An organization wanted staff using Copilot in Excel. The real risk wasn't getting an answer; it was trusting a wrong one. I designed a 6-lesson course where every skill ends with a check, then prototyped it in two Articulate formats so the client could compare before development.
The method behind every lesson
Copilot can write a formula or summarize a table in seconds. In a budget or a shared report, a confident wrong answer costs more than the time Copilot saves.
Teach staff to use Copilot in Excel for formulas, data cleanup, analysis, and charts.
Build a verification habit: prompt it, then prove it, every time, before a result is shared.
Before building anything in Articulate, I prototyped the same six lessons in both formats. The client could click through each one and choose the experience that fit their learners, before any development time was spent.
I also rebuilt the course in Mindsmith, an AI course-authoring tool, starting from my own outline, to test how far an AI authoring tool can take a well-designed course. The result is an 8-section lesson with a timed "one-minute decision" scenario, tabs comparing Copilot's chat, plan, and edit modes, and a closing activity where learners write the prompt and the verify check they'll use this week.
Learners practice the judgment, not just the prompts. Both formats share these decisions.
"Prove it" checks follow the practice in both versions, such as reading the formula Copilot wrote in the formula bar or checking one row by hand.
Why: Repeating one habit in different tasks is what makes it automatic.Every example uses one fictional budget workbook. Learners run a prompt and see exactly what Copilot adds or changes.
Why: Safe practice with no license, no real data, and no risk of breaking a file.Rise learners find the mistake in a plausible Copilot answer. Storyline learners match prompts to tasks, choose the right chart, and sort strong prompts from weak ones.
Why: Choosing between options builds the judgment that a prompt list alone can't.Learners choose which Copilot mode fits each task, through Maria's scenarios in Rise and a matching activity in Storyline, then review a plan before a multi-step build.
Why: Matching control to risk is the judgment call the job actually requires.The same six lessons in both formats, each with hands-on practice and a knowledge check. The Rise version adds a wrap-up and final assessment.
Tour the workspace, write and explain formulas, and troubleshoot errors.
Highlight, sort, filter, format, and clean data with prompts.
Ask questions of the data, then refine the answer with follow-up questions.
Choose the right chart, then build charts for reports.
Choose between chat, plan, and edit modes, then practice a multi-step build.
Five habits that keep results accurate and data secure, then key takeaways.
The Rise and Storyline versions are rapid prototypes for client review before development in Articulate, built with Claude Code for a fictional company, Acme Financial. The Mindsmith version is my AI authoring experiment.
I designed the course, the practice activities, and the assessment, and reviewed every lesson. I used AI (Claude and Claude Code) as a build partner to turn the design into two clickable prototypes, one styled like Rise and one like Storyline, for client review. Separately, I tested Mindsmith, an AI course-authoring tool, by generating a version of the course from my outline and refining it.
I'd love to help your people use them well, and know when to double-check.
Let's talk