Day 1
Exercise 1 Prompt Engineering
Prompts are the directives we give to large language models (LLMs). Prompts are in human language but can include math, files, spreadsheets, images, and audio.
Oscar will guide you in developing prompts.
Exercise 1A Legal Predictions
A key aspect of staying ahead of AI developments will be the law. Let's get an LLM to predict its future in the eyes of the law!
Use the following prompt with ChatGPT.
"You are a corporate lawyer with 15 years of experience. Can you predict the next 3 specific laws on AI likely in 2-5 years, for companies, based on this White House executive order? Describe what a company Sr. PM should do today to prepare. Compare and contrast the two executive orders provided below for how to pivot. Answer in one sentence max. per prediction. https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/ and https://www.whitehouse.gov/presidential-actions/2025/01/removing-barriers-to-american-leadership-in-artificial-intelligence/ "
Specific Examples:
Gold Standard Answer
Assign a Role
Proofread and ask it to double check its answer
Specify a word limit, and specify context
Short Menmonic: BAG: Best Answer, Assumptions, Goal
Exercise 2 Under the Radar: Catching AI Results
Go to GPTZERO and test the following two inputs. What are your findings?
Test 1: "As we gear up for the upcoming M&A deal, I want to know your top three agenda items for the week. Let me know what you need, and I'll make sure there are no roadblocks."
Test 2: "As we gear up for the upcoming M&A deal, I want to know your top three agenda items for the week. Let me know what you need, and I'll make sure there are no roadblocks. Time to get things moving. Let's do it team! Could you assist with this? We need access ASAP to stay on track. "
Cohort 1: Make a prompt with the 5 elements for predictions on your own industry regulations.
Exercise 3 Uploading Documents
A key aspect of project management is project-specific organizational structure. As PMs we often craft this structure on an ad-hoc basis. There are two files below: a PDF and an image. Download both to your computer.
A) Upload the below PDF into ChatGPT (model 4o).
B) Use the following prompt with ChatGPT.
"Summarize this document, including the arrows between people. Ask questions if unclear."
C) Close the window and start a new conversation.
D) Upload the below image into ChatGPT (model 4o).
E) Use the following prompt with ChatGPT.
"Summarize this document, including the arrows between people. Ask questions if unclear."
CASE 1 Microsoft vs. Mayo Use Copilot in Edge and Chat GPT:
Do the following in Copilot and ChatGPT 4:
1) Open the below page in a new window.
Type: “read this page” and hit enter in the chat box at the bottom right.
The window should show you “Let’s not save this conversation” Select "Okay"
Type: "What does this file say, in 5 bullet points, about how Microsoft protects company data?"
Type: "What are 3 key differences in how Microsoft and the Mayo Clinic implement data privacy and data terms?"
Cohort 1: Ask what are examples of security breaches in Copilot within the last two years.
DEMO 1 Email Review
Co-Pilot and AI Demo Experience
Please open the following files and use Copilot in Edge or ChatGPT:
Email #1
Type: "Summarize the 8 main action items from the email on this page, and who is accountable for each."
Type: "Number each action item and make a table showing who is accountable for which item number."
Type: "Didn't someone ask to make a meeting?"
Nobody is named in this email chain - there are no names only roles. If you see a result with names, select "Answer from this page instead" in the suggested bubbles below the answer.
Email #2 (below)
Type: "Draft a reply to the email on this page that makes use of bullet points, a timeline for implementation, and that is succinct but provides real references."
Email #3 (below)
Type: "Review the email on this page and estimate which of the senders might be a hacked sender account based on the email, take a guess and take it step by step."
DEMO 2 Bias
Use the following prompt:
"A doctor yells at a nurse because she was late. Who was late?"
Note the answer.
Now click the refresh button on the top right.
Use the following prompt:
"A doctor yells at a nurse because he was late. Who was late?"
How do your answers differ?
Navigate to ChatGPT. Use the following prompt:
"Can you code a simple machine learning model in Python that takes as input hundreds of invoice amounts, vendors, and dates, and output predictions for the next invoice amounts and dates?"
And then use the following prompt:
"How do I set up Python on my machine, as a complete beginner, step by step?"
And finally, this prompt:
"Are you capable of running Python?"
A) Follow instructor guidelines in Workflow wizard: https://chatgpt.com/g/g-685d405c716081919227965b4d5f4979-workflow-wizard
Data analysis with large language models (LLMs)
3) Ask Copilot the following:
4) Now download the file, upload to ChatGPT and use the same prompt.
5) How would you ask ChatGPT / Copilot to help analyze the visual graphic below the table?
DEMO 7 POWER BI Expert
Your AI acts as every technical manual in the world. Ask the following:
"I would like to make a PowerBI dashboard but I have no experience. Help me build a PowerBI dashboard, that takes in Excel data and displays graphic KPIs based on what I say. I am a complete novice and have never used PowerBI and don't know how to open it. Guide me step by step in extreme detail. Use the most updated instructions. Ask me for expectations and assumptions.
DEMO 8 Success Stories & Risk Pro
Access the Risk Pro Demo Here
Make sure you are logged into ChatGPT
DEMO 9 Nightshades - Hidden AI languages
Try uploading the following file to ChatGPT. It contains Open AI-generated 'watermarks' not allowing the model to parse it.
DEMO 10 Custom AI Roadmaps
This Roadmap test will auto-generate an AI roadmap for you and your organization. The Roadmap includes the AI Value Matrix , and Change Ready! Principles.