As a hobby/non-work-related creative outlet, I've started to write and create YouTube videos about retro football (soccer) stories. Part of the visuals are vintage stickers of the players mentioned. This used to be a time-intensive Google/eBay search when I was looking for 20+ players at a time. So I used Claude to build a local "Sticker Search" tool. It lets me enter the player, season, and team, find their sticker from that year, and download it to my working folder with one click. It's made my hobby way more fun and sped up the tiresome bit. P.S. I used Billy's guide on Manus to create the animated logo for the videos! Step-by-step: 1. I listed the inputs I needed for each search: player, team, and season. 2. I used Claude to build the local Sticker Search interface and search logic. 3. I added recent-search shortcuts so I could repeat or refine searches quickly. 4. I made each result downloadable with one click to my working folder. 5. I used Billy's Manus guide to create the animated logo for the videos.

I’m Jesús Núñez, an artist and the owner of J. Nunez Gallery, an independent contemporary art gallery with locations in Summit and Millburn, New Jersey. Founded in 2020, the gallery presents original abstract and figurative art, landscapes, still life, and photography. We help people discover artwork for their homes and work with interior designers on residential projects. Alongside running the gallery, I’m exploring how ChatGPT can help a small business improve its operations, marketing, and decision-making. I manage the business myself, so the practical question is how to turn existing information into useful, completed work. The workflow starts with real source material: website content, spreadsheets, analytics exports, screenshots, and the gallery’s business rules. I use focused conversations to examine one area, prepare concrete changes, and review the results. The work includes website improvements, artwork catalog organization, marketing analysis, audience segmentation, and outreach preparation. For example, AI-assisted troubleshooting helped identify duplicate website page-view tracking and guided its correction, which we checked against live analytics. That is an operational improvement; it is not evidence of increased sales. Another small-business owner can recreate the approach as follows. Step-by-step: 1. Record the business context: customers, products, geographic market, budget, brand preferences, and operating constraints. 2. Choose one specific task and define what completion means. Provide the relevant source material. 3. Require the AI to distinguish verified facts, interpretations, missing information, and proposed actions. It should not guess prices, contact details, or results. 4. Ask for a concrete deliverable, such as revised website copy, a classification table, implementation instructions, or an outreach draft. 5. Review the work and verify the actual result after implementation. Keep preparation, implementation, verification, and blocked work clearly identified. 6. Preserve approved decisions and completed actions in a current record so later sessions can continue from the existing work. 7. Measure qualified inquiries, appointments, proposals, and sales alongside marketing activity. This is an ongoing project. AI can repeat recommendations or lose track of previous decisions, so human review and continuity remain essential. I have not established a measured revenue increase or time-saving figure. I’m testing whether this approach can build a stronger business while allowing more attention for art, artists, and clients. If this example makes you curious about the gallery, you can browse available artwork and find information about our Summit and Millburn locations at https://www.jnunezgallery.com. You are welcome to explore the collection or contact us through the website for help choosing art. Jesús Núñez Artist and Owner, J. Nunez Gallery Summit and Millburn, New Jersey https://www.jnunezgallery.com

I'm a British Academy (BAFTA) voting member. Every autumn, the members' screener platform fills up with more than 100 eligible films—major contenders, obscure documentaries, and hidden gems all mixed together. I have a few weeks to decide what deserves my viewing time before I vote. The fun challenge is finding the sleeper nobody has heard of yet; the problem is the sheer volume of clutter I have to sift through. I built a workflow in Claude Cowork that turns the overwhelming list into an ongoing conversation with a curator that knows my taste. I started by inputting my film notes from previous years: what I watched each season, what I loved, what I abandoned, and why. Claude stores this in persistent memory alongside a growing profile of my taste, including my go-to critic, my low tolerance for slow cinema, the kinds of films that reward me, and my rule that a film gets minutes—not acts—to earn my time. Every session starts with this context already loaded. When a new batch of films drops, Claude opens the screener platform in its built-in browser, reads the full slate, and sends research agents to cover every title in parallel. They research the director, cast, runtime, Rotten Tomatoes scores, festival prizes, awards buzz, and whether my favourite critic has reviewed each film. Claude even pulls the transcripts of his YouTube reviews and summarises the verdict. In about 20 minutes, a 37-film batch is triaged into three categories: priority viewing, worth sampling, and skips. Slow starters are flagged so I know which films need a committed evening and which get 10 minutes to prove themselves. As I watch, I feed verdicts back in plain English, such as “gave it ten minutes, too abstract.” Claude updates both the tracker and its model of my taste, so each recommendation round becomes sharper. By voting time, I have a complete, searchable record of everything I watched and what I thought of it, built conversationally throughout the season. Step-by-step: 1. I input my film notes from previous years—everything I watched, loved, and abandoned, along with my reasons. Claude saves them to persistent memory, which every future session loads automatically, and builds a profile of my taste from them. 2. When new films appear on the members' platform, Claude opens it in its built-in browser and reads the full list of titles. 3. Claude launches parallel research agents to cover every title, including the cast, crew, runtime, Rotten Tomatoes scores, festival prizes, awards buzz, and my preferred critic's verdict from YouTube review transcripts. 4. Claude compiles a triage tracker that ranks every film by viewing priority, flags likely sleepers, and warns me about slow starters. 5. As I sample films, I report quick verdicts in plain English. Claude logs them and continuously refines its profile of my taste, so recommendations improve throughout the season. 6. At voting time, I have a complete record of what I watched, what I thought, and why, built conversationally across the season.

