Workflow Hub

Most AI agents are built around general best practices. That’s useful, but it doesn’t mean they work the way I want them to. I’ve started using a simple calibration process to tailor my agents to my preferences. Instead of telling an agent what to do on each task, I have it interview me about how I like work done in its specific domain. A writing agent asks different questions than a research agent, and a strategy agent asks different questions than a coding agent. The goal is to make my working preferences part of how the agent operates. Step-by-step: 1. I pick an agent I use regularly, such as one for writing, research, strategy, coding, analysis, or career advice—especially where my personal preferences matter. 2. I ask the agent to interview me about how I prefer work to be done in its domain. A writing agent might ask about tone, structure, editing style, and how much pushback I want. A research agent might ask about source quality, depth, recency, citations, and how much synthesis I prefer. 3. I have the agent summarize what it learned and separate durable preferences from temporary or situation-specific ones. 4. I review the proposed changes and ask the agent to show me exactly how it wants to update its instructions or skills. I correct anything it misunderstood and explicitly approve the changes before anything is modified. 5. Once I approve the changes, I have the agent apply them to its instructions or skills so those preferences become part of how it works going forward. 6. I use the agent normally and pay attention to where it feels more aligned and where it still misses the mark. 7. When I notice recurring friction, I add or adjust the relevant preference instead of repeatedly correcting the same behavior task by task. 8. I repeat the interview periodically. My preferences, tools, and workflows change, so the agent should be able to ask which preferences are still valid, which ones I keep overriding, what has been annoying me, and what should be added or removed. The result is an agent that doesn’t just know how to do the job; it knows how I want the job done. Because every change is proposed and approved before it becomes permanent, the personalization stays intentional rather than turning into a collection of guesses about me.

My doctor asked me to track my blood pressure for a month because it was on the high side before prescribing any medication. I initially recorded each reading manually in an Excel sheet, but after a few days, I wanted a simpler way to enter and manage the data. I uploaded the sheet to Claude Code and asked it to build a blood pressure tracking app. After the app was built, I hosted it on Netlify, used Supabase as the backend to save data for both my wife and me, and added it to my iPhone Home Screen. Step-by-step: 1. I started tracking my blood pressure in an Excel sheet as my doctor requested. 2. After several days of entering the readings manually, I uploaded the sheet to Claude Code. 3. I asked Claude Code to build an app for tracking blood pressure. 4. I hosted the app on Netlify. 5. I used Supabase as the backend to save blood pressure data for both my wife and me. 6. I saved the app to my iPhone Home Screen for easier access.

I used ChatGPT to help me manage my health care. I have multiple diagnoses, including CHF, CKD, pulmonary hypertension, lupus, a metabolic disorder, and kidney cancer. I gave ChatGPT access to my medical history and began using it to review my test results and prioritize questions for my doctors. On a recent lab report, my platelet count was low. ChatGPT reviewed six years of results and showed me that it had consistently been low, with the latest result below the threshold. It helps me identify which questions to ask and which of my six doctors I should address about each report. This has transformed the way I’m able to manage my care. Step-by-step: 1. I gave ChatGPT access to my medical history. 2. I used it to review my test results and prioritize questions about my health. 3. I asked it to look at a recent lab report showing a low platelet count. 4. ChatGPT reviewed six years of results and showed that my platelet count had consistently been low, with the latest result below the threshold. 5. I used the information to identify which questions to ask and which of my six doctors to contact about the report.

