[Steve Side Hustler]

I have a pile of raw notes—user interview highlights, meeting minutes, and quick sketches—and I want to turn them into a clear, honest UX case study for my portfolio. I’m not very technical and would prefer a beginner-friendly, practical approach that uses AI tools to speed things up without losing accuracy or my voice.

Could you suggest a simple AI workflow (step-by-step) that covers:

• Order of steps (e.g., extract insights, draft narrative, refine visuals)
• Tool types or specific friendly tools for each step
• Sample prompts or templates I can copy and tweak
• Editing and fact-checking tips so the case study stays accurate and authentic

If you’ve done this yourself, please share a short example workflow or a couple of prompts that worked well. Practical, non-technical answers and common pitfalls to avoid are especially welcome—thanks!

[Jeff Bullas]

Nice focus — wanting a repeatable AI workflow is exactly the right move. Turning messy notes into a clear, persuasive UX case study is about structure, not magic. I’ll give a tight, practical workflow you can implement today.

What you’ll need

• Raw notes: interviews, screenshots, sketches, metrics, and timestamps.
• An AI writing tool (GPT-4-style) and a text editor.
• A simple case-study template: problem, role, process, solution, impact.
• 10–30 minutes for each iteration (do-first mindset).

Step-by-step AI workflow

1. Ingest: Paste raw notes into the AI in chunks (don’t overload the model). Label each chunk: Interview A, Usability test notes, Metrics.
2. Extract key points: Ask the AI to list user quotes, pain points, goals, and surprising findings.
3. Map to structure: Convert those extracts to headings: Problem, Research, Insights, Design decisions, Outcome.
4. Draft sections: Prompt AI to write each section in plain language — one section at a time. Keep sections short (3–6 paragraphs).
5. Create visuals brief: Ask the AI for 3 visual suggestions (wireframes, flow diagram, before/after screenshot callouts) and alt text.
6. Edit for voice & accuracy: Rewrite phrases to match your voice, verify metrics and quotes against original notes.
7. Format & polish: Add headings, bullets, callouts, and a TL;DR summary. Run a readability check.
8. Final review: One read-through to confirm facts, then export for portfolio or presentation.

Practical prompt you can copy-paste

Use this with your AI tool. Replace bracketed items.

Prompt (main):

“You are an expert UX writer. I will paste raw research notes and artifacts. Extract user problems, key quotes, and primary insights. Then draft a 600–800 word UX case study using this structure: 1) TL;DR (2–3 sentences), 2) Context & my role, 3) Problem & goals, 4) Research & key findings (include 3 direct quotes), 5) Design decisions & prototypes, 6) Outcome & metrics, 7) Lessons learned. Use a professional, conversational tone aimed at hiring managers. Provide 3 suggested visuals with short captions. Keep factual items in brackets and flag anything you’re uncertain about.”

Prompt variants

• Concise: “Summarise these notes into a 300-word case study with headings: Problem, Research, Solution, Impact.”
• Detailed: “Create section-by-section drafts. For each section, give a headline, 3 bullets, and a 60–90 word paragraph.”

Example (before → after)

Before: messy interview notes listing frustrations about onboarding and slow load times. After: TL;DR + 2 user quotes + design changes (progressive onboarding, reduced assets) + 40% lift in activation.

Common mistakes & fixes

• Over-trusting the AI: Always verify quotes and numbers against originals.
• Too much fluff: Ask AI for concise summaries and bullet lists.
• Losing your voice: Edit the draft to match your tone and role.

Simple 3-step action plan (today)

1. Gather and label your notes (30 min).
2. Run the main prompt on one chunk and create the TL;DR (20 min).
3. Iterate section-by-section, verify facts, finalize visuals (60–90 min).

Do this once and you’ll see how quickly a raw pile of notes becomes a compelling case study. Small iterations, real outputs — that’s the win.

All the best,Jeff

[aaron]

Good point — structure is the lever. Your step-by-step workflow is solid; here’s a tighter, KPI-first version that turns raw notes into a hiring-ready UX case study with measurable outcomes.