My friend shot a short film and gave me his hard drive to help with post-production. It contained more than 400 clips, with no clear way to tell when each one had been shot. I asked Claude to review the metadata for every clip and group them by timestamp, so they were organized by shoot session instead of sitting in one large folder. Claude also built a spreadsheet listing each clip, its shoot session, the date, runtime, and file size. This saved my friend the hassle of reviewing every clip manually. Step-by-step: 1. I received my friend’s hard drive with more than 400 short-film clips. 2. I asked Claude to review the metadata for every clip. 3. I had Claude group the clips by timestamp and organize them by shoot session. 4. I had Claude create a spreadsheet with each clip’s shoot session, date, runtime, and file size. 5. My friend could avoid going through every clip manually.

I write science fiction and use ChatGPT to make sure my stories stay within certain rules. I use Willow Voice AI for dictation and video generators to create proof-of-concept visuals. I also recently used AI to find quick answers within a 40-minute YouTube video. I turned it from watchbait into quick answers. Step-by-step: 1. I use ChatGPT to check that my science-fiction stories stay within certain rules. 2. I use Willow Voice AI to dictate my writing. 3. I use video generators to create proof-of-concept visuals. 4. I use AI to find quick answers within a 40-minute YouTube video. 5. I turn the video from watchbait into quick answers.

I built Bubble Grotto, a skill-based arcade game for mobile devices, using AI as a development partner. The concept is deliberately simple: start with a small bubble, grow it, navigate through a cave filled with hazards, and decide when to escape. The larger the bubble becomes, the greater the potential reward—but the harder it becomes to manoeuvre safely. The aim was to create the classic “one more go” experience: controls that can be understood almost immediately, with gameplay that becomes progressively harder to master. The interesting challenge was that building a game is very different from implementing a list of features. The code can work perfectly and the game can still be no fun. Timing, movement, difficulty, visual feedback, and risk versus reward all have to feel right when somebody actually plays it. Step-by-step: 1. I used AI to discuss how the core concept should work, including bubble growth, movement, hazards, progression, scoring and rewards, and the escape mechanic. 2. Rather than designing the entire game upfront, I used AI-assisted development to turn each mechanic into working code and get it onto a real device as quickly as possible. 3. Once a mechanic existed, I tested it myself. I checked whether movement was responsive, whether the bubble grew too quickly, whether obstacles were fair, whether escaping was too easy, and whether failure made me want another attempt or simply became frustrating. 4. I brought those observations back into the AI workflow, identified the relevant behavior or code, made targeted changes, and tested again. 5. Once the core loop felt enjoyable, I refined the interface, visual feedback, progression, and presentation instead of allowing cosmetic work to hide weak gameplay. This produced a development loop of: idea → mechanic → playable build → play-test → adjust → repeat The final result is Bubble Grotto, an arcade game with simple controls but increasingly demanding skill-based gameplay. Players grow their bubble while navigating hazards and must balance risk against reward by choosing the right moment to escape. One of the most useful things I learned is that AI can dramatically accelerate game development, but it cannot replace judgment about whether something is enjoyable. AI can help create a mechanic, investigate why it behaves incorrectly, and implement changes extremely quickly. The human still has to play the game and decide: is this actually fun? That combination allowed me to move rapidly from a simple game idea to a functioning mobile game while spending far more of my time experimenting with gameplay than wrestling with implementation.