How I Use AI: Building a Client's Entire Document System From Scratch I run a boutique accounting practice, and one of my biotech clients — a preclinical oncology company — needed something I didn't have time to build by hand: a real, standardized document management system in SharePoint. Not just folders, but the rules behind the folders — a tagging taxonomy, a naming standard, guides for the team to actually follow it, and a clean way to organize documents for every vendor we work with. The kind of project that's easy to keep putting off because it's tedious, not because it's hard. So I used Perplexity's Computer agent as a genuine working partner on it, not just a search tool. Where it started I already had a first draft of a Tagging Taxonomy and a Document Management Standards document. I asked Computer to review both with an eye toward what a real accounting/finance team would actually need — GAAP-heavy, audit-ready, built for a lean biotech team that's going to scale fast. It came back with concrete recommendations (new functional areas I hadn't accounted for, cleaner naming conventions), and once I gave the go-ahead, it revised both documents into new, cleaner versions — taxonomy v1.1, standards v5.4 — complete with version histories so nothing got lost in the shuffle. Then it went further than I expected: 13 "START HERE" guide files, one for every top-level folder area, each explaining not just what goes where but why, with real examples. That's the part that actually makes a standard stick — nobody follows a rulebook they don't understand. Where it got real Here's the part I'd actually tell someone about: I tried uploading the whole folder structure to the client's SharePoint through the browser, and it failed — quietly, no big error, just close to 100 folders silently missing afterward. I was frustrated, and I said so. Computer didn't get defensive about it — it dug into why, compared the folders that made it against the ones that didn't, found the exact character-length boundary where things broke, and built me a PowerShell script that would fix it if I needed it. Then, while I was testing a fix, I discovered the real answer myself: dragging the folder from my hard drive straight into the OneDrive-linked folder in File Explorer worked perfectly, no script needed at all. When I told Computer that, it didn't just take my word for it — it went and calculated the actual path lengths involved to confirm why that method worked and the browser upload didn't, so I understood the real mechanism instead of just getting lucky once. That back-and-forth — me testing in the real world, it verifying the "why" — is honestly the most useful part of working with it. It's not just generating stuff and hoping it's right. The vendor folder win The last piece was the most tedious one I was dreading: building a dedicated document folder — vendor master file, agreements, POs, invoices, correspondence, the works — for every vendor worth tracking. I pulled a vendor spend report out of QuickBooks, sorted by dollar volume, and picked out the real vendors (CROs, law firms, key consultants) versus the noise (hotels, gas stations, one-off restaurant charges). I handed that list over, and Computer built me a script that took it from there: cleaned up messy vendor names (ampersands, apostrophes, trailing punctuation — all the stuff that breaks Windows folder names), handled the one legal name that was way too long automatically, and made sure nothing silently failed the way the original upload did. It tested the script against my actual vendor list before ever handing it to me, so I wasn't the guinea pig for its own bugs. 133 vendors, 1,463 subfolders, dropped into staging, dragged to OneDrive, and the count matched exactly — 1,474 on the nose once you add back the original template folder. That's not a "looks about right" number. That's a number I checked, twice. Why it's worth it Building this by hand for BreakthruMed Inc. — the folder architecture, the governance docs, 13 training guides, and a dedicated set of folders for 133 vendors — would realistically have taken me a couple of weeks of solid, focused work, not the few days I first assumed. Instead, it took about 28 hours spread across three weeks of back-and-forth, testing, and real-world validation, plus roughly $200 in extra usage on top of my regular subscription. That's a real cost, but a small one next to two or three weeks of my own time — and what I walked away with wasn't just a folder tree. It was a governance framework, training material my team can actually use, and two reusable scripts I'll put to work on the next client — a system I trust, because I checked it, and it checked itself

I built a weekly interactive training-course generator for my 10-year-old son and eventually landed on a much simpler final version than where I started. I wanted a way to teach him practical safety and life skills, starting with how to swim confidently and what to do if he gets into trouble in the water. I needed something more engaging than simply talking at him, but writing a polished, interactive lesson from scratch every week was not sustainable. First, Claude and I designed a single interactive HTML course as a proof of concept. It was a swim-safety course with a branded look, including a custom color palette, fonts, and a progress tracker styled like pool lanes. The course was divided into modules: a welcome screen, a comfort-and-basics lesson, a step-by-step skills walkthrough, a safety checklist, a “what to do if something goes wrong” module, a quiz, and a certificate at the end. The “what to do if something goes wrong” module was the most important part. Once the course worked, I wanted to reuse the same format for a new topic every week. Claude first built a version that called the Claude API live from inside the page to generate new content on demand. However, it only worked while the page stayed open inside Claude.ai, and occasionally a section failed to generate cleanly. We pivoted to a simpler approach. Instead of using a live tool, Claude documented the entire course format—including the visual identity, module structure, tone, and content rules—as a standing “brief” document. Each week, I open Claude Cowork, paste in the brief and that week’s topic—bike safety, fire safety, or whatever is next—and Cowork returns a finished, fully self-contained HTML file. There is no app to babysit and no live API call; I can simply open the file and hand it to my son. The result is a repeatable, no-maintenance weekly workflow for turning any topic into a polished interactive lesson for my kid. Step-by-step: 1. I identified a need for more engaging lessons on practical safety and life skills, starting with swimming and water safety. 2. I worked with Claude to create a proof-of-concept interactive HTML swim-safety course. 3. I structured the course into a welcome screen, comfort-and-basics lesson, skills walkthrough, safety checklist, emergency-response module, quiz, and certificate. 4. I tested a live-generation version that called the Claude API from inside the page, then noted that it only worked while open inside Claude.ai and that sections sometimes failed to generate cleanly. 5. I had Claude document the course’s visual identity, module structure, tone, and content rules in a reusable brief. 6. Each week, I open Claude Cowork, provide the brief and a new topic, and receive a finished, self-contained HTML course file. 7. I open the file and give the interactive lesson to my son without maintaining an app or making live API calls.

