AI can make a child’s drawing look more polished, but it can also erase exactly what made it interesting. A yellow tree, a rabbit larger than a person, a horse with impossible legs, or a tiny floating object may look like mistakes to a model—but they may be the whole point. I use the child’s drawing as art direction: preserve its visual logic, then build outward. The child supplies the invention; AI helps develop the surroundings. Step-by-step: 1. I read the drawing before transforming it by making a neutral description of what is visible: placement, relative sizes, colours, expressions, unusual shapes, and small details. For example: “A large yellow tree stands on the left. Two tiny figures sit near its trunk. A blue shape fills the lower right.” 2. I avoid deciding what an unclear shape represents. “An oval object with three legs” is more faithful than “a rocket” unless the child confirms it. If possible, I ask the child what is happening, since a strange proportion or colour may have a specific story behind it. 3. I separate essentials from flexible details in two short lists. Essentials might include the yellow tree, oversized rabbit, horse’s pose, characters’ arrangement, and red object in the corner. Flexible details might include lighting, textures, materials, environmental detail, and depth. 4. I make clear that the original is the structural source, not just a mood reference. This gives the model room to work while defining the boundaries. 5. I choose a target style, such as a storybook illustration, watercolour, digital painting, comic panel, or 3D scene. 6. I explicitly ask the model to preserve unusual proportions, unexpected colours, expressions, and relationships between characters. I identify details that must remain, even if they appear anatomically impossible or visually awkward. I avoid vague instructions such as “make it better,” because they leave the model to decide what counts as improvement. 7. I use a starting prompt such as: “Use this drawing as the structural blueprint for a storybook illustration. Preserve the composition, relative sizes, poses, expressions and original colour choices. Keep the yellow tree and the rabbit larger than the person. Do not normalize unusual anatomy or remove unexplained objects. Add texture, lighting and environmental depth around the existing scene.” 8. I treat comparison as part of the workflow because specific instructions do not guarantee a faithful result. I expand the world around the invention: a blank background can become a forest, a blue patch can become a pond if that interpretation fits, and two skiing figures can gain a mountain landscape. 9. I keep the original spatial relationships: who stands beside whom, what dominates the scene, which way characters face, and where empty space matters. I give colour the same care, so a yellow tree does not quietly become green because the model expects green trees. 10. I place the source and result side by side and check whether a character disappeared, the rabbit shrank, the palette changed, or the model invented a focal point, “fixed” an unusual shape, or altered the story. I also watch for generic cuteness—big eyes, pastel colours, and perfect symmetry—which can make very different drawings converge into the same image. I ask whether the result still feels like an expansion of this exact drawing. 11. If most of the result works, I request a targeted edit, such as: “Keep this version, but restore the original hair shape.” “Make the rabbit larger again.” “Return the tree to yellow.” 12. I check the whole image after each local edit because changes can affect other areas. I keep useful versions instead of repeatedly starting over. 13. I treat handwritten text separately. I do not guess unclear wording, correct spelling, or invent labels. If the tool cannot reproduce the text faithfully, I retain the original lettering through a separate editing step. 14. I save the original photo or scan alongside the result, instructions, and useful intermediate versions. I also keep a brief note about protected details to make future transformations easier. 15. Once I have a faithful version, I explore alternatives such as a space setting, surreal painting, or cinematic scene, keeping them as branches from the original. Across several drawings, I preserve recurring colours, shapes, and characters without forcing every image into one rigid style. The child has already decided who exists, what matters, how large things are, and what belongs together. Those decisions are creative direction. A drawing does not need to become less itself to become more finished. The impossible colour may be the atmosphere, and the awkward shape may be the character. The question I return to is: “How can I help this drawing become more fully what it already is?”

I used AI to develop a simple daily care plan for my above-ground pool. I copied the links to the pool I bought online and asked which chemicals would be best and whether I should make any upgrades right away. Then I asked AI to create a daily routine to keep the pool sparkling throughout the summer. When the water started looking cloudy, I took pictures of the water tests I was running and shared them so AI could help me get the pool back where it needed to be. Step-by-step: 1. I copied the online links for the above-ground pool I bought. 2. I asked AI which chemicals would be best for the pool and whether I should make any upgrades. 3. I asked AI to create a daily pool-care routine for the summer months. 4. When the water became cloudy, I took pictures of the tests I was running on the water. 5. I shared the pictures with AI to get guidance on bringing the water back to the right condition.

