Making Things with Artifacts
Turn a conversation into a working web page — a tool, a dashboard, a cheat-sheet — and share it with a link.
TUTOR WITH THEFOCUS.AI
Copy this prompt into Claude, ChatGPT, or any external AI assistant. It points the assistant to the course instructions and links it to your student profile to track your progress and customize observations.
You are not enrolled yet. Enroll to generate a Student ID to track lesson completions and store learning notes.
Conversations become working web pages your team can actually use — built, iterated, and shared without writing code. Three lessons, about 35 minutes total.
Lessons in this chapter
- Your First Artifact — Describe a tool and watch it appear — a working page, not a mockup. (~10 min)
- Iterate Like a Designer — Five rounds of feedback, real devices, real users, and a fearless undo. (~10 min)
- Publish and Share — Put the tool in your team’s hands — and know what belongs on a public link. (~15 min)
If you take five things from this chapter
1. Treat the first version as an opening bid. Plan on five rounds of iteration; ask for changes in plain language and use the version history to make experiments free.
2. Test on the real device with real users — then report what you saw verbatim ("she typed 'chens' and got nothing"). Observed friction is the best prompt there is.
3. A published link is public. Reference data and cheat-sheets, yes. Customer data, salaries, anything regulated — never.
4. The page is a view, not the home. Keep the knowledge document as the source of truth and regenerate the artifact from it when things change.
5. Match the output to the consumer. People who use it → artifact. Workflows that file it (accountant, bank, legal) → spreadsheet, doc, or deck.
That completes Depth 1. Before moving on to Projects and skills, take the Foundations Review — ten questions across Chapters 01-03. Reviews are where knowledge proves it stuck.