13 minutesHow to Use Copilot to Automate Meeting Notes in Microsoft Teams!
Design a meeting workflow that captures transcripts, summaries and action items without losing human review.
Play videoAndrej Karpathy. The creator lists a "ChatGPT memory, custom instructions" chapter at 1:53:29. Use the personal workflow as a discussion example alongside the article's distinction between response defaults and retained context; current memory behavior must be checked separately.
Keep reusable preferences non-sensitive. Current behavior may differ by version, region and workspace setting. A memory summary is not a complete inventory, and deleting a chat, removing remembered information and opting out of training are separate actions.
Understand how a power user separates durable preferences from one-off context.
Know where custom instructions and memory live in your current ChatGPT settings.
Last reviewed: May 18, 2026
Continue through the same learning path with the next curated companion videos.
13 minutesDesign a meeting workflow that captures transcripts, summaries and action items without losing human review.
90 minutesUse AI for research, structure and revision while keeping final wording and judgment under human control.
35 minutesBuild a source-grounded research notebook and turn it into briefings, study guides or working notes.
Hand-picked external courses that go deeper on this topic.
Dr. Jules White
The academic complement to DeepLearning.AI's short course — same discipline, longer arc, written for people who don't code. Dr. White teaches prompting as a set of reusable patterns (Ask for Input, Outline Expansion, Fact Check List, Menu Actions) rather than tricks. After this you'll prompt LLMs like a designer, not a guesser.
Isa Fulford · Andrew Ng
Ninety minutes to a year's worth of intuition. If you've started writing code that calls an LLM — or you're about to — this is the most efficient course online for closing the gap between "playing with ChatGPT" and "shipping a feature that calls an LLM."
Microsoft Learn
Prompt engineering, but for the tool most office workers will actually touch first. Microsoft's own four-part prompting framework (goal, context, source, expectation) is a genuinely useful mental model, and unlike the generic ChatGPT prompting courses already in our catalog, this one is grounded entirely in Microsoft 365 Copilot's specific quirks and grounding behavior.