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.

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.”

Nano Banana Pro has been a step change both for staying true to prompts and also being able to take its own creative liberties. The ability to talk through prompt brainstorming, image edits, and even providing context directly from our newsletter has made for some highly personalized new creative paths. Step-by-step: 1. I gave Nano Banana Pro the newsletter context and the creative goal for the image. 2. I used conversation to brainstorm several possible prompt directions before generating. 3. I created initial images and evaluated both prompt fidelity and the model’s useful creative choices. 4. I described the edits I wanted and kept the relevant newsletter context in the conversation. 5. I iterated toward a more personalized final creative rather than restarting from a generic prompt.

I use this workflow when I want fresh creative input for my visual work and want to expand my inspiration library in Eagle without collapsing into randomness. The starting point is not a generic prompt like “show me inspiring artists.” I give the AI examples of images, artists, materials, traditions, or visual details that already catch my attention. The AI first looks for patterns in what I respond to: color, material, composition, atmosphere, craft techniques, cultural traditions, natural structures, architectural forms, and more. From there, we branch outward. I explore adjacent references across disciplines, cultures, periods, and materials rather than looking only for visually similar work. I react freely to the suggestions: “This texture, yes.” “This artist, no.” “More of that construction method.” “Less decorative.” “Stranger.” “Older.” “Softer.” Those reactions steer the next round of research. One research session, for example, moved through Indian stepwells; Ajrakh and Bandhani textiles from Gujarat and Kutch; Tibetan/Ladakhi painted textiles; Miao baby carriers; Dong wooden bridges; art from Papua; Russian lubok prints; and even 11th-century goldworking in Panama. These references do not belong to one tidy category, period, or geography. That is precisely the point. The session was driven by visual responses and emerging connections involving color, surface, construction, ornament, repetition, symbolism, material, and technique. Each discovery created a new branch to follow. AI made it possible to move laterally across disciplines, cultures, and centuries without losing the thread of what was visually interesting to me. I then selected only the references that genuinely sparked something and added those to Eagle. The result is not just a collection of “similar images,” but a deliberately expanded visual vocabulary. The human remains the curator. AI expands the search radius; taste decides what enters the library. Sometimes there is no initial research question at all. A joke, misheard word, object, memory, or accidental phrase becomes the seed. The value is in allowing associative drift to continue long enough for a real curiosity trail to emerge. > The research does not always begin with a topic. Sometimes the topic is discovered during the wandering. Step-by-step: 1. I start with a few visual references I genuinely like. 2. I ask AI to identify recurring visual qualities and possible connections. 3. I explore adjacent references across disciplines, cultures, periods, and materials rather than searching only for visually similar work. 4. I react freely to the suggestions, noting what I want more or less of, such as a particular texture, artist, construction method, decorative quality, age, or atmosphere. 5. I let those reactions steer the next round of research. 6. I open the references and collect only the images that actually trigger something. 7. I save those images in Eagle as a curated visual library rather than an indiscriminate image dump. 8. I add useful context through folders, collections, tags, or notes so the references can resurface later.

I wanted a publicly viewable leaderboard on the web, with input coming from creators. I prompted Gemini: " Can you design good looking leaderboards using Google documents. I want three: all time, rolling 30 days and rolling 90 days. They should be different tabs on the same document. They should be easy to administer/update. Show me a mockup and describe how it would work." After I was satisfied that it would be easy to launch and maintain, I got more specific. Because it was for creative types, I wanted more than a basic spreadsheet ranking. Gemini responded: "It features profile avatars, gamified badges, high-contrast dark visual styling, and clear ranking tabs for All-Time, Rolling 30 Days, and Rolling 90 Days..." That's what AI calls creative, I guess. Later in the chat, Gemini suggested achievement levels with a more creative feel: - 👑 Century Virtuoso / Platinum Mic - 🔥 Monthly On-Fire / Speedster - 🎙️ Heartstring Weaver - 🌟 Smile Architect For the podium treatment, rows 1, 2, and 3 feature custom metallic highlights—Warm Gold, Silver Slate, and Bronze Copper—with circular numerical rank badges to make top contributors stand out instantly. Gemini heavily integrated Google Docs and Google Sheets. The system uses Google Apps Script to update the leaderboard in real time based on creator activity. Step-by-step: 1. I asked Gemini to design three leaderboards—All-Time, Rolling 30 Days, and Rolling 90 Days—as separate tabs in the same Google document. 2. I asked for the leaderboards to be easy to administer and update, along with a mockup and an explanation of how they would work. 3. After reviewing the initial concept, I clarified that the leaderboard was for creative types and should be more distinctive than a basic spreadsheet ranking. 4. Gemini added profile avatars, gamified badges, high-contrast dark visual styling, and clear ranking tabs. 5. I incorporated creative achievement levels, including Century Virtuoso / Platinum Mic, Monthly On-Fire / Speedster, Heartstring Weaver, and Smile Architect. 6. I used Warm Gold, Silver Slate, and Bronze Copper highlights for the top three rows, along with circular numerical rank badges. 7. I connected the system to Google Docs and Google Sheets and used Google Apps Script to update it in real time based on creator activity.

