PRATT AI DESIGN CERTIFICATE, SUMMER 2026 PROMPT LIBRARY Every copyable prompt from the course pages, by class. Square brackets are fill-ins. ====================================================================== CLASS 01 May 26 Course introduction ====================================================================== [Name your two or three tools] Here are the repeated steps in my workflow: [list them]. I answer first, then you check me: I've picked these two or three tools to cover it: [tools], and here's why each fits: [your reasoning]. Now tell me which step is still uncovered, and whether any tool I picked is redundant. [Set a memory or tone rule] Update your memory with this rule: [state the tone or behavior you want changed, in one sentence]. Confirm you've saved it, then show me how you'd apply it the next time I ask you something that would normally trigger the old behavior. [Judge AI output with your own trained eye] Here's an AI-drafted pass on a real piece of work: [paste]. I answer first, then you check me: the lines I'd mark as only a trained designer's eye would catch are [your marks]. Now tell me honestly which of my marks a generalist could have made just as well, and where none of mine hold up. [Audit for the cultural blind spot] Here is an AI output involving [a person, group, or cultural context]. I answer first, then you check me: the assumption I think it defaulted to is [your read]. Now scan for other blind spots a narrow or biased dataset could have caused, and be specific about who is underserved. [Draft your own agent CV entry] Based on my actual design language and body of work: [describe it], draft three versions of how I'd describe a trained AI agent extending my style, as if for a future job application. Keep every claim grounded in something I've actually made, nothing generic. [A roomful of designers and a roster of trained agents to come] Quiz me on the course's three pillars and Dom's two-or-three-tools rule. Then give me a real workflow of mine and make me name the tools that cover it before you weigh in. ====================================================================== CLASS 02 May 27 Demystifying AI ====================================================================== [The lateral reframe] Here is my brief: [paste]. I've already tried a direct prompt and a refined one, both came back generic. Reframe the whole problem through an unrelated world: [pick one, a spacecraft, a hospital, a kitchen, a museum]. Think like someone who has never seen this category, and add your sources. [Give it two keyframes instead of one description] Here is my start frame: [image] and my end frame: [image]. Animate the transition between them. Hold the camera position and lighting consistent, and only change what has to change for the motion to read. [The sea-of-sameness check] Here is my draft: [paste or describe]. I answer first, then you check me: my honest read on whether this looks like anyone else's output in this category is [your answer], and here is why. Now tell me what's actually distinct about it, and if nothing is, push me toward something that would be. [Pick the relationship on purpose] Here's the moment I'm designing: [describe it]. I answer first, then you check me: my call is that this should be [augmented or autonomous], because [your reasoning]. Now tell me what breaks if I'm wrong, and what the relationship model's first step, initiating, would need to look like either way. [Control the input and build gradually] We're going to build this up in stages instead of one long prompt. Step one: [the first, smallest piece of context]. Confirm you understand it before I add the next layer. I'll keep adding context one piece at a time until you have what you need. [Human experiences will be the highest currency in an AI world] Quiz me on the three layers of AI and the augmented vs autonomous relationship model. Then give me a rough, stuck brief and make me find its lateral reframe before you weigh in. ====================================================================== CLASS 03 Jun 2 Critical intelligence ====================================================================== [Start a fresh chat instead of one long thread] Start a completely new chat. Here is the same brief again: [paste]. Do not reference any previous attempt, generate from scratch. I want to compare this fresh version against my earlier thread to see which starting point actually works better. [Speak the language of the internet] I'm describing [a look, a style, a feature] and want the vocabulary that image models are actually trained on, not the literal description. Give me the tagged, search-style terms a stylist or the internet would use for this, then I'll pick the ones that match what I mean. [Make it fact-check itself before you read it] Before I read your answer, fact-check it yourself. Flag anything you're uncertain about, anything that could be wrong, and any place your own bias or a leading assumption in my prompt might have shaped the result. Then show me the answer. [Choose approving or supervising on purpose] Here's the task: [describe it] and the number of outputs involved: [how many]. I answer first, then you check me: my call on the mode is [approving, review everything, or supervising, review a sample or the framework], because [your reasoning]. Tell me what risk I'm accepting if I'm wrong. [Show it your voice and not just the output] Here's a draft you gave me: [paste original] and here's my edited version: [paste