My car recently lost a small part near the bonnet. I didn’t know what it was called, and even the official workshop couldn’t help because the model was no longer in production. I gave ChatGPT my car details and a photo showing where the part was missing. It identified the part, helped me cross-check the specifications and compatible part numbers, and found sellers that had it available. I found the right part and had it delivered within a week. Step-by-step: 1. I shared my car model and a photo of where the part was missing. 2. I used ChatGPT to identify the part and its specifications. 3. I cross-checked compatible part numbers and alternatives. 4. I searched for sellers carrying the correct part. 5. I compared the options and ordered the right one.

When medical care, psychosocial support, and administrative follow-up are spread across services, emails, documents, and people over many years, there can be plenty of information but very little overview. A new provider sees snapshots, old decisions hide in email threads, and referrals resurface months later. Reconstructing the full story from memory every time requires almost a second brain. So I built a living chronological timeline. I did not want a summary of what my situation was “more or less.” I wanted: `date → event → action taken` For example: `14 March 2026 — Symptoms discussed with service X — Service refers me to Y; appointment requested.` This shows not only what happened, but what followed. My timeline runs from 2009 to the present and is divided into five documents covering meaningful periods. A new document begins when a new phase in life or support begins. Older periods stay stable, while almost all active maintenance happens in the latest document. I reopen historical files mainly when a missing record resurfaces. Step-by-step: 1. I collect existing traces, including emails, appointments, referrals, medical or administrative documents, formal decisions, and earlier notes. A sent email is often only half an event, so I also search for replies and follow-up. 2. I search by trajectory rather than by one name. I use names, spelling variants, organisations, domains, senders, recipients, subject words, and attachment terms. 3. I read the full conversation. A search result is not yet a timeline item, so I establish what happened, when it happened, who was involved, and what action or response followed. 4. I separate evidence levels. I distinguish between my own report at the time, a response or confirmation, an official decision or document, and an event that seems real but still lacks confirming evidence. I do not replace a missing document with an assumption; the absence itself becomes part of the record. 5. I track people and organisations separately. “Contact with organisation X” can hide that different people suggested, revisited, or formally communicated different things. 6. Before adding a new event, I compare it with the existing timeline. It may add information by filling a gap, replace an incomplete entry, clarify an existing event, or mark a missing record while preserving uncertainty. This prevents duplicate versions of the same event. 7. For substantial historical work, I first create a temporary review document using `date — event — action taken`. It can contain open issues, missing documents, and uncertainties. Only after review do I update the main timeline. For ordinary new events, I skip this step when the source and date are clear. 8. I make uncertainty visible by grouping research notes into “Clearly found,” “Possible identity confusion,” and “Not found or insufficiently documented.” 9. I maintain the living timeline using the structure `year → month → chronological events`. Older information is preserved, duplicates are merged, uncertainties stay visible, and open trajectories remain open. In practice, the five documents behave like version control: the first four are mostly archive, while the fifth is alive. 10. I reuse the timeline for thematic analysis. Chronology is the factual foundation, but events can also be regrouped to reveal patterns in functioning, work capacity, transport, medical developments, administrative burden, communication needs, and realistic conditions for participation. Two workflows emerged: - Historical reconstruction: collect sources → reconstruct trajectory → determine evidence status → review → update the correct historical period - Ongoing follow-up: new event → verify source → record date and action → add to the active document Most records are organised around institutions. A GP sees one part, a psychologist another, and an agency only its own procedure. Emails are chronological within a mailbox, but not across a life. A personal timeline turns that model around. The person becomes the organising axis, not the institution. That lets administratively separate events appear next to each other in time, revealing patterns such as repeated referrals, waiting times, administrative burden, or support disappearing when the need for it increases. The workflow in one line is: `Collect sources → reconstruct trajectories → connect events to actions → distinguish evidence status → compare → review → integrate → maintain → analyse thematically.` The result is not a perfect record, but a steadily improving map of what actually happened, with mainly the newest edge continuing to grow while the past stays calmly in place.

