Embedded Files
Day 1
Success and Failure - How to distinguish them:
CASE 0 Actions vs. Risks
Scan and summarize the following links for common risks regarding AI models taking action.
Case 0.1 AI Models TAKING ACTION:
Generative AI Lawyer: Source 1 Source 2, Amazon hiring, Meta Galactica, Agents Everywhere?
Case 0.2 AI Models identifying risks for HUMAN ACTION:
McKinsey: Dubai Eye Health, McKinsey Lilli, Palantir AIP, Blackstone Aladdin
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!
Exercise 2 Under the Radar: Catching AI Results
True story: A hedge fund manager receives an email:
"Please forward $2.8 Million to the following account. The CEO has already approved as you see below. I would need this within the next 3 hours due to tax."
She has a gut feeling this is not real, but everything looks valid. How would you proceed?
Exercise 3 Agentic Modifying Project Documents
A key aspect of project management is project-specific document structure. As PMs we often craft this structure on an ad-hoc basis. We will now use AI to create a Project Charter using only an Email Chain between executives.
A) You will be given a link to a Copilot chat below. Copilot has been given 1) a project charter template, and 2) an email chain with all relevant information.
B) Ask Copilot to "Fill in the Project Charter".
Exercise 4 Agentic Modifying Project Documents Part 2
Question for you to discuss in groups: how can we modify prompts to ensure accuracy?
Exercise 5 Context is Key: Learning from an Architect
(Video)
DEMO 1 Online & Excel AI
DEMO 1 Online & Excel AI
We can use the Logistics Curve to predict numerical project outcomes like budget and schedule. We provide you a tool at the following page, and an Excel sheet where you can edit for yourself!
We can use the Logistics Curve to predict numerical project outcomes like budget and schedule. We provide you a tool at the following page, and an Excel sheet where you can edit for yourself!
CASE 1 YOUR CUSTOM GPTS
Choose a topic of professional interest:
CASE 1.1 Email Review
Co-Pilot and Custom GPT Experience
Please use the Copilot links provided below
Quick Email Analysis
Ask: "Number each action item and make a table showing who is accountable for which item number."
Then Ask: "Didn't someone ask to make a meeting?"
CASE 1.2 I Can Code? And Create AI?
CASE 1.2 I Can Code? And Create AI?
Navigate to Copilot. 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?"
CASE 1.3 Data & Budget Analysis
CASE 1.3 Data & Budget Analysis
Data analysis with large language models (LLMs)
Let us now analyze numerical project data. The below table has already been loaded into the following link. In the copilot chat simply enter "yes" to the question.
Demo 1.1 Agentic Analysis Bias
Do the following in Copilot:
1) Open the below link that contains legal Microsoft Terms for Copilot Use and Mayo Clinic Terms for Health Data use.
Type: "Summarize"
Compare with your group - are the answers exactly the same?
AI Usability Quiz
AI Usability Quiz – Fill out form
Page updated
Google Sites
Report abuse