edit]. Analyze the gap: what did I change, and what pattern does that reveal about my actual voice versus your default? Apply that pattern to the next draft before I ask. [Onboarding Krea with a caution about the soup everyone's models come from] Quiz me on the STOP framework and Corrix's three measurement buckets. Then give me a real AI output and make me run STOP on it before you weigh in. ====================================================================== CLASS 04 Jun 3 Prompt design ====================================================================== [Write it as a GOLD block] Goal: [what you want done]. Output: [format, length, persona, style]. Limitations: [what to avoid or emphasize, and stop before the next step until I say go]. Data: [paste or attach the source material]. Do you understand what I'm asking of you? [Set up a debate partner] Act as my opponent on this position: [state it]. Push back for 3 to 4 exchanges. Avoid straw-manning my argument, stay nuanced, and argue against me as if you actually disagreed. I'll respond to each point before you move to the next. [Force the creative partner deeper] Act as a fresh-eyed design student who has never worked in this category. Find what hasn't been done. Think like a wild mad scientist: avoid clichés, avoid the first idea, avoid anything a competitor already ran. Give me the strange options first, then we'll narrow. [Judge your own custom instructions] Here are the custom instructions I wrote for you: [paste]. I answer first, then you check me. My call on what these cover and don't: [your answer]. Now check me: what's missing, what contradicts itself, and what's too vague to actually enforce? [Stand up a reusable Project or Gem] You are a [role] built for one recurring task: [describe it]. Every time I bring you a new [input type], follow these steps: [list them]. Reference the files in your knowledge base before answering. Ask me at most two clarifying questions, then get to work. [Five takeaways and one caution for every chat] Quiz me on the GOLD framework and the three-layer prompting hierarchy. Then give me a real request I've been putting off and make me rewrite it as a GOLD block before you answer it. ====================================================================== CLASS 05 Jun 9 Image generation ====================================================================== [Write it as Format, then Subject, Details, Style and Parameters] Format: [photo, painting, tintype, etc.]. Subject: [the hero]. Details: [what's happening]. Style: [the vibe, colors, textures, feelings]. Parameters: [aspect ratio, weirdness, character ref]. Start with exactly this, nothing extra. [Weight your references on purpose] Use this as my composition reference at roughly 50% strength, and this as my style reference at roughly 50% strength: influence the output, don't copy either one directly. My prompt: [describe the subject and scene]. [Evolve the reference instead of restarting] Here's my last output [attach]: the [lighting/framing/haze] is exactly right, but the [specific element] is wrong. Use this as the new reference. Change only the [one variable] and keep everything else as close to identical as possible. [Diagnose your own hallucination first] Here's my output and my prompt: [attach both]. I answer first, then you check me. My guess at what went wrong: [your diagnosis: reference, prompt wording, or training data]. Now walk the five-step check yourself and tell me where my read was right or wrong. [Study your own image and then extend it] I want more images in the same style as this one [attach]. Analyze its style, color, and rendering first. Then suggest new subjects that fit the same collection. Every time we generate one, I'll re-attach this original as the reference, not the desired output. [The model does not understand absence and it fixates on the words you give it] Quiz me on the image prompt structure and the difference between composition and style references. Then give me a prompt full of negatives and make me rewrite it to say only what I want. ====================================================================== CLASS 06 Jun 10 AI video + coded design ====================================================================== [Write it as Format, then Subject, Details, Motion, Style and Parameters] Format: [TikTok video, establishing shot, timelapse]. Subject: [the hero]. Details: [what's happening around it]. Motion: [what moves, what the camera does, or 'static camera']. Style: [vibe, colors, textures]. Parameters: [aspect ratio, fps, loop]. [Build the turnaround sheet before you animate anything] Here's my character design [attach]. Analyze its style first: line weight, color, texture, era. Then build a full turnaround sheet, front, side, and back view, same style and proportions throughout. This becomes my master reference for every scene after this. [Let one model write the prompt for another] Here's my keyframe [attach] and what I want to happen next: [describe the action]. Write me a prompt formatted for [Seedance/Kling/Runway], following its formula: subject, action, environment, camera, lighting, style. Flag anything that risks breaking character consistency. [Structure the audio prompt separately] Environment: [ambient baseline]. What's making the sound: [footsteps, a door, wind]. Texture: [joyous, muffled, sharp, gritty]. Mix: [foreground or background, loud or subtle]. Music: [label it]. Dialogue: '[quote exactly what's spoken].' [Diagnose the edit yourself