I use ChatGPT as a label-reading filter for packaged snacks, uploading product photos and asking it to flag hidden sugars, oils like palm, and preservatives, then compare options against a strict checklist of clean ingredients, minimal processing, and decent macros. It's especially useful for decoding lesser-known, jargon-heavy terms on the back label, translating things like INS numbers, stabilizers, and emulsifiers into plain English so it's clear what's actually being consumed. Instead of trusting front-of-pack claims like "multigrain" or "sugar-free," it breaks down what's inside, surfaces trade-offs, and narrows choices to the best options available online Step-by-step: 1. I photographed the ingredient labels on the packaged snacks I was considering. 2. I gave ChatGPT a strict checklist covering hidden sugars, oils such as palm oil, preservatives, processing, and macros. 3. I asked it to translate ingredient jargon such as INS numbers, stabilizers, and emulsifiers into plain language. 4. I had it compare the products based on what was actually inside rather than the claims on the front of the package. 5. I used the trade-offs it surfaced to narrow the list to the best available options.

I moved recently, and the movers took apart my bed frame. The hardware needed to reassemble it had been taped to the back of the headboard, but it disappeared during transport. I took photos of the headboard, sideboards, and footboard and uploaded them to Claude. I asked Claude to identify the hardware I needed to put the bed back together. It asked me to measure a couple of places, then produced a complete list, including four M8 screws measuring 80 mm, among other pieces. I took the list to the hardware store, and everything fit perfectly. I’m not sure how I would have solved the puzzle without Claude. Step-by-step: 1. I photographed the headboard, sideboards, and footboard. 2. I uploaded the photos to Claude and asked it to identify the hardware needed to reassemble the bed. 3. I measured the requested areas. 4. I used Claude’s list, including four 80 mm M8 screws and the other required pieces, to shop for replacement hardware. 5. I reassembled the bed with the replacement hardware, and everything fit perfectly.

I recently learned that I have severe osteoporosis. Two doctors highly recommended Evenity, which is prescribed and insurance-approved only for people at severe risk of fracture, so I knew the situation was serious. The decision was difficult because Evenity carries an increased risk of heart attack and stroke. Both conditions run in my immediate family, and one of my arteries has 75% plaque buildup. Ultimately, we agreed that my risk of a life-altering fracture was much greater than my risk of a heart attack or stroke. My father died six weeks after suffering a life-altering fracture, while my mother survived two heart attacks and a stroke, and my brother died from his first heart attack at age 60. That made it even more important to follow recommendations for both heart and bone health, even though the goals for each can be different. Monitoring everything myself would have been overwhelming, so I created a project called "Daily Meals" and prompted Chat to create a chart that tracks my daily intake of protein, carbohydrates, fiber, healthy and unhealthy fats, calcium, cholesterol, and other selected nutrients, along with a goal for each one. I enter everything I eat throughout the day. The chart maintains a running total and displays my goals underneath. When I am about halfway through my calorie goals, Chat recommends foods for the rest of the day to help me stay on target. Within a week, Chat had learned my go-to foods, and I also told it about other foods I like. There is no harsh judgment when I include ice cream. I also added pictures of the labels for the supplements I take each day. In addition to tracking my intake, Chat advises me about combinations that may help or hinder absorption. One important example for me is that vitamin D, which must be taken with fat, helps with calcium absorption, while vitamin K2 activates proteins that help carry calcium to my bones instead of my arteries. Chat also provides guidance about medications. When I was prescribed an antibiotic, I learned that taking it with calcium could greatly reduce the medication's absorption, so I adjusted what I ate accordingly. There is much more benefit than I can fit here. This project may literally be a lifesaver for me. Step-by-step: 1. I created a project called "Daily Meals." 2. I prompted Chat to create a chart for tracking protein, carbohydrates, fiber, healthy and unhealthy fats, calcium, cholesterol, other selected nutrients, and goals for each one. 3. I added pictures of the labels for the supplements I take each day. 4. I enter everything I eat throughout the day so the chart can maintain running totals. 5. I review the totals against my goals, and when I am about halfway through my calorie goals, I ask Chat to recommend foods for the rest of the day. 6. I told Chat about my go-to foods and other foods I like so its recommendations could reflect my preferences, including occasional ice cream. 7. I use Chat's guidance about nutrient combinations, including vitamin D with fat for calcium absorption and vitamin K2's role in helping carry calcium to my bones instead of my arteries. 8. When I was prescribed an antibiotic, I used Chat's medication guidance to learn that taking it with calcium could reduce the medication's absorption, and I adjusted my meals accordingly.