Problem

Raw research is messy. Hiring managers decide in seconds — you need a repeatable path from notes to narrative that proves impact, not just process.

Why it matters

A clear, outcome-focused case study converts attention into interviews and offers. Recruiters look for context, decisions, and measurable impact — give them that fast.

My key lesson

Use the AI to extract facts and draft structure; use you to verify and quantify. AI speeds drafting. You guarantee truth and voice.

What you’ll need

• All raw artifacts (notes, timestamps, screenshots, metrics).
• An AI editor (GPT-4-style) and a simple case study template.
• 10–30 minute focused iterations.

Step-by-step workflow

1. Chunk & label: Split notes into Interview A, Usability B, Metrics, Screenshots.
2. Extract facts: Run the main prompt (below) on one chunk. Get quotes, pain points, and exact metrics.
3. Map to headings: Create Problem, Role, Process, Decisions, Metrics, Lessons.
4. Draft section-by-section: Ask AI to write one section at a time; keep each to 60–150 words.
5. Visual brief: Ask for 3 visuals + alt text and a short caption for each.
6. Verify & quantify: Cross-check quotes and numbers against originals. Replace approximate claims with exact figures or [estimate].
7. Polish voice: Edit to your tone; shorten sentences for scannability.
8. Export & test: Publish a PDF/portfolio page and time how long a reader needs to get the impact (target: < 60s).

Metrics to track

• Time-to-first-impact (how long until reader sees the outcome) — target <60s.
• Interview request rate from portfolio views — baseline and lift.
• Clarity score: % of readers who correctly state the problem & outcome (informal user test).

Common mistakes & fixes

• Over-trusting AI: Fix — verify quotes/metrics; flag anything uncertain in brackets.
• Too much process: Fix — lead with outcome and decisions, not methodology.
• Vague metrics: Fix — use absolute numbers and percentages with dates.

Copy-paste AI prompt (use as main)

“You are an expert UX case study writer. I will paste raw research notes and artifacts. Extract: 1) three user pain points, 2) three direct user quotes, 3) key metrics (with units and dates). Then draft a 450–650 word case study using headings: TL;DR (2 sentences), Context & my role, Problem & goals, Research & key findings (include 3 quotes), Design decisions & prototypes, Outcome & metrics (be explicit), Lessons learned. Flag any data you can’t verify with [UNVERIFIED]. Tone: professional, outcome-focused for hiring managers. Provide 3 visual suggestions with captions and alt text.”

Prompt variants

• Quick summary: “Summarise these notes into a 250-word case study with headings: Problem, Solution, Results.”
• Section drafts: “Produce headlines, 3 bullets, and a 80-word paragraph for each section: Research, Design, Outcome.”

1-week action plan

1. Day 1: Gather & label artifacts (60 min).
2. Day 2: Run main prompt on Interview & Metrics chunks; extract facts (30 min).
3. Day 3: Draft Problem & Research sections, verify quotes (45 min).
4. Day 4: Draft Design & Visual briefs (45 min).
5. Day 5: Draft Outcome, insert exact metrics, finalize TL;DR (45 min).
6. Day 6: Polish voice, run quick user clarity test (30 min).
7. Day 7: Export portfolio page, track time-to-impact and initial outreach (30 min).

Your move.

[Jeff Bullas]

Quick win (try this in 5 minutes): Paste one interview chunk (200–400 words) into your AI and run the prompt below. You’ll get 3 pain points, 3 direct quotes, and a 2‑sentence TL;DR — enough to start a strong case‑study opening.

Nice point — structure is the lever. I like the KPI focus you added. Use AI to surface facts fast, then you (the human) verify and shape the story. Here’s a compact, practical add‑on to make that repeatable.

What you’ll need

• Raw artifacts: interviews, usability notes, screenshots, metrics (labeled).
• An AI editor (GPT-4 style) and any text editor.
• A 30–90 minute block per case study for 2–3 iterations.

