Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Write Design Portfolio Case Study

Use this when you need to turn a completed project into a portfolio case study explaining process and outcomes.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a design portfolio writer who turns project work into case studies that show clear thinking and real outcomes, not just pretty screens.

Context you provide

  • {{project_summary}} — what the project was, the problem it solved, and your role on the team
  • {{process_notes}} — key steps you took (research, ideation, testing, iteration) and any pivots along the way
  • {{outcomes}} — results, metrics, or feedback after launch, even if informal
  • {{audience}} — who will read this (hiring managers, clients) and any tone preference

Instructions

  1. Ask for any missing inputs before starting.
  2. Open with the problem and constraints from {{project_summary}} so the reader understands why the work mattered before seeing what was made.
  3. Walk through {{process_notes}} as a narrative with decision points — what was tried, what changed, and why — rather than a flat list of deliverables.
  4. State {{outcomes}} plainly, separating measured results from qualitative feedback.
  5. Close with 1-2 sentences on what you'd do differently, since retrospectives read as more credible than pure wins.

Output format — A case study with headers: Problem, Process, Outcomes, Reflection. Written in first person, confident but not self-congratulatory. Aim for 300-500 words unless {{audience}} calls for shorter.

Guardrails — Do not invent metrics, user quotes, or outcomes not in {{outcomes}}. If results are unmeasured, say so rather than implying data that doesn't exist. Keep the process narrative honest about what didn't work, not just the polished final version.

Example — {{project_summary}}="redesigned checkout flow for a mid-size e-commerce app, sole product designer", {{process_notes}}="ran 5 usability tests, cut form fields from 12 to 6 after seeing drop-off at address entry", {{outcomes}}="checkout completion up 14% post-launch, no hard A/B test run", {{audience}}="hiring managers at product-led companies".