子どもが気に入って毎日読んでいる絵本の付属品が、破れたり紛失したりしてボロボロになっていました。そこで、付属品を写真に撮ってChatGPTに送り、似たものを複製してもらいました。 さらに、もともとは付属していなかったものの、子どもがあったら喜びそうな付属品も追加で作ってもらいました。完成したものをハサミで切ってラミネート加工し、絵本と一緒に渡しました。 ポイントは、絵本のページをいくつか写真でChatGPTに送り、同じようなデザインやテイストのイラストを生成してもらうことです。そうすることで、絵本の世界観を崩さずに付属品を作れます。 Step-by-step: 1. 破れたり紛失したりした絵本の付属品を写真に撮る。 2. 絵本のページをいくつか写真に撮り、ChatGPTに送る。 3. 絵本と同じようなデザインやテイストで、付属品を複製してもらう。 4. 子どもが喜びそうな、もともとは付属していなかった付属品も追加で作ってもらう。 5. 作成した付属品をハサミで切ってラミネート加工し、絵本と一緒に渡す。

I had a project brief to build an e-learning experience that would help people barbecue safely. I used Claude to generate the storyboard, ElevenLabs to create the voice-overs, and Claude Design to bring everything together into a multiscreen e-learning experience with interactive screens. Step-by-step: 1. I used Claude to generate a storyboard for the e-learning experience. 2. I used ElevenLabs to create the voice-overs. 3. I used Claude Design to bring the storyboard and voice-overs together into a multiscreen e-learning experience with interactive screens.

I used Perplexity to find the right earbuds for my iPhone, mainly for light music and calls. It compared AirPods 4, Pro 2, Pro 3, Beats Fit Pro, and Nothing Ear models, breaking down ANC, call quality, Apple ecosystem features, and prices. It helped me see that AirPods Pro 2 gave me everything I needed—strong noise cancellation, seamless pairing, and Spatial Audio—without paying extra for Pro 3 or Beats' upgrades I wouldn't use much. Step-by-step: 1. I described how I would use the earbuds, focusing on light music, calls, and compatibility with my iPhone. 2. I asked Perplexity to compare AirPods 4, AirPods Pro 2 and 3, Beats Fit Pro, and Nothing Ear models. 3. I had it break the comparison down by noise cancellation, call quality, ecosystem features, and price. 4. I separated must-have features from upgrades I was unlikely to use. 5. I chose the model that met the requirements without paying extra for unnecessary improvements.

I moved to France, where my German hunting license is not accepted. As a resident, I have to pass the French hunting exam to obtain a French license. I downloaded a guide for the exam from various internet sources, along with publicly available literature on the relevant topics. I gave these materials to Perplexity and instructed it to develop a preparation course with logically structured learning units covering French hunting vocabulary, exam topics broken down into detailed subunits, game, hunting law, and more. For each unit, I requested a test with 12 questions combining multiple-choice and free-text formats. I also asked Perplexity to include every mistake in the next unit and continue reviewing those errors until I know the material 100%. Now, every second day when I open my computer, Perplexity presents a new unit aligned with my progress and the errors from previous units. The preparation schedule is optimized for the exam this November, with October reserved for reviewing all topics. Step-by-step: 1. I downloaded an exam guide and publicly available literature on the relevant French hunting topics. 2. I provided these materials to Perplexity. 3. I instructed Perplexity to create a logically structured preparation course covering French hunting vocabulary, detailed exam topics, game, hunting law, and related subjects. 4. I required each learning unit to include a 12-question test with a mix of multiple-choice and free-text questions. 5. I asked Perplexity to carry every mistake into the next unit and continue reviewing it until I know the material 100%. 6. Every second day, I open my computer and complete the new unit generated according to my progress and previous errors. 7. I use the schedule leading up to the exam in November, reserving October for a full review of all topics.

