prompts below work with or without it, but the TA skill gives more course-specific coaching.
Confirm your computing setup: MATLAB with Simulink (campus license or CAEDM remote lab) and/or Python with matplotlib, numpy, and scipy. AI assistants will write much of your code this semester, but these tools are how you run and verify it.
Bookmark the simulation and control apps - browser-based digital twins (tank level, blending, reactor, valve design, cascade, distillation, temperature control lab) used throughout the course to run experiments without writing code.

Step 1: Run the Topic Preview Prompts

Work through the six prompts below with your AI assistant, one topic at a time. Answer the AI's questions yourself before asking it for explanations. Copy each prompt as written, then engage in the conversation it starts.

Prompt 1 - Process Dynamics (Classes 3-6)

"I am a chemical engineering student starting a senior-level Process Dynamics and Control course. Act as a tutor. Using a real example (a stirred tank heater, or the thermal management of an EV battery pack), teach me what it means for a process to be 'dynamic' and what a 'time constant', 'gain', and 'dead time' are, without calculus. Then ask me 4 conceptual questions one at a time, wait for my answers, correct me with explanations, and end with a summary of what I should review. Do not reveal answers before I attempt them."

Prompt 2 - Modeling with Balance Equations (Classes 13-15)

"Quiz me on physics-based modeling for a senior process control course. Ask me 5 questions, one at a time, about conservation of mass and energy for a tank that is being filled and heated: what accumulates, what flows in and out, what assumptions make the model simpler, what happens at steady state, and why engineers linearize the resulting equations. Grade each answer, keep score, and finish by listing my misconceptions. Then show me the general balance form: accumulation = in - out + generation."

Prompt 3 - Feedback and PID Control (Classes 5-8)

"Explain the difference between open-loop and closed-loop (feedback) control using a shower temperature analogy, then tell me where the analogy breaks down. Then give me an explanation of proportional, integral, and derivative control action that contains ONE subtle conceptual error. I will try to find the error. After I answer, reveal it and explain why it matters when tuning a real controller."

Prompt 4 - Valves, Sensors, and Process Equipment (Classes 9-10)

"Act as a senior instrumentation engineer interviewing me for an internship. Ask me 4 practical questions, one at a time, about how a control loop touches real equipment: what a control valve's Cv rating means, what 'fail-open' vs 'fail-closed' means and how to choose for safety, why an oversized valve hurts control, and why sensors have accuracy limits and response lags. Correct my answers with brief explanations and give me an overall assessment at the end."

Prompt 5 - Laplace Transforms and Transfer Functions (Classes 16-19)

"I am about to learn Laplace transforms and transfer functions in a process control course. Without heavy math, explain WHY engineers transform differential equations into the Laplace domain and what a transfer function lets you do that a differential equation makes difficult. Use the analogy of logarithms turning multiplication into addition. Then ask me 3 questions to check that I understood the purpose (not the mechanics), one at a time, and correct my answers."

Prompt 6 - Stability and Advanced Control (Classes 28-40)

"In the second half of my process control course I will study closed-loop stability, cascade and feedforward control, and model predictive control. Using a modern example (a data center's cooling system, or fast-charging an EV battery without overheating it), explain in plain terms: why a feedback loop can become unstable if tuned too aggressively, what a second 'inner' control loop adds, and what it means for a controller to optimize over a prediction of the future. Then ask me 4 questions, one at a time, to check my intuition, and end with a personalized list of what I should watch for when these topics arrive."

Step 2: Test the AI's Engineering Judgment

AI assistants are confident even when wrong. Pick one of the exchanges above and push back: ask "What are the limitations of your explanation? Give a case where the rule you taught me fails." Then verify one specific claim from the conversation against an authoritative source - the textbook (Seborg et al.), the lecture notes, or a course page. Note whether the AI was right, incomplete, or wrong.

Step 3: Plan Your Prompts for the Semester

A good prompt is a small engineering specification with four parts: context (who you are, what system), task (exactly what you want), constraints (level, units, format), and verification (how the answer will be checked). The Machine Learning for Engineers course develops these with structured prompt builders: Agentic Workplan, Agentic Coding, Agentic Visualization, and Agentic Reports. Write two reusable prompts of your own that you plan to use in this course: one for learning a new concept and one for checking your homework solutions, each with all four parts.

What to Turn In

Submit a report (PDF, about 2-3 pages) that curates what you learned. You may use Generative AI to help write and format the report, but you must guide it to include correct content, and you are responsible for every claim in it. Answer these questions:

For each of the six topic prompts: what is one thing you learned and one question you answered incorrectly (with the corrected answer)?
From Step 2: what claim did you verify, what did you find, and what does this tell you about when to trust AI output?
From Step 3: include your two reusable prompts and explain how each part (context, task, constraints, verification) improves the response.
Which AI assistant did you choose for the semester, and what is one thing you noticed about how the quality of your prompt changed the quality of its teaching?
Include a screenshot showing your verification toolchain is ready: a MATLAB or Python plot from any short script (for example, the step response of dy/dt = -y + u).