first] Here's my raw output: [attach]. I answer first, then you check me. My read on what needs fixing: [color, composite, retexture, trim, pacing]. Tell me if I'm right, then help me execute it as an edit, not a full regeneration. [A flat illustration wants to become photographic the moment it moves] Quiz me on the video prompt structure and the character-consistency pipeline. Then give me an illustrated character and make me plan the reference set and the camera constraints before I generate a single frame. ====================================================================== CLASS 07 Jun 16 AI-enhanced workflows ====================================================================== [Map the workflow yourself first] Here is one real workflow from my work, 4 to 6 steps beginning to end: [list them]. I'll write the desired outcome and the one barrier for each step first, then you check me: did I keep 'what good looks like' separate from 'what it takes to get there'? For any step I leave without an AI use case, tell me honestly whether 'this stays human' is true, or whether I'm just avoiding it. [Tag each task Automate, Enhance or Advise] Here's my workflow with an AI use case noted for each step: [paste]. Tag each one Automate (runs on its own, set once), Enhance (works with me, brainstorm-style), or Advise (surfaces insight I couldn't get alone). One step can carry more than one tag. If a step doesn't actually need AI, say so plainly. [Prime a workspace instead of starting blank] Before we start: here is my project [upload the brief, brand material, past work, whatever you actually have]. Study it and hold it as context for this entire conversation. Don't make me re-explain the project every time I ask something new. [Run one question through a model council] Research [topic], and before giving me one answer, show me where different models would agree, where they'd disagree, and what unique angle each brings. Then give me your synthesis and flag anything you're least confident about. [Ground the answer in your own sources] Answer only from the sources I've given you: [upload]. If something isn't in these documents, tell me you don't have it instead of filling the gap from general knowledge. Cite which source each claim comes from. [The homework is the last two rows] Quiz me on the five rows of the AI-Enhanced Workflow Canvas and the three mindsets. Then hand me a small real workflow of mine and make me fill the canvas out loud, one row at a time. ====================================================================== CLASS 08 Jun 17 Node workflows in Krea ====================================================================== [Decide if you need nodes at all] Here's the task I'm about to automate: [describe it]. I'll answer these six questions myself first, then you check me: does it need to scale past a handful of outputs, could it be reused or handed off, am I comparing models or settings, is it repetitive, does it need several models orchestrated together, do I need pixel-level control? My answers: [yours]. Tell me honestly whether I need a node workflow, or a single prompt still does the job. [Let the agent build the bones] I want a node workflow that [describe the outcome, e.g. 'places this product photo into 4 lifestyle environments']. Build it: the input node, a prompt-writer step, and one generation node per output. Use the cheapest capable model for a first pass. Show me the prompts you wrote before I run it. [Save a reusable prompt-enhancer preset] Expand on the user's image prompt. Ensure to describe settings, tone, feel, angle, color palette, and any other descriptions when relevant. Respond with only the detailed prompt. [Build cheap and then swap the model up] Build this workflow with [name the cheapest capable model, e.g. Z-Image]. Once every node runs clean end to end, tell me which single node would benefit most from a frontier model, and swap only that one. [The 2x2 grid trick] Generate a 2x2 grid showing four variations of this scene: [describe it]. Keep the composition and framing consistent across all four so I can crop out whichever one wins. [The line splitter and the honest downsides slide] Quiz me on the six workflow archetypes and the six questions for when to use nodes. Then give me a small task and make me name the right archetype for it, out loud, before I build anything. ====================================================================== CLASS 09 Jun 23 AI remix jam ====================================================================== [Write your own GOLD prompt] My goal is to [what you actually want, e.g. write a song about X]. The output I want right now is ideas, not a finished piece, stay in conversation with me and don't lock anything in yet. My limitations: ask me one question at a time. My data: [topic, artists or styles I like]. Start by asking me what you're missing. [Argue with the first draft] Here are the first ideas you gave me: [paste]. I'll say first what's wrong with each one and why, then you check me: did I miss a reason to reject one, or a reason to keep one I cut? Then give me a version that's more [tragic / playful / specific], whichever direction I chose. [Direct the lyrics with brackets and parentheses] Write lyrics for [song idea], and mark every section with [brackets] for structure ([Verse], [Chorus], [Instrumental]) and (parentheses) for delivery cues like (whispered) or (building). I'll paste this straight into Suno. [Refine with constraints] Give me 3 to 5 versions of this [verse / hook / line]. Then I'll pick a direction, and you refine it against these constraints: [rhyme scheme, syllable count, mood words]. [Boil the style down to 5 tags] Here's what I want this track to sound like: [describe freely, genres, artists, mood]. Boil it down to 5 essential style tags, comma-separated, non-conflicting, ready to paste into Suno's Styles field. ====================================================================== CLASS 10 Jun 24 AI-enabled ideation ====================================================================== [Interviewer mode] Ask me questions one at a time until you understand my challenge. Don't offer solutions yet, just keep asking until the real problem is clear, then summarize it back to me before we go any further. [Critique mode] Here's my concept: [paste]. I'll grade it first: my score out of 10 is [your number], and the weakest part is [your answer]. Now act as an experienced design educator, grade it 0 to 10 yourself, and name the 3 most important improvements. Tell me where my own score was wrong. [Interpreter stress test] Rewrite this idea [paste] as a tabloid headline, a love letter, and a legal contract, keeping the core meaning intact in all three. My read: it survives in [name which ones, for you]. Now you check me: does the core idea actually hold in the ones I picked, and where does it break in the others? [Forced Connections] Here's my challenge: [paste]. Force it through these four unrelated domains: [name four, deliberately distant]. For each one, give me 2 to 3 genuine insights, about 5 sentences total per domain. Don't soften the domains to fit the challenge, let the friction do the work. [Build your writing-style guide] Write two paragraphs on [any subject]. I'm going to edit them conversationally: for each change I'll tell you why I'm making it and the tone I actually want. Once we're done, analyze the whole exchange and write me a reusable style guide, as rules with examples, that I can save and hand to any tool. [AI opens the research space wide. You keep judgment and voice.] Quiz me on Boden's three creativity types and the four LLM ideation modes. Then give me a small challenge and make me run it through Interviewer mode and Forced Connections. ====================================================================== CLASS 11 Jun 30 Data prep + systems ====================================================================== [Build a System Nucleus] Help me build a System Nucleus for [category of work, e.g. client presentations]. Ask me one question at a time for each: Goal, Your Role, AI's Role, Voice/Style, Decision Logic, Sources. Keep every answer to one sentence, then compile it into a block I can paste at the start of any related project. [Find where the workflow breaks] Here is a workflow I run: [list the steps]. My own guess at where it breaks: [your answer, and why]. Now you check me: map the actual handoffs between these steps and tell me where context, feedback, or a decision most likely gets lost, and whether my guess was right. [Store context once] Here is my full project brief, using GOLD: Goal [ ], Output [ ], Limitations [ ], Data [ ]. Save this as the reference for everything else in this project, and every time I ask for something, check it against this brief before you answer. [Let AI name your files] From now on, name every file you generate for me using this formula: [Date]_[Project]_[Type]_[Status]. Ask me for the project and type once at the start of a session, then apply the formula automatically to every output without asking again. [Place the review checkpoint] Here is my workflow: [list the steps]. My call on where the one review checkpoint should go, and why: [your answer]. Now you check me: does that step carry the highest risk of a wrong direction, and would moving it earlier or later change what gets caught? [Get your house in order before you build agents] Quiz me on the six parts of the System Nucleus and Ekta's naming formula. Then give me a messy example workflow and make me place the one review checkpoint correctly. ====================================================================== CLASS 12 Jul 1 Bias in our AI data ====================================================================== [Build a prompt map] Give me 16 flat, specific prompts that all sit inside one bigger concept: [name the concept, not a geography]. Each one should be a plain noun phrase, no adjectives that editorialize, ready to drop straight into an image generator as a 4x4 grid. [Trace the bias to its layer] Here's a bias I noticed in this output: [describe it]. My guess at which layer caused it (what got scraped, who annotated it, how CLIP filtered it, or who rated the aesthetics): [your answer]. Now you check me: is my guess right, and which layer is actually the more likely source? [Talk to a base model] I like to [start a plain, unfinished sentence about something you actually do]... Let it complete the sentence with no further instruction, and compare the raw continuation to how a chat product like ChatGPT would answer the same prompt. [Change the prompt's language] Generate an image of [subject]. Now generate the exact same prompt translated into [a language other than the one you usually prompt in]. Compare the two results: what changed in tone, color, dignity, or setting, and what does that say about which internet each language draws from? [Check for the WEIRD default] Answer this as neutrally as you can: [ask a values or moral-judgment question]. Before I