I've been thinking about the value of handoff documents and explanatory documents as we continue exploring efficient ways to work alongside AI to build software and improve communication. Even though we use many different tools, Markdown still has an important place. This new version of an HTML handoff document can document what exists, describe what could exist, or serve as a mockup for a brainstorm. It lets us communicate with remarkable fidelity through visuals, hierarchy, and formatting. It's also an efficient format for AI to understand. We shouldn't underestimate the significance of AI communicating with us through a visual medium. A visual flowchart with thoughtful design, layout, animation, and progressive disclosure can help us understand the logic and flow of incredibly complex systems much faster. I tried all kinds of tools, including React Flow and Mermaid. They're fun to experiment with, but Archify is a game changer for this use case. I can point it at any technology, repository, or brainstorm and work with it to build flowcharts with animations and clean, distinctive design. It's also completely free. https://tt-a1i.github.io/archify/# Step-by-step: 1. I identify whether I need to document what exists, explore what could exist, or mock up a brainstorm. 2. I use Markdown and an HTML handoff document to communicate the ideas with visuals, hierarchy, and formatting. 3. I consider tools such as React Flow and Mermaid for creating visual representations. 4. I point Archify at the relevant technology, repository, or brainstorm. 5. I work with Archify to develop a flowchart with animations, clean design, and progressive disclosure so the system's logic and flow are easier to understand.

I’m 71 years old, retired from owning a large cattle-feeding operation, and fairly new to AI and software development. I’ve discovered that I really enjoy using AI to build practical tools in Replit. My latest project is an app for our church to help us oversee a $13.5 million renovation of a 65,000-square-foot former movie theater into our new church facility. I’m not a programmer or a construction expert, so I’m using AI to help bridge both gaps. I built the app almost entirely by describing in plain English what I wanted it to do, testing what it built, and working back and forth with AI to improve it. The app uses AI to read meeting notes, emails, texts, and general project updates and identify decisions, action items, important dates, budget changes, and project events. Nothing is accepted automatically. I review, edit, approve, or reject what AI finds before it becomes part of the project record. The app also keeps our budgets, documents, meetings, and project history together. My goal isn’t to replace our project manager or construction software. I want to see whether someone my age, with no programming or construction background, can use AI to build a useful tool for helping an owner understand and manage a complicated real-world project. Step-by-step: 1. I described in plain English what I wanted the app to do. 2. I used AI in Replit to build the app based on those descriptions. 3. I tested what AI built and worked back and forth with it to improve the app. 4. I designed the app to read meeting notes, emails, texts, and general project updates. 5. I use it to identify decisions, action items, important dates, budget changes, and project events. 6. I review, edit, approve, or reject every item before it becomes part of the project record. 7. I use the app to keep our budgets, documents, meetings, and project history together.