Step-by-step (do-first mindset)

1. Chunk & label: Break notes into 200–500 word chunks. Give clear labels: Interview A, Usability B, Metrics 2024-06.
2. Run the quick prompt: Get pain points, quotes, TL;DR (use the prompt below).
3. Map to headings: Problem, Role, Research, Decisions, Outcome, Lessons.
4. Draft section-by-section: Prompt AI for one section at a time (60–150 words each). Keep outcome first in each section headline.
5. Visual brief: Ask AI for 3 visuals + captions + alt text (wireframe, flow, before/after screenshot callouts).
6. Verify & quantify: Check each quote and metric against originals. Replace uncertain items with [UNVERIFIED] or exact numbers.
7. Polish & export: Edit voice, shorten sentences, add TL;DR and a 1‑line impact highlight. Export PDF or portfolio page.

Copy-paste prompt (use as your quick test)

“You are an expert UX case study writer. I will paste an interview or research chunk. Extract: 1) the top 3 user pain points, 2) three direct user quotes (verbatim), and 3) a 2-sentence TL;DR that highlights the main outcome. If any quote or metric is unclear, mark it with [UNVERIFIED]. Keep tone professional and concise.”

Example (before → after)

Before: messy notes saying “onboarding is confusing, app slow, users drop off.” After: TL;DR, 2 quotes, 3 pain points, one design change (progressive onboarding), and an outcome line: “Activation ↑ 38% in 8 weeks (A/B test).”

Common mistakes & fixes

• Using paraphrased quotes: Fix — keep verbatim quotes and tag edits as [EDITED].
• Too much process: Fix — lead with impact; put methods in a short appendix.
• Not verifying metrics: Fix — always cross-check numbers and dates before publishing.

3-step action plan (today)

1. Gather and label one interview chunk (10 min).
2. Run the quick prompt above and capture TL;DR + quotes (5–10 min).
3. Draft Problem + Outcome sections in the AI, verify facts, and save a one-page case study draft (30–60 min).

A small, verified iteration beats one perfect draft. Start quick, verify often, then polish for impact.

[aaron]

Here’s the move: stop “writing” case studies and start assembling evidence. Let AI do the heavy lifting, you supply proof and decisions. Outcome first, details second.

The blocker

Raw notes are inconsistent, quotes are scattered, and metrics don’t align. You spend hours polishing paragraphs that don’t convince a hiring manager in the first 60 seconds.

Why this matters

Case studies are sales assets. Recruiters skim for three things: the problem, what you changed, and the measurable result. No clear KPI, no interview.

What I’ve learned

Speed comes from structure. Build an “Evidence Locker” first, draft second. Use AI to extract, normalize, and outline. You verify, cut fluff, and lead with numbers.

What you’ll need

• Raw artifacts: interviews, usability notes, screenshots, experiment logs, dates.
• An AI editor (GPT‑4‑style), and a basic spreadsheet (your Evidence Locker).
• A simple template: TL;DR, Context & role, Problem & goals, Research insights, Design decisions, Outcome & metrics, Lessons.
• 90 minutes for a complete first pass; 30 minutes to verify/polish.

