Become the designer you want to be. Decide, build and prove with AI.

You leave with a working AI Skill, the assistant you built and evaluated, live at a link.

1. 01How an AI system is put together

   Someone in planning asks whether the AI can remember what the user picked. You need to know if that is the model, the app, or neither. Get it wrong and you design the wrong settings screen, then the wrong error state. By the end you can answer that out loud.

2. 02Context and instruction

   More context is not better context. You rewrite one instruction twice, then add 2 documents it does not need. The answer gets worse while you watch. The assumption never comes back.

3. 03Grounding, retrieval and memory

   A citation proves nothing until somebody opens it. 4 claims come cited, and one does not survive the check. Then you design the screen for when the search comes back empty.

4. 04Tools, workflows, agents and permission

   Your product will soon take actions without asking. Someone has to draw that line. You take 4 AI actions and decide which ones need a human first. Reversible is not the test on its own. You leave naming one action you would never let it take alone.

5. 05Failure, recovery and a first evaluation

   AI breaks in 7 distinct ways. Most products answer all 7 with one spinner and an apology. You design 3 recovery states, then score 2 versions across 6 cases. Quality stops being taste and becomes a number you can defend.

You leave with an evidence file, a friction score, and a persona nobody takes on faith. Plus a ranked plan carrying its rejected list.

1. 01Brief

   A request now arrives as a working prototype somebody generated on Sunday. Evidence on one side, assumption on the other, and a date on every gap. The problem under the request gets named, with a baseline nobody invented.

2. 02Design Audit

   Any model can audit a product now. Almost nobody can make two raters agree. You score the product task by task, then write the protocol down. Another rater follows it and lands within 1 point of your total. That is what makes the number in your case study survive.

3. 03Competitive Analysis

   An agent scores 10 competitors overnight, more consistently than you would. Where all of them fail the same task, the category left a gap. You also record what users already expect, because a gap can be a convention. 3 to 5 gaps go in your backlog as hypotheses.

4. 04Persona Creator

   A model writes a persona in seconds, and it will sound right. You write the screener, run it, and rank drives and blocks against what people said. 2 to 3 cards, each block traced to the screen it happens on.

5. 05AI Opportunity Map

   Somebody will ask you to put AI in the product this quarter. You map where the model should act and where it becomes a liability. Then the AI idea gets ranked against a copy fix. It has to earn the slot.

6. 06Hypothesis Backlog

   Ideas are cheap to build now, so the argument moves to which one. 3 audit findings become hypotheses, 7 fields each, ranked by effort against impact. Then someone else tries to disprove yours using only what you wrote. Most of the course hangs off this one file.

You leave with a design system with its foundations, one fully specified component, and a prototype that runs.

1. 01Requirements & Acceptance

   The build happens overnight now, and nobody asked you anything. Your rules were the only steering input there was. Here you write the rule and the test that proves it, side by side. Every AI surface gets 4 defined behaviours: success, uncertain, empty, failure.

2. 02Flows & Structure

   AI features get bolted on top because nobody mapped the flow underneath. You diagram the one users actually walk, counting steps, people and systems. Then you draw the target, with the AI surface placed inside the structure.

3. 03Wireframes & Copy

   The model draws all 5 states now: default, empty, loading, error, uncertain. It cannot decide what uncertain should mean in your product. You write that string twice, once badly and once useful. Only you know what your product can afford to be wrong about.

4. 04Visual Design, System & Prototype

   A flat frame cannot show a model being wrong in front of a user. Your prototype runs the 4 AI behaviours at real latency. Foundations first, then the real screens, then the parts harvested from them.

You leave with a test protocol, verdicts on your own hypotheses, and a decision you can defend.

1. 01Usability Testing

   Watching one real person fail is the last research a model cannot run for you. Every task comes from a hypothesis you wrote on day one. Findings come back as 3 verdicts: confirmed, disconfirmed, inconclusive. You stop defending taste in front of people who outrank you.

2. 02AI Eval

   Anyone can make the screen now. Setting the pass mark is the rarer job. You build a case file from the rules you wrote in Build. The pass mark gets set first, because the same prompt answers differently each time. Known failures go into a regression set so they cannot return.

3. 03Measurement & Impact

   Nobody tracks whether users override the model. That number is about to matter. You name the metric before the design exists. Then you instrument the 4 signals: override, rephrase, abandon, ignore. Reading a metric you picked afterwards is decoration, and everyone can tell.

4. 04Improvement Loop

   The model under your product changes every few months, and your product changes with it. Once a month you re-score, read the deltas, and refill the backlog. Then you pick where to re-enter: Decide, Build or Prove. Next quarter's roadmap comes from your evidence, not from whoever spoke last.