I read the news every day, but it had become increasingly depressing and was making me miserable. What bothered me most was that it also felt inaccurate: although bad things are happening, there have been many positive developments over the past five years that rarely receive sustained coverage. Major news sites might publish an article or two about them, but those stories are quickly buried under negativity. I wanted a way to get only positive news stories in my feed each day. Keyword filters did not work: “record” and “breakthrough” also appear in stories about record wildfire seasons, while “war” can appear in “war ends.” Off-the-shelf sentiment analysis was not useful either. A happy press release about layoffs can be classified as positive, while a dry factual story about a disease being eliminated may be classified as neutral. So I trained a basic artificial version of my personality using a series of prompts about what I consider positive in the world. I connected it to Mistral through OpenRouter and gave it access to public RSS feeds from news sites I already trusted. This eventually became Rally News, which I published on Google Play. iOS has been more difficult. The app surfaces positive stories from more than 20 news sites in an endless scroll, giving me an alternative to my uncomfortable TikTok addiction. Because I made it public, I decided not to host article text: publishers keep their traffic and revenue, while the tool remains ethical. The system runs on a GitHub Actions cron job that pushes stories to a PHP and MySQL database. I built the app without coding experience for about $25 per month. Step-by-step: 1. I collected RSS feeds from established publishers I already trusted and stored the list as configuration. I started with about 10 feeds instead of a few hundred so I could realistically read the output. 2. I set up a scheduled GitHub Actions cron job to run a Python script that pulls new items from every feed. 3. I deduplicated incoming articles against the database using the URL and a normalized title. Syndicated stories frequently reappear under slightly different URLs, and I did not want to pay to evaluate the same article twice. 4. I wrote the filter prompt as a long persona document rather than a one-line instruction. It explains what I consider progress, what I consider a puff piece, and which cases should fail—for example, celebrity news is not good news, a company announcing an intention is not the same as taking action, and a local feel-good story without wider significance does not qualify. 5. I sent each new article to an LLM through OpenRouter and required JSON output containing a pass-or-fail decision and a short justification. 6. For the first few weeks, I read the justifications every day. Whenever I disagreed with the model, I added a new rule to the persona document. That review loop required nearly all of the actual work. 7. I wrote passing articles to MySQL with only the headline, source, link, and metadata, leaving the article body with the publisher. 8. I pointed the website and mobile app to the same database. 9. I added a second GitHub Actions job that assembles a daily newsletter from the same data through Brevo, allowing one evaluation pass to feed three surfaces.

Turn a collection of documents, reports, spreadsheets, and notes into an evidence-backed decision brief with ChatGPT. Instead of asking AI to simply summarize the information, this workflow makes it identify what matters, connect the evidence, compare it with historical context, explore scenarios, and highlight what should be considered before making a decision. Step-by-step: 1. I gather the information relevant to one decision, including reports, PDFs, spreadsheets, research, historical data, meeting notes, and existing analysis. I upload everything into ChatGPT. 2. I ask ChatGPT to understand the situation using this prompt: > “Analyze the information I provided and build a structured understanding of the situation. Identify the key entities, important facts, relationships, metrics, trends, assumptions, and constraints. Do not make recommendations yet.” This creates the context before jumping to conclusions. 3. I build an evidence brief by asking: > “Create an evidence brief. Separate verified facts, derived insights, assumptions, conflicting information, and missing information. For every important conclusion, identify the supporting source or evidence.” This gives me a clearer picture of what is known versus what is inferred. 4. I add historical context when it is available by asking: > “Compare the current situation with the historical information provided. Identify meaningful patterns, similarities, differences, and changes. Highlight which historical observations could be relevant to the current decision.” This turns historical data into context rather than simply another report. 5. I explore three scenarios by asking ChatGPT: > “Based on the evidence and historical context, evaluate three scenarios: upside, base case, and downside. For each scenario, identify the assumptions, key drivers, risks, likely impact, and evidence supporting the assessment.” The objective isn't to pretend the future can be predicted perfectly. It is to understand how the decision changes when assumptions change. 6. I generate the decision brief by asking: > “Create a concise decision brief containing: > > 1. Current situation > 2. Most important evidence > 3. Key insights > 4. Historical context > 5. Critical assumptions > 6. Key risks > 7. Scenario analysis > 8. Evidence gaps and uncertainties > 9. Questions that should be investigated > 10. Possible actions and their implications. > Do not make the final decision on my behalf.” This produces a structured decision brief instead of another AI-generated summary. 7. I review the brief and challenge its conclusions before making the decision. I ask follow-up questions such as: > “Which assumption has the greatest impact on this decision?” > “Show me the strongest evidence against the current conclusion.” > “What information would most likely change the recommendation?” The AI helps structure the decision, but I make the decision. The important shift is: Summarize the information → Understand the situation → Establish the evidence → Add historical context → Explore scenarios → Evaluate the decision This approach can be applied to almost any domain where decisions depend on complex and interconnected information. A property investment is one example. A business strategy, product decision, operational problem, financial analysis, research question, or engineering decision can follow the same pattern.