I created an online app where my friends can select the gigs they plan to attend. It shows who is going to each gig and when, along with a clear festival-wide timeline. The festival host only provides stage-based schedules, which are difficult to read and coordinate. My app brings the information together in a more practical format for planning with friends. Step-by-step: 1. I created an online app for coordinating festival plans. 2. I added a way for friends to select the gigs they plan to attend. 3. I organized the selections to show who is going to each gig and when. 4. I created a clear timeline that combines the festival’s stage-based schedules. 5. I used the combined timeline to make planning and coordination easier.

Creative ideas often appear in the wrong place: inside unrelated chats, jokes, photographs, or practical problems. The problem usually isn't a lack of ideas. Ideas are scattered across time and conversations, while humans are bad at holding dozens of active threads at once. I built this workflow to turn scattered conversation history into a recoverable creative idea system. Its job isn't to decide what matters; it's to make sure good ideas can come back. I keep four jobs separate: a local script tracks what has been processed, an extraction model finds ideas and recurring language, a synthesis layer connects related concepts across conversations, and I decide whether an idea is alive and worth doing now. Step-by-step: 1. I export chats roughly once a week so the recent past doesn't disappear before it becomes useful. 2. I use an Incremental Archive to compare exports and mark conversations as New, Changed, Unchanged, or Missing. Only new and changed conversations need extraction. I reprocess changed conversations in full because later context can change earlier meaning. The Incremental Archive decides what changed; Creative Idea Recovery decides what is worth remembering. 3. I extract information conversation by conversation, looking for creative concepts, project ideas, visual motifs, writing fragments, systems, metaphors, recurring language, worldbuilding, and unfinished ideas. 4. I preserve the raw language instead of aggressively normalizing labels. “liminal space” and “The Liminal Space” may later mean different things, while “desert” may belong to the same family without being identical. Raw labels are evidence. 5. I build a lexicon above the extraction layer without replacing the original terms. It records aliases for the same concept with different spellings, variants from the same family with meaningful nuance, subtypes that are more specific, related concepts that are connected but not interchangeable, and concepts to keep separate because they are similar but distinct. I normalize obvious formatting noise without flattening meaning. 6. I periodically review recurring container terms such as autonomy, worldbuilding, or liminal space across the corpus. I don't only ask how often a term appears; I ask what different things it is doing across contexts. 7. I leave the long tail alone. Not every strange one-off phrase needs a taxonomy. The Royal Sleeping Tail™ can remain gloriously unclassified. Rare ideas can stay raw until they recur, become useful, or connect to something else. 8. I build a browseable creative inventory so I can ask questions such as: - Show me creative concepts I never made. - Which visual ideas disappeared? - Which concepts resurfaced several times? - Which unfinished ideas fit low physical energy? Each concept can include its name, description, sources, recurrence, status, and timing. 9. I track state lightly so the system doesn't keep rediscovering something already hanging on the wall. 10. I use Timing rather than Priority because creative ideas aren't invoices. I classify them as Now when they are alive and actionable, Someday when they are valuable but not right for this period, Maybe when they are worth preserving, and Unreviewed when they haven't been assessed yet. I make this decision, not the system. 11. I let ideas resurface intelligently by combining timing with recurrence. For example, I can ask, “Show me Now ideas requiring little physical effort” or “Which Maybe ideas have resurfaced three or more times?” An idea that keeps returning may simply be waiting for the right conditions. 12. I use recent scans as short-term continuity. They can say, “You mentioned this once. It seemed meaningful. Here it is again.” I can then answer, “Still alive,” “That passed,” or “This is ready now.” Retrieval is the intervention. 13. I use evidence to challenge unreliable self-assessment, such as “I never have good ideas.” The archive doesn't respond with motivational fluff; it points to evidence of progress that can be hard to feel from inside the current day. 14. I treat renewed access as the real product, rather than the archive itself. The system exists so I can say, “I know I thought about this before. Find it,” “Show me what I already made possible but forgot existed,” or “Give me something worth making today.” When my brain says, “I never have good ideas,” the system can point toward the pile of evidence and say, “I dispute this claim.” For non-octopuses. 😑🐙 A creative life shouldn't require eight arms, perfect memory, and seventeen open mental tabs.