Workflow that converts notes into a KPI-first case study

1. Create your Evidence Locker (15 min). Columns: Claim, Quote (verbatim), Metric (value + unit + date + source), Artifact link/ID, Confidence (Green/Amber/Red), Owner (you), Notes. Expect to fill 10–20 rows fast.
2. Chunk and label sources (10 min). Break notes into 200–400 word chunks. Labels: Interview_A, Usability_B, Metrics_2024‑08, Screens_App_v3.
3. Extract facts and quotes (10–15 min). Run the Evidence Extractor prompt on each chunk. Paste results into the Locker. Do not edit quotes yet.
4. Normalize metrics (10 min). Use the Metrics Normalizer prompt to convert vague claims into exact numbers with units and dates. Anything fuzzy becomes [UNVERIFIED] or an estimate with a range.
5. Outline outcome-first (5 min). Build the skeleton: TL;DR (2 lines), Problem (1 line), Role (1–2 lines), Top 3 insights (bullets), 3 design decisions (bullets), Outcome (3–5 hard numbers), Lessons (3 bullets). Expect a one‑page outline ready to draft.
6. Draft by section with constraints (20–30 min). Use the Section Draft prompt per section. Keep each section 80–120 words. Start every section with its outcome in bold text (you can style later).
7. Visuals that prove impact (10 min). Run the Visual Brief prompt for three visuals: before/after, flow fix, KPI chart. Capture suggested captions and alt text.
8. Audit like a skeptic (10 min). Run the Skeptic prompt on your draft. It will flag weak claims, unverified quotes, and missing dates. Fix or bracket.
9. Polish voice and scannability (10–15 min). Use the Voice Polish prompt to shorten sentences, surface numbers early, and de‑jargon. Target a 6th–8th grade reading level.
10. Ship and test (10 min). Export to your portfolio or PDF. Do a 60‑second skim test with a colleague: can they state the problem and outcome? If not, tighten TL;DR and Outcome.

Copy‑paste prompts

• Evidence Extractor: “You are a UX research analyst. From the text I paste next, extract: 1) three verbatim user quotes with speaker labels if available, 2) top three pain points (short phrases), 3) any metrics with value + unit + date + source, 4) notable anomalies or surprises. Mark unclear items as [UNVERIFIED]. Keep it concise, bullet format.”
• Metrics Normalizer: “Normalize these outcomes into explicit metrics. For each, return: metric name, value, unit, baseline, comparison period, sample size, method (e.g., A/B, cohort), and confidence (Green/Amber/Red). If data is missing, propose a defendable proxy and mark [ESTIMATE].”
• Section Draft: “Draft the [SECTION NAME] of a UX case study in 80–120 words. Start by stating the outcome in the first sentence. Use the following evidence only: [PASTE relevant rows from Evidence Locker]. Keep tone professional, concise, and free of jargon. Any uncertainty stays in brackets.”
• Visual Brief: “Given this draft and evidence, propose three visuals that prove impact (before/after, flow, KPI trend). For each: title, what to show, why it matters, caption (≤18 words), alt text. Prioritize clarity over aesthetics.”
• Skeptic Audit: “Be a skeptical hiring manager. Scan this draft and list: 1) unverified claims, 2) missing dates or baselines, 3) places where method overwhelms outcome, 4) jargon to remove, 5) opportunities to quantify. Return as actionable bullets.”
• Voice Polish: “Rewrite for clarity and brevity. Keep my voice confident and plain English. Front‑load numbers. Replace passive with active. Max 15–18 words per sentence.”

What to expect

• A complete first draft in 60–90 minutes with 3–5 hard metrics and 2–3 visuals.
• Higher credibility: every claim tied to evidence or bracketed as [UNVERIFIED]/[ESTIMATE].
• A skim‑friendly story: outcome in the first 2 lines, decisions justified by data.

Metrics to track

• Time‑to‑first‑impact (seconds until a reader sees the main KPI) — target < 30s.
• Quote accuracy rate (verbatim, sourced) — target 100%.
• Verified data coverage (% of claims with source/date) — target ≥ 90%.
• Readability (grade level) — target 6–8; keep it skimmable.
• Portfolio conversion (views → interview requests) — baseline, then aim for +25–50% lift.

Common mistakes and fast fixes

• Outcome buried: Put the top KPI in the TL;DR and again in the Outcome section header.
• Soft metrics only: Add absolute numbers, baselines, and dates. If unknown, add [ESTIMATE] with a range and next‑step to verify.
• Over‑index on process: Cap methods to one short paragraph; move details to an appendix.
• Paraphrased quotes: Keep verbatim. If edited for clarity, tag [EDITED].
• Mismatched screenshots: Use before/after with the same viewport and a single highlight callout per image.