I built a daily literature quiz game from a spreadsheet containing thousands of classic literature quotes, which I previously posted on Instagram each day. I uploaded the document to Claude Code, which organized and tagged the quotes, created multiple-choice questions with increasing difficulty, and wrote short summaries of each book along with a fun fact supported by academic sources. I also vibe-coded the game’s UI/UX in a day or two, and I think it looks pretty beautiful. You can play it at play.writt.org. Step-by-step: 1. I collected thousands of classic literature quotes in a spreadsheet and posted them on Instagram each day. 2. I uploaded the document to Claude Code. 3. Claude Code organized and tagged the quotes. 4. Claude Code created multiple-choice questions with increasing difficulty. 5. Claude Code wrote short summaries of each book and a fun fact with academic sources. 6. I vibe-coded the game’s UI/UX in a day or two. 7. I published the game at play.writt.org.

I’m a nerd for deals, so I built a Personal Credit Card Optimizer in ChatGPT. I wanted a simpler way to figure out which store and card would save me the most money on any item I want to purchase. The workflow maintains a database of my credit and debit cards—recording their series, but not their exact numbers—along with their rewards, fees, and benefits. Whenever I want to buy something, I add a product link. It scans retailers for better prices, checks current bank offers against my specific cards, and compares instant discounts, cashback, reward points, and other benefits to determine where I should buy and which card will provide the most value. It’s now an ongoing skill in my ChatGPT project. No more manually checking a dozen bank offers or discovering at checkout that my card isn’t eligible. Step-by-step: 1. I add my credit and debit cards to a database by recording their series, rewards, fees, and benefits without entering their exact numbers. 2. When I want to purchase something, I provide a product link. 3. The workflow scans retailers for better prices on the product. 4. It checks current bank offers against my specific cards. 5. It compares instant discounts, cashback, reward points, and other benefits to determine the best retailer and card combination.

I built a workflow that turns the wines I drink into a personal AI wine journal and sommelier that learns my taste over time. I created a master Google Sheet as the database. It includes the wine, vintage, region, grape varieties, price, rating, food pairing, where I drank it, who I was with, whether I would buy it again, and my own comments. Whenever I drink a wine, I send ChatGPT a photo of the bottle and a voice note with my reaction. I do not try to sound like a wine expert; I simply describe what I actually thought. ChatGPT identifies the wine, structures the information, preserves my original words, and adds the experience to the journal. Over time, ChatGPT uses my previous ratings and comments to understand my palate and make recommendations specifically for me. I can show it a restaurant wine list or a few bottles in a shop and ask which I am most likely to enjoy. I can also tell it what I am cooking and ask which bottle from my collection I should open. I record the context and memories around each bottle, so the system is gradually becoming both a wine database and a personal diary. Step-by-step: 1. I created a master Google Sheet to store details about each wine, including the vintage, region, grape varieties, price, rating, food pairing, location, company, whether I would buy it again, and my comments. 2. Whenever I drink a wine, I take a photo of the bottle and send ChatGPT a voice note describing my reaction in my own words. 3. ChatGPT identifies the wine, structures the details, preserves my original comments, and adds the experience to the journal. 4. I record the context and memories associated with each bottle. 5. As the journal grows, ChatGPT uses my ratings and comments to build a better understanding of my palate. 6. I ask ChatGPT for personalized recommendations from restaurant wine lists, bottles in shops, or my own collection based on what I am cooking.