Turn scattered creative preferences into four living style books THE PROBLEM My taste was scattered across old conversations, clothing lists, search terms, saved images, handmade collages and experiments transforming my childhood drawings with AI. I wanted something I could use to make new work, rather than another archive of everything I had ever mentioned. A generic label like “colourful and whimsical” was not enough. My preferences also change with the application: a collage, an outfit, a room and a digital course do not need the same treatment. THE WORKFLOW 1. Bring together different kinds of source material. I used an earlier style conversation, a digital design style document, a list of search terms, photos of my own collages and the corrections I had made during image-generation experiments. Ask AI to read source texts fully, and distinguish your statements from suggestions made by an earlier assistant. 2. Analyse patterns, then correct the interpretation. The AI proposed connections involving colour, texture, shape, atmosphere, vintage objects and visual storytelling. I refined these through concrete examples. For instance, liking stilettos and being able to wear them comfortably are separate facts. Liking geometric structures does not mean I want triangular wallpaper. A technically imperfect image can still work when it preserves the atmosphere I intended. 3. Treat corrections as part of the research. “Too childish” may mean wrong for this drawing’s intended audience, rather than a universal dislike. A saved image may be intriguing without being something I want to keep encountering. An entire family of similar images may appeal to me without needing to rank every member. One especially useful correction: patterns visible in my collages do not prove I consciously planned them. I sort clippings into categories and sometimes colour groups; the collage itself develops while I make it. 4. Include my own categories. My clipping categories include texture, image, black-and-white, colour, background, small meaningful items, comics and words. “Colour” means a clipping kept mainly for its colour, not simply any colour photograph. “Texture” includes both natural surfaces and designed patterns. These definitions provided better starting points than generic categories imposed by the AI. Digital design and graphics also received a full category of their own, rather than being treated as an exception to my taste elsewhere. 5. Create four distinct outputs. • Style Book: precise preferences, boundaries, exceptions and provisional design principles. • Visual Atlas: image families connected across subjects, with actual examples and explanations of what might link them. • Prompt Bible: modular language for colour, material, light, composition, figures and atmosphere, plus reusable recipes and lessons from corrections. • Curatorial Map: connections between interests such as vintage objects, memory, surfaces, small living worlds, language and digital design. 6. Keep the books open to revision. Separate confirmed preferences, observations and hypotheses. When new material arrives, ask what it confirms, refines or contradicts. Add what changes the understanding instead of documenting every conversation. WHAT THIS PRODUCED Four separate first-draft HTML books, including a visual atlas with 14 photographs of my collages. They bring clothing, interiors, fragrance, digital design and creative work into the same research project while preserving their different requirements. WHY IT HELPED The process made my corrections useful. Instead of asking AI to define my taste once, I could respond to concrete interpretations until the descriptions became more accurate. The books support future making without prescribing how I must create. STARTER PROMPT “Use these sources to draft four separate living documents: a personal Style Book, a Visual Atlas, a modular Prompt Bible and a Curatorial Map of Fascinations. Read the source texts fully and distinguish my own statements from earlier AI suggestions. Find recurring patterns, exceptions and unexpected connections. Keep preferences specific to their application, including clothing, interiors, digital design and graphics. Treat my corrections as evidence. Label observations and hypotheses clearly, and do not invent conscious intentions behind intuitive work. Use supplied images in the atlas where available. Build useful first drafts rather than a complete archive, and translate each finding differently for each document’s purpose.”

I used ChatGPT to help create a book in a specialized area of hypnosis. It still needs some refining. The book provides a verbal account of the actions parents need to take to accomplish their goal. It supports both the parents and the child through positive reinforcement. As the parents speak their part, the message becomes ingrained in them as well. Step-by-step: 1. I used ChatGPT to help create the book. 2. I focused the content on the actions parents need to take to accomplish their goal. 3. I used positive reinforcement to support both the parents and the child. 4. I had the parents speak their part so the message would become ingrained in them as well.