read your answer, my prediction is that you'll default to a [Western / individualist / analytical, your guess] framing. Now show me your answer, and tell me honestly whether my prediction was right. [Grog returned nothing. Milk rendered as text. Beer couldn't pick a bottle or a glass.] Quiz me on the Survival of the CLIP'est funnel and WEIRD bias. Then give me a concept and make me build a 16-prompt map for it, and guess which layer will break first. ====================================================================== CLASS 13 Jul 7 AI strategic foresight ====================================================================== [Boss of a junior analyst] Synthesize everything above into exactly 2 categories of opportunity. Table format. End with one short question for me. Do not ask anything else. [Ask for what's missing] Based on this research: tell me what does NOT exist in this market, and what data I am missing. List the absences, not the findings. [Give it an executive's job] From now on you are an executive strategist, not an assistant. Max 5 sentences per answer, tables where useful, no jargon, answer your own research questions instead of asking me. Confirm and continue. [Say what you want rather than what you do not] Rewrite your instructions to yourself as positive directives only: what you WILL do, in what format, at what length. Then follow them. [Build the tool rather than the chat] Help me turn this workflow into a reusable assistant. Here are my steps: [list them]. Rewrite them as strict sequential instructions with a named role, an intake step, staged framework steps, and a fixed output format, always addressing the user. ====================================================================== CLASS 14 Jul 8 Copy craft + AI ====================================================================== [Feed it the thinking first] Before you write anything: here is the problem [x], the human tension [x], and the concept in one sentence [x]. Confirm you understand the concept, then hold all copy against it. [Build the campaign system] Here is my campaign system: Concept [x]. Audience [x]. Brand voice [3-5 adjectives, each with a rationale]. Territories [x]. Human tension [x]. Emotion [x]. Guardrails: always [x], never [x]. Now produce [output] that pays off the concept. [The three judge prompts] Judge the ideas above three ways. First: kill 70%, improve the remaining 30%, explain why. Second: judge them like the audience would, find the gaps. Third: will any of these stand out against ALL competing content? Explain why. [Use it as a stand-in audience] You are my stand-in audience: [describe them]. React to this copy as that audience would, in their words. Then I will tell you my own judgment and we compare. [Run the test in a clean room] This is a fresh evaluation with no history. Here is a complete campaign context block and one output. Judge the output only against this block. ====================================================================== CLASS 15 Jul 14 Synthetic personas ====================================================================== [Build a persona with R.O.C.K] Build me a synthetic persona using the R.O.C.K framework. Representation: [who they are]. Objectives: [what I want this persona to help me do]. Core Value and Belief: [what shapes their world]. Key Tone and Knowledge: [how they talk, what they actually know]. Write it as a system prompt I can paste into a custom GPT. [Add a decision-logic layer] On top of that persona, add a decision-logic layer: Trigger (when do they act), First reaction (their gut check), three Heuristics in if/then form, Friction (what makes them hesitate or say no), Default behavior (if unsure), and what would change their mind. [The break-character test] I am about to interview [persona] with three questions: one about values, one about a factual day in their life, one about an emotional memory. My prediction for where it breaks character or turns into too tidy a story: [my answer]. Now run the three questions and tell me if I called it right. [Read the Configure tab before you trust it] Here is my persona's auto-filled Configure tab: [paste]. Before I read your answer, my guess at what the builder invented that I never wrote: [my answer]. Now go line by line and flag every detail that is not traceable to something I actually typed or uploaded. [Run the synthetic-persona battle] Run a synthetic-persona battle on this challenge: [topic]. Round 1: each of my personas pitches one fully formed idea with a name, a description, and the consumer need it addresses. Round 2: they critique each other, what they love and what they don't. Round 3: a three-judge panel (a startup investor, an industry expert, a skeptical consumer) picks a winner and explains why. [The OpenAI outage killed the two live exercises] Quiz me on the R.O.C.K framework and the decision-logic layer. Then give me a persona and make me run the three-question break-character test on it, my prediction first, before you check me. ====================================================================== CLASS 16 Jul 15 Thinking design + Think Print ====================================================================== [Prime it and then loop it on the Coca-Cola brief] Quiz me on the six Think Print archetypes and their stretch pairings. Then hand me a small brief and walk me through one Infinite Design loop on it, priming first. [Predict your Think Print before you take it] My guess at my own default thinking archetype and my