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.

I built Atlas to turn AI-assisted creative findings into readable project cards with source links, relationships, comments, and a calm HTML interface. Extracting creative findings is only half the job. Once fragments, metaphors, visual ideas, and research trails accumulate, I need somewhere to return to them and keep working. Atlas is that project layer over my old conversations. AI helps me revisit source material and suggests findings worth keeping. I decide what they mean, how to name them, where they belong, and which relationships matter. The results become readable cards. My harvesting system points to conversations that seem rich, and then I revisit them with AI. We identify existing projects, standalone findings, recurring material, and connections. Sometimes the review sparks new ideas. After just two rich conversations, we had 28 cards, including four collection cards and three new ideas. The harvest is the radar. The review is where interpretation happens. Atlas keeps the results usable. Step-by-step: 1. I let the harvest flag chats containing project ideas, unusual language, visual concepts, or unfinished thoughts. It suggests where to look without deciding what matters. 2. I review promising conversations with AI and ask, “What here deserves a place in the creative system?” AI suggests findings and connections, while I correct interpretations, separate unrelated material, and decide what belongs together. The card structure grows out of that dialogue. 3. I create readable cards with information such as a name, category, description, findings, sources, relationships, questions, and comments. The contents depend on the material: a story needs different information from an essay. The goal is to recognise and understand the work when I return. 4. I group recurring fragments into collection cards for language finds, story material, or visual motifs. Individual items stay visible without turning Atlas into hundreds of tiny, barely distinct cards. 5. I link each card back to the original conversations so I can access exact wording, context, and how an idea developed. Several conversations can feed one card, giving me a stable starting point while its source history grows. 6. I record meaningful relationships that I recognise, such as shared themes, predecessors, spin-offs, fictional worlds, or research overlaps. Similar words alone do not establish a meaningful relationship. Categories provide visual orientation, while relationships let me move across them. 7. When I remember a source but cannot find it yet, I leave a comment: “Find and link the old conversation about XYZ.” When it turns up, I attach it and update the comment: “Found it, now linked.” This turns imperfect memory into a useful breadcrumb, so missing sources do not have to stop the work. 8. I use a small green indicator to mark cards with updates I have not viewed yet, such as a new source, finding, relationship, or resolved comment. This shows me where something changed without requiring me to check every card. 9. I let cards stay unfinished. One paragraph, one source, and an open question can already make a useful card, and more context can accumulate later. Reviewing old material can also spark new work, making the archive generative through fresh interpretation. 10. I keep the HTML environment calm and make it feel like a reading room: Browse → recognise → open → read → follow a source or relationship. Code handles IDs, CSV rows, statuses, and consistency checks underneath while I work with readable cards. Each layer answers a different question: the harvest tells me where to look, the collaborative review tells me what is there and what it means, and Atlas keeps the result usable. AI helps me notice and organise, while I assign meaning. Atlas preserves the results with the original conversations available underneath. I can navigate backwards to the source and sideways to related work, starting wherever I am. The harvest tells me where to look, the review tells me what I found, and Atlas makes sure I can use it again.

I use Ideogram and Reve for newsletter images, and they're impressively good even with minimal prompts. I'll set a general style and tone, and they consistently deliver solid renderings of the tech personalities we cover — the style has become part of our storytelling. Step-by-step: 1. I defined the general style and tone I wanted the newsletter illustrations to share. 2. I prompted both Ideogram and Reve with the same editorial subject and visual direction. 3. I compared which model produced the strongest rendering for each tech personality. 4. I refined the selected image while preserving the recurring style. 5. I reused the visual language across editions until it became part of the newsletter’s storytelling.