patrickz
Before you start
A chat assistant and one project you can discuss publicly. Remove confidential material.
Why this lesson exists
The archived posts behind “I Turned My Job Search Into a Music Video” use a memorable artifact to start a conversation. A portfolio still needs to make the work and its evidence legible. The last step draws on the Interactive AI/ML Strategy Portfolio project write-up, which turns a case study into a page.
The idea this guide practices: I gave three AIs my LinkedIn archive. They built this website.
Do the exercise
Choose one relevant problem
Identify the reader and the decision they need to make. Select a project that demonstrates a capability relevant to that decision.
Collect receipts
Gather the original goal, your role, an output, a test result and a limitation. A prototype, a local render and a live deployment are different outcomes.
Write problem, choices and result
Ask for a concise narrative showing the tradeoff you made and what evidence changed your approach. Do not let the model invent business impact.
Make the artifact inspectable
Link a public demo or sanitized example when available. Add a short next-step note. Ask a reader to explain what you actually did after viewing it.
Publish it as a simple page
Put the case study on one static page before adding anything interactive. Add a diagram only when it helps comparison, and label proposed systems separately from deployed ones. Check every number and link.
A prompt to adapt
Replace the bracketed parts with your own details.
Write a project case study for [audience] using these receipts: [evidence]. Structure it as problem, my role, key decision, result, proof and remaining limits. Distinguish prototype from production. Flag unsupported claims and confidential details instead of filling gaps.
What this looks like
“Built a local prototype and tested three workflows” is stronger than “transformed an industry” when that is what the evidence proves.
Check your result
Use evidence from your output. A confident explanation from the AI is not enough.
If it isn’t working
If the case study becomes a list of tools, ask which decision the tools helped you make. Keep numbers only when you can explain how they were measured.
Optional. Progress stays in this browser.
Where this came from
Adapted from the archived LinkedIn theme “I Turned My Job Search Into a Music Video.” See the post coverage and editorial method.
Prepared September 2026. Tools and interfaces change; use current official setup instructions. Session lengths are estimates.