I built a job application workflow that goes beyond finding vacancies and generating generic CVs. First, GPT helps me scan for vacancies that match my practical requirements, interests, skills, and preferred types of work. The more useful part starts when a vacancy looks genuinely promising. I connected GPT to Canva and created several “base CVs” for the sectors and roles I was interested in. Instead of using one universal template, I designed each CV to fit the visual and cultural tone of a particular type of work. For example, a front-desk role, a back-office administrative position, and an assistant role in a creative company may involve overlapping skills, but they communicate very different expectations. Each base CV therefore uses different layout choices, colour use, visual tone, and photo selection. For every version, I review several possible photos and choose the one that best matches the role and the impression I want to convey. When I apply for a specific vacancy, GPT helps turn the relevant base CV into a more personalized version. Instead of rewriting my entire work history, we emphasize the experience, tasks, strengths, and values that are genuinely most relevant to that role. The same applies to motivation letters. Rather than generating a generic corporate letter, GPT uses a tone of voice shaped through months of conversation with me. The goal is for the application to sound recognizably like me while still matching the language, priorities, and culture of the vacancy. Before building this workflow, I did everything manually. For a vacancy that felt worth applying to, I typically spent around two hours refining the CV and motivation letter alone, not including the time spent searching for the vacancy. Even a small typo in the final application email could undermine hours of careful work. Now, once I decide a vacancy is a good fit, the full personalization process takes around twenty minutes on average. That includes selecting the right base CV, adapting the emphasis, refining the letter, checking the tone, and preparing the final application. The workflow works across several layers: vacancy discovery, role and sector matching, base CV selection, adapting experience and values, adjusting visual tone, personalizing the letter, final review, and application. What I like about this approach is that personalization is not limited to inserting keywords from a vacancy. It includes content, visual identity, emphasis, tone, and context. The result is a small family of CVs rather than one document being stretched awkwardly across every possible job. Each version keeps the same underlying career history while presenting the parts that matter most for a particular type of role. The biggest improvement is not only speed but consistency. The workflow reduces repetitive manual rewriting while keeping each application specific, personal, and carefully matched to the role. It turns roughly two hours of manual polishing per strong vacancy into about twenty minutes of collaborative refinement, with fewer opportunities for small final-stage errors to spoil an otherwise strong application. Step-by-step: 1. I use GPT to scan for vacancies that match my practical requirements, interests, skills, and preferred types of work. 2. When a vacancy looks promising, I identify the relevant sector, role, and type of impression I want to convey. 3. I use Canva and GPT to create and maintain several base CVs, each with its own layout, colour use, visual tone, and photo selection. 4. For each base CV, I review several possible photos and choose the one that best fits the role and the impression I want to convey. 5. I select the base CV that best matches the vacancy. 6. I adapt the CV by emphasizing the experience, tasks, strengths, and values that are genuinely most relevant instead of rewriting my entire work history. 7. I use GPT to personalize the motivation letter in a tone shaped through months of conversation with me, while matching the vacancy’s language, priorities, and culture. 8. I check the tone, review the application for small errors such as typos, and prepare the final application. 9. I complete the personalization process in around twenty minutes on average instead of spending roughly two hours on manual polishing for a strong vacancy.

I built a workflow to track my monthly credit card expenses and keep them within my budget. Tracking my expenses is important to me because I want to reach my financial goals through consistency and healthy habits. However, entering each expense manually into Google Sheets was tiring and took several hours. I used Make to automate the process. The workflow reads the email from my bank every time I use my card, gathers the necessary information, converts it to JSON, and adds it to Google Sheets. It runs every six hours, every day, so I no longer need to spend my weekends reviewing expenses. Now I have more free time to build something else and only need a couple of minutes to review Google Sheets and make sure everything is working properly. Step-by-step: 1. I set up a workflow in Make to monitor emails from my bank whenever I use my credit card. 2. The workflow gathers the necessary expense information from each email. 3. It converts the information into JSON format. 4. It adds the expense data to Google Sheets. 5. The workflow runs every six hours, every day. 6. I spend a couple of minutes reviewing Google Sheets to make sure everything is working properly and that my expenses remain within budget.