For years, I kept lists of things I wanted to look up someday: names, historical references, places, traditions, techniques, unfamiliar concepts, and strange terms I encountered along the way. Most of them lived in Google Keep. They were little bookmarks for my attention: > “I don’t know what this is yet, but something about it caught me.” The problem was returning to them. Looking everything up separately takes effort, especially when I cannot remember why I saved a particular term. So I use AI to turn a batch of those notes into small doors I can open. The basic idea I give AI a list of terms and ask for short, accessible introductions—just enough to understand what each thing is and decide whether I want to learn more. Then I react. Some entries get a quiet “interesting.” Others get: > “OOOH. Tell me more about THIS one.” That reaction determines the next branch. Step-by-step: 1. I copy a manageable batch from my notes. The items do not need to belong to the same subject. A batch might contain an artist, a religious figure, an architectural technique, a place, and an unfamiliar philosophical term. 2. I keep any context I recorded, such as where I encountered the item, what caught my attention, or whether there was a picture, quotation, object, or question attached. That context can help AI interpret an ambiguous name and reconnect me with the original curiosity. 3. I ask for small introductions. My request is roughly: > “Give me a short, accessible introduction to each item. Explain what it is, what makes it interesting, and a few directions I could explore. Flag ambiguous names or uncertain identifications. Keep the first pass light so I can choose what pulls me.” The first pass should make choosing easy. A deep report on every entry would bury the interesting parts under another backlog. 4. I read the introductions and respond naturally: “More about this one,” “How did that tradition begin?”, “Show me what it looks like,” “Why does that material behave like that?”, or “Wait, is this connected to the thing we discussed earlier?” I do not have to justify why one item suddenly becomes fascinating. The other entries can stay for later. 5. Once something catches, I follow the question that appears. An explanation introduces a new term, an image reveals a detail, the detail raises a question, and the question leads somewhere unexpected. For example, a visit to a small chapel prompted questions about a Madonna statue represented in the style associated with Lourdes. That opened into saints, prophets, religious imagery, and how particular figures become visually recognizable. The chapel provided the first door; the next questions appeared while I explored. 6. I use AI suggestions as invitations. AI can suggest entries I might enjoy based on interests that have emerged in our conversations, helping me notice an unfamiliar item I might otherwise skip. My response still steers the exploration. I can follow the suggestion, ignore it, or become absorbed in something completely different. The useful feedback is often immediate: “Yes, more of that,” “Too technical,” “I want the historical story,” or “The visual part is what interests me.” 7. I keep only what I want to return to. Sometimes I save a useful explanation, source, image reference, or new question. Some discoveries later feed into my creative research database. Sometimes the conversation itself is enough. There is no requirement to turn the discovery into a project, course, post, or finished piece. Learning something because it was interesting already counts. If I save a trace, I keep what will help me reconnect later: what it was, what interested me, and where I could continue. 8. I leave room for changing curiosity. An item that feels dull today may become fascinating after another encounter gives it context. Unchosen entries therefore remain available. A backlog is a reservoir, not a queue I must finish. This also makes mixed lists useful: the next interesting connection may come from crossing subjects rather than staying inside one category. The workflow in one line Collect loose curiosities → ask AI for small introductions → notice what pulls → follow emerging questions → save useful traces → return when something feels alive again. Why I use it This workflow makes the first encounter with an unfamiliar subject easy enough that I actually begin. I do not need a polished research question. I can arrive with a strange word from a note written three years ago and say: > “What was this little creature again?” AI helps open the door. My curiosity decides how far we wander. 😅📚

I turned vague fragrance preferences into a usable scent profile by combining perfume notes, dislikes, changing sensory perception, and real-world feedback. I started by telling AI which perfumes I already liked. Rather than immediately recommending more fragrances, it broke those perfumes down into their notes and broader families, such as floral, woody, musky, citrus, sweet, powdery, spicy, green, and amber. I used product information from a qualitative webshop I liked to support that analysis. I then added scents and individual notes I do not enjoy. That distinction matters because liking a perfume does not necessarily mean liking every ingredient in it. A note may work beautifully in one composition and become overwhelming in another. My perception of fragrance had also changed. After a long period of not smoking, many scents seemed to arrive more sharply than before. Perfumes I might once have experienced as soft or pleasant could now feel much more intense. The important part is that AI does not treat perfume notes as a fixed formula. Instead of assuming, “You like vanilla, therefore recommend vanilla perfumes,” it can learn something more nuanced: “You like vanilla when it is softened by certain notes, but dislike it when it is combined with others, and you currently experience certain sharp notes more strongly.” Price can become another layer rather than a separate search. Once a promising scent profile emerges, AI can look for fragrances with similar structures at different price points. The result is a personal scent map: not only a list of perfumes I like, but an evolving model of why certain combinations work for me. The best validation is eventually reaching the highly scientific fragrance classification: > “HALLELUJAH, HOW GOOD DOES THIS SMELL?!” 😂🌺 Step-by-step: 1. I listed perfumes I already enjoy. 2. I analyzed their notes, scent families, and recurring combinations, using product information from a qualitative webshop I liked. 3. I added notes and fragrance types I dislike on their own. 4. I described how perfumes actually feel when worn, using reactions such as sharp, soft, warm, clean, heavy, sweet, fresh, comforting, or overwhelming. 5. I used those reactions to refine my scent profile. 6. I generated new fragrance suggestions based on the emerging pattern. 7. When a perfume looked promising but was expensive, I asked for similar lower-cost alternatives. 8. I smelled or wore the suggested fragrances in real life. 9. I fed my reactions back into the model, including whether a scent was too sharp or sweet, became nicer after an hour, had an opening I loved but a dry-down I disliked, or was simply amazing. 10. I repeated the process until the recommendations became increasingly precise.