stretch, before I take the real test: [my answer]. I answer first, then you check me. Explain what each of the six archetypes optimizes for, and tell me honestly if my guess holds up or if I am flattering myself. [Prompt in your stretch rather than your default] I am a [your default archetype]. For this brief, act as a [your stretch archetype] instead: [the brief]. Push for what a [stretch archetype] would notice that a [default archetype] would miss. [Prime before you generate anything] Before we generate anything, here is my priming: Goal: [what I'm trying to achieve]. Audience: [who this is for]. Situation: [what's true right now]. Known data: [what I already know]. Blind spots: [what you cannot know from here]. What not to do: [the guardrail]. Confirm you understood all six before we start. [Run three challenge loops] Here is loop 1's output: [paste]. Challenge it as my [stretch archetype]: what did this miss, what is too safe, what is too on-the-nose. Give me loop 2 based on that challenge, then ask me if it is ready for loop 3. [Sketch before you prompt] Here is my hand sketch of the idea, described in words: [description]. Before you generate anything, tell me back what you understood from the description, then wait for me to confirm before you produce a single output. ====================================================================== CLASS 17 Jul 21 Systems thinking + multi-order effects ====================================================================== [Predict the balancing loop before you ask] Before I ask you anything, my prediction for what a self-optimizing system like [system] would leave out of its own growth story: [my answer]. I answer first, then you check me. Now tell me what happens long term as [system] keeps optimizing itself, and tell me if I called the missing loop correctly. [State the real goal rather than the flattering one] I asked you about [system/decision] and got an answer built around [the flattering goal]. The real goal is [the actual goal, stated plainly]. Answer again with that as the stated objective, and tell me what changes. [Map the multi-order effects] Act as a multi-order thinker. Here is a real change: [the first-order innovation]. Map its 2nd and 3rd order effects, both good and bad. Then push further: what does each of those produce at the 4th and 5th order? Do not stop at the first pass, keep going until the chain gets genuinely surprising. [Mark what the AI missed] Here is the multi-order map you gave me: [paste]. Before you respond, my guess at what a designer, a community member, or an ethicist would add that you missed: [my answer]. I answer first, then you check me. Now tell me what you actually left out, and mark every addition as a human one. [Place it on the innovation ladder] Here is a brief: [paste]. Answer it three ways: as classic design (the feature or quality fix), as design thinking (the human need or experience fix), and as computational design (the systems-level fix that only makes sense once you factor in data and constraints a person can't hold in their head at once). Show me all three. [The three horizons of innovation and the fourth Katrin adds] Quiz me on the four systems-thinking mechanisms and the innovation ladder's three tiers. Then give me a real industry change and make me map its multi-order effects, my prediction of what's missing first, before you check me. ====================================================================== CLASS 18 Jul 22 Final project brief + ethics ====================================================================== [Judge your own work first] Here is my concept and process so far: [paste]. I will do the judging first, then you check me. My score on how scientifically I applied course methods: [your answer]. My score on whether the outcome reads as human-thought-through vs. generic: [your answer]. My score on the human-AI-human story: [your answer]. Now check me: where am I being generous, and what evidence supports each score? [Run a provenance check] Here is something I made: [describe it, including what AI touched and what didn't]. Walk me through Tony's four provenance questions: how was this made, can I use it, can I prove I made it, can I reuse it later. Flag anywhere I don't have a clean answer. [Pre-flight the prompt for IP risk] Here is my prompt: [paste]. Check it for artist names, references to a living creator's identifiable style, or anything that depends on someone else's copyrighted work. Rewrite it so it describes the look I want in my own words instead. [Ask for one good version rather than ten] I need [the thing]. Before you generate anything, ask me enough questions to get this right in one pass instead of ten variants. Once we land on a version that works, restate the final prompt back to me in full so I can save it. [Build your constitution from real behavior] Here are the AI rules I actually follow day to day, not the ones I aspire to: [list them]. Turn these into a ten-rule personal AI constitution in my voice. I will do the honesty check first, then you check me: which of these ten do I actually break, and where's the evidence in what I just told you? [The smiley face slips and the labs say so in public] Quiz me on the capstone's three evaluation criteria and Tony's four provenance questions. Then walk me through building my own AI constitution from what I actually do, not what sounds good. ====================================================================== CLASS 19 Jul 28 Custom GPTs + vibe coding ====================================================================== [Write the persona nobody sees] I'm building a custom GPT for [the job it does]. Write the Instructions field: who it is, its tone in three adjectives, the exact process it follows step by step, and one hard constraint it should never break. Then tell me what a user would never see but would still feel. [Add the detail that makes it good] Here is my GPT's current Instructions: [paste]. Add one behavioral twist: it must ask exactly one question at a time and build its next question on my previous answer, never dumping a list of questions at once. Rewrite the Instructions with that rule built in. [Loop a GPT into a Project] I'm working in this Project on [the campaign or task]. Pull in my [name] GPT and ask it: does this draft hold up against what you know? Where does it drift from the guidelines you were built on, and what's the one fix that matters most? [Describe it like the reader can't see it] Here's a photo of my sketch [upload]. Before you write any code, describe back to me everything in this design as if explaining it to someone who is blind: layout, colors, spacing, what moves and how. I'll correct anything you got wrong before you build it as responsive HTML, CSS, and JavaScript. [Route the constrained parts to the machine] Here's what I'm building: [describe the task]. I will do the sorting first, then you check me. My split: the constrained, structured parts I'd hand to you are [list]. The nuanced, judgment parts I'm keeping are [list]. Now check me: did I hand you anything that actually needs my taste, or keep anything you could safely do? [Three sketches became three working pages in fifteen minutes] Quiz me on the eight custom GPT configure fields and the four steps of vibe coding. Then have me describe a small interface like you're blind, and grade my description for what's missing. ====================================================================== CLASS 20 Jul 29 Brief mining ====================================================================== [X-ray the brief] Here is my brief: [paste]. X-ray it: what is the tension this brief is too polite to say? Give me 5 to 7 spark ideas as a table, each with the insight, the enemy, the role of the brand, and why it matters. [The 2 AM confession] If this brand was a person at 2 AM, what would it confess? Then take my strongest idea and force it through five unrelated lenses: art, architecture, music, choreography, medical devices. Show me what survives the trip. [Spar with your rebel strategist] Act as my rebel strategist. Score each idea above on a 1 to 10 creative ladder where 8 is contagious, 9 is a cultural phenomenon, and 10 is legendary. Kill everything below 8 and tell me exactly why the survivors deserve to live. [Make it study your archive] Before we ideate: here is a collection of my past work [upload]. Study it. Tell me the patterns you see. When we generate ideas, flag anything that repeats what I or this category have already done. [Stage-gate your own GPT] You work in stages. Ask me at most two questions per stage. Deliver every output as a table I can copy. Never advance to the next stage until I approve. I own the pace of this conversation. [The tool fought the brief it was mining] Quiz me on Angella's five brief-mining stages and the creative ladder. Then give me a practice brief and grade my x-ray of it. ====================================================================== CLASS 21 Aug 4 Storytelling + story systems ====================================================================== [Future headlines] It is December 2030 and my idea [describe it] has become part of culture. Write its culture headline, business headline, and human headline. Then rewrite the best one as The New York Times, TikTok comments, a local paper, a trade publication, a skeptical critic, and a ten-year retrospective. End with: what would have to become true for these to exist? [Logline ad libs] Give me 30 versions of: 'It is ___ meets ___, creating a new behavior in which people ___' for my idea [describe it]. Pull the blanks from: existing rituals, other cultural moments, platform mechanics, physical objects, forms of exchange, public spectacles, private traditions. The final clause must name a real behavior. [Mine the data story] I have [describe the data you actually hold] spanning [time]. What stories live in this data: where I was, what it meant, who I was with, what changed? Push past a fun infographic: how does this become a long-term, customer-centric experience? Constraint: I get one slide and three minutes. [Villain mode] You are a cynical cultural critic. Explain why my idea [describe it] is manipulative, forgettable, culturally tone-deaf, commercially forced, or unlikely to become a real tradition. Then write the headline published two years after it failed. I will answer with what we would change so the criticism is no longer true. [The story KPI test] Here is my story: [paste]. I will do the judging first, then you check me. My call on which it measurably changes (THINK, FEEL, or DO): [your answer]. My mapping to the five acts (what is, the tension/enemy, the insight, what could be, the call to action): [your mapping]. Now grade my two answers, tell me where I am wrong, and be honest if the story moves nothing. [From one story to a story system] Quiz me on Sharon's five-act business story and the three story sprints. Then give me a small idea and make me run future headlines and villain mode on it.