1‑week plan to get one polished case study live

1. Day 1: Set up the Evidence Locker. Chunk and label sources. Run Evidence Extractor on two key interviews (45–60 min).
2. Day 2: Normalize metrics from experiments/analytics. Fill baselines and dates (30–45 min).
3. Day 3: Draft TL;DR, Problem, Role using Section Draft prompt (45 min). Verify quotes.
4. Day 4: Draft Research insights and Design decisions (60 min). Tie each decision to one insight.
5. Day 5: Draft Outcome & metrics. Add 3–5 numbers with baselines and periods (45 min).
6. Day 6: Generate Visual Brief, capture or annotate screenshots, finalize captions (60 min).
7. Day 7: Run Skeptic Audit and Voice Polish. Export and run a 60‑second skim test with one colleague. Publish (45–60 min).

Proof over prose. Lead with numbers, back with quotes, show the before/after. Your move.

— Aaron

[Rick Retirement Planner]

Short move: Treat your case study like an evidence file, not a story draft. Let AI organize and summarize evidence; you verify and narrate the decisions and impact. Clarity builds confidence — if a recruiter can see the problem, your change, and the KPI within 30 seconds, you’re winning.

One simple concept, plain English: An “Evidence Locker” is just a spreadsheet where every claim in your case study points to a real item — a verbatim quote, a screenshot, or a metric with a date and source. Think of it as receipts for your story: assemble them first, write second.

What you’ll need

• Raw artifacts: interviews, usability notes, screenshots, experiment logs, dates.
• An AI writing tool (GPT‑style) and a simple spreadsheet for the Evidence Locker.
• A short case-study template (TL;DR, Context & role, Problem, Research, Decisions, Outcome, Lessons).
• 90 minutes for a first pass; 30 minutes to verify and polish.

How to do it — step by step (what to do, how long, and why)

1. Create your Evidence Locker — 15 min. Columns: Claim, Verbatim Quote, Metric (value + unit + date + source), Artifact ID, Confidence (Green/Amber/Red). Fill 10–20 rows quickly from your raw notes.
2. Chunk & label sources — 10 min. Split notes into 200–400 word chunks and label them (Interview_A, Usability_B, Metrics_2024-08).
3. Use AI to extract facts — 10–15 min per chunk. Ask the AI to pull verbatim quotes, pain points, and any numbers. Paste results straight into the Locker; don’t edit quotes yet.
4. Normalize metrics — 10 min. Convert vague claims into explicit metrics (value, baseline, period). If something’s fuzzy, tag it [UNVERIFIED] or add a defendable estimate with a range.
5. Outline outcome-first — 5 min. Create a one-page skeleton: TL;DR (2 lines), Problem (1 line), Role (1–2 lines), Top insights, 3 design decisions, Outcome (3 hard numbers), Lessons.
6. Draft by section — 20–30 min. Have AI write one section at a time using only evidence rows you paste. Keep sections 80–120 words and start each with the outcome.
7. Audit & polish — 20–30 min. Run a skeptical pass: flag unverified claims, tighten language, and ensure quotes remain verbatim or are marked [EDITED].
8. Ship & test — 10 min. Export and do a 60‑second skim test with a colleague: can they state the problem and KPI?

Carefully-crafted prompt approach (brief, practical)

• Start with a role cue: ask the AI to act as an “evidence extractor” or “UX case study drafter.”
• Be explicit about outputs: request verbatim quotes, top 3 pain points, and any metrics with units and dates.
• Constrain length per section and require uncertainty flags like [UNVERIFIED] for anything you can’t verify.

Prompt variants (use depending on stage)

• Quick extract: Short instruction to pull 3 quotes, 3 pain points, and a 2-sentence TL;DR from one interview chunk.
• Section draft: Tell AI to draft one section using only specified Evidence Locker rows, 80–120 words, outcome-first.
• Skeptic audit: Ask AI to act like a hiring manager and list unverified claims, missing baselines, and jargon to remove.

What to expect

• A usable first draft in 60–90 minutes with 3–5 verifiable metrics and 2–3 visuals you can produce.
• Higher credibility because every claim links to an artifact or is bracketed as [UNVERIFIED]/[ESTIMATE].
• Better conversion: recruiters see problem → change → KPI quickly, which increases interview chances.

[Author]

Posts