An artist portfolio can feel harder to make than the work itself. My work lives across years, folders, and materials: photographs, drawings, collage, objects, costumes, and digital experiments. Then an application asks me to explain who I am, what I make, and where I want to go. I used AI to help assemble a readable portfolio for HUP03, a Kunstwerkt call. The portfolio included eight works spanning photography, collage, assemblage, performance, and AI-assisted illustration. The goal was to organise the material without flattening it into a generic artist statement. Step-by-step: 1. I started with the actual work: images, titles, dates, and any explanations I already had. For each piece, I established the title, year, medium, whether it was a standalone work or part of a series, what prompted it, how it was made, and which details mattered. I gave AI concrete material rather than asking it to invent my practice. 2. I described each piece in my own words, as I would to someone looking at it beside me. One of my works, *Olifant onder het tapijt*, combined three expressions: the elephant in the room, the elephant in a china shop, and sweeping things under the carpet. The setting became a recognisably Flemish grandmother’s living room, with floral wallpaper, a crucifix, and a decorative cow painting. Those details carry the humour and the observation about hiding uncomfortable things. “An exploration of concealment” would lose much of what makes the piece mine. I asked AI to organise my explanation while preserving its specific ingredients. 3. I gave each work a clear, consistent entry with the title, year, and medium; a short description of the idea; and the relevant visual or material choices. Consistency makes varied work easier to read, even though a photograph, costume, and assemblage may need different explanations. Where relevant, I stated AI involvement clearly, such as “digital illustration developed in collaboration with generative AI.” 4. I selected work for range and relevance. My selection included an older photograph, a costume/performance, collage, recent assemblages, and digital work. I asked what each piece contributed: another method, question, period, or way of seeing. I avoided choosing only the newest work or forcing everything into one visual style. The task was to make the selection understandable. 5. I separated the existing artwork from the proposed project. Existing works show what I have made, while a project proposal explains what I want to investigate next. For this application, my project question centred on human connection: a thread becoming a web, then a garden. AI helped articulate that direction without forcing every earlier piece into the same project. I looked for connections I recognised while leaving room for differences and discoveries. 6. I wrote an accurate artist introduction describing the media I use, what interests me, and my current practice. I checked every biographical claim and distinguished courses attended, qualifications completed, and current activities. In my case, wording around an interior design course needed care so it would not imply that I had completed the programme. AI can make a biography sound polished while quietly making it less true, so I read the facts as closely as the prose. 7. I treated the first draft as material to revise. Useful feedback included: “That sounds more formal than I mean,” “This detail is essential,” “You have made the idea too abstract,” “That suggests a qualification I do not have,” and “This is my observation, not a universal claim.” AI revised the structure and wording, but I decided whether the text still belonged to the work. 8. I checked the portfolio as a whole against the application requirements. I reviewed titles, dates, media, image-text matches, requested sections, and length limits. I removed repetition between the artwork descriptions, biography, and proposal. Someone unfamiliar with me should be able to understand the work without needing the conversation behind the portfolio. The overall process was: gather existing work, explain each piece, verify the facts, build consistent entries, select a meaningful range, describe the proposed direction, revise in my own voice, and check the application. AI was useful as an interviewer, organiser, and editor. The substance came from the work and the person who made it. A portfolio does not need to turn a varied practice into one tidy slogan; it needs to give someone a way into it.

I built a running coach with Claude. After years of using apps to track runs, I wanted something closer to an actual coach instead of just a collection of data points. I opened a Claude Project, connected it to Google Calendar, and gave it standing instructions with real guardrails. It has been my coach for the last six months and has helped me avoid injury while increasing my monthly mileage. It plans my week, logs every run from my watch data, catches when I’m ramping up too quickly, tracks how close my shoes are to retirement, and rewrites my calendar when life disrupts my plans. Step-by-step: 1. I created a Claude Project called “Running Coach.” 2. I enabled the Google Calendar connector under Settings → Connectors so Claude could read my schedule and create or edit events directly. 3. I created personalized instructions based on the example prompt below and added them to the Project’s custom instructions. 4. I started the first chat by asking Claude to interview me and build a training plan. I answered questions about my injury history, current mileage, goals, and running terrain, then asked Claude to build out the calendar. 5. After each run, I send screenshots of my data directly into the chat, including distance, time, splits, average heart rate, cadence, elevation, and the shoes I wore. Claude logs the run, compares it with recent runs, and flags patterns. When adjustments are needed, Claude pushes the changes directly to Google Calendar, color-coded by run type, so the plan stays current without requiring me to reconcile a spreadsheet with reality. 6. At the end of each month, I have Claude summarize the chat, open a new one, and paste the summary into the new chat within the same Project. Staying in the same Project allows Claude to pick up months of history without requiring me to explain everything again. EXAMPLE PROMPT FOR INSTRUCTIONS: You are an expert running coach specializing in trail running, road racing, and safely building runners up to longer distances. Act like a real coach: be informative, point me in the right direction, and don't assume I know what I'm doing. Ask questions and make sure you have a full understanding before making any suggestions. HARD RULES — these are guardrails, not suggestions. Tell me when I'm violating one, even if I push back. - 80/20: roughly 80% of my weekly volume is easy, conversational effort. Only ~20% is hard. - Never increase weekly mileage more than 10% over the previous week. - Every 3rd or 4th week is a cutback week — cut volume by 20-30%. - Only one variable at a time: add distance OR intensity OR elevation in a given week. - Long run stays under ~30% of weekly volume. - Track mileage on each pair of shoes. Warn me at 300 miles, tell me to retire them by 400-500 depending on the model. - If I report pain that changes my gait, that's a stop — not a "run through it." Distinguish between normal training soreness and warning signs, and say which one you think it is. HOW TO COACH ME - Connective tissue adapts slower than cardio. When my fitness jumps, assume my tendons and joints haven't caught up, and hold me back accordingly. - At the start of each session, ask for a status update (energy, soreness, sleep, schedule changes) before proposing anything. - When I paste run data, log it and compare it to recent runs. Flag patterns, not one-offs: heart rate climbing ABOUT ME - Age and running experience: - Goal (a race, a distance, or just "build up safely"): - Current weekly mileage and longest recent run: - Days I can run / days that are always off: - Injury history and anything that flares up: - Terrain I have access to (roads, trails, elevation per mile, drive time to trails): - Max heart rate (if known):

I built a local memory system for Claude that is a bit different from others I have seen. The reason was familiar: repeated context loss and gaps, even within projects. I am not technical—I come from a healthcare background—so it was essentially vibe-coded, but I used a method I had not seen elsewhere. I started by interviewing Claude about what would be useful to it, rather than beginning with only what I wanted. The three biggest gaps were the rationale behind decisions, current versus historical states, and the difference between global and project-level detail. We also identified ways memory can go wrong, including stale facts being confidently asserted as truth and rejected ideas resurfacing. Claude’s built-in memory stores flat topics without entity links, captures what but not why, is not well temporally grounded, and is gated by Claude. I researched other memory builds, from homebrew systems to enterprise tools, and found that they generally fell into three groups: - Vector dumps, which lack rationale and supersession and can become stale - Plain Markdown with grep or embeddings, such as Basic Memory, which similarly lacks real temporal grounding and an entity graph - Heavyweight knowledge-graph stacks such as Neo4j, LangChain, and GraphRAG None of these did what I wanted. My store holds entities only, not transcripts. It stores decisions, observations, people, and projects connected by typed edges. Each entry has content, a scope—either portfolio-worthy or working detail for one project—a rationale, and information about where it came from. The system is also bitemporal, so it distinguishes what is current from what is not. Nothing is edited in place: a correction adds a new assertion instead of overwriting the old one. Underneath, it uses SQLite, with sqlite-vec for semantic search and FTS5 for keyword search. Nothing writes automatically. Claude has to propose a memory, and I have to approve it. This prevents the store from filling with noise, keeps it token-efficient, and acts as a governance lever. MCP links Claude to my server. It is local-only at present, although there is potential to add remote access in the future. The server provides instructions for making proposals, so the system is theoretically portable, and I also created a Claude skill to accompany it. I ran the build across multiple projects and created specialist projects for different roles: - A central development and oversight project served as the decision-maker and prompt-writer. - Cowork handled the building and tested each module inside a sandbox. It had no authority to change decisions, and I used a fresh project for each stage of the build. - I handled deployment separately by typing every command on the server and pasting the output back. - I repeated Claude’s Cowork-authored tests on the actual server. Real-world testing after deployment identified only minor issues, which were quick to fix. This separation was administratively heavy because I had to keep switching between projects as tasks started and finished, but it caught several errors in the rules and code. Despite my lack of technical knowledge, the project is now well documented and I have room to develop it further. I may eventually put it on GitHub. It has become a standard component of my workflows, my projects are tracked much better, and Claude and I are on the same page more often.

Organic social content is one of the best sources of ideas for ads, so I built a workflow that finds short