I made Claude Code my apprentice CAD designer because I don't know anything about engineering. My wife needed a ring container to attach to her water bottle at the gym. I drew my idea for a threaded container and told Claude to prototype it. The first few prints were rough. But after the 8th prototype, we had the perfect design. Step-by-step: 1. I sketched the threaded ring-container idea and described how it needed to attach to a water bottle. 2. I gave the sketch and functional requirements to Claude Code and asked it to act as an apprentice CAD designer. 3. I turned the proposed design into a first physical print. 4. I tested each prototype, described what was wrong, and asked Claude to revise the design. 5. I repeated the print-and-feedback loop until the eighth prototype fit and worked correctly.

I use AI to turn my watch history into a personal recommendation engine that can answer situational questions such as, “What should I watch tonight?” Generic recommendation algorithms know what is popular and what resembles something I clicked before. They usually know much less about why I want to watch something tonight. For this workflow, I give AI two different datasets: - Already watched: Evidence of my actual viewing history and taste. - Want to watch: Shows my curiosity, intentions, and unexplored directions. This should not automatically be treated as proof that I will like something. AI analyzes both lists for patterns such as genre, themes, emotional intensity, pacing, humor, visual atmosphere, storytelling style, cultural interests, darkness versus comfort, realism versus imagination, and other recurring preferences. Instead of reducing everything to genres, the workflow builds a descriptive taste profile. It keeps confirmed preferences separate from hypotheses based on the watchlist and uses my later reactions to refine the profile. When I want a recommendation, I add my current context: available time, mood, energy, desired emotional intensity, whether I want something comforting or challenging, and whether I want a movie or an episode. The system matches that temporary context against my longer-term taste profile and the available watchlist. So instead of asking: > “Recommend me a good series.” I can ask: > “I have about 90 minutes, my brain is tired, I want something comforting but not stupid, and I don't want anything emotionally brutal tonight.” The recommendation is based on three layers at once: past taste, future curiosity, and present state. Over time, the system becomes less like a recommendation list and more like a personal cultural navigation tool. Step-by-step: 1. I import or paste my watched films and series. 2. I add a separate list of things I still want to watch. 3. I ask AI to analyze recurring themes and less obvious connections. 4. I build a descriptive taste profile rather than reducing everything to genres. 5. I keep confirmed preferences separate from hypotheses based on the watchlist. 6. I use my later reactions to refine the profile. 7. When choosing something to watch, I add the current context, including available time, mood, energy, desired emotional intensity, whether I want something comforting or challenging, and whether I want a movie or an episode. 8. I match that temporary context against my longer-term taste profile and the available watchlist.

When my sixth-grade daughter needs math help, I sometimes feel a bit lost myself. Some of the teaching methods have changed since I was a kid, and I don't always have time to dig through her textbooks. So I use ChatGPT to walk me through problems step by step — in French, since that's how she learns — so I can actually explain them to her in a way that makes sense. Step-by-step: 1. I brought ChatGPT the sixth-grade math problem and the teaching method being used in class. 2. I asked it to solve the problem step by step instead of jumping directly to the answer. 3. I requested the explanation in French, since that is the language my daughter uses at school. 4. I asked follow-up questions about any step I did not understand myself. 5. I used the final explanation to teach the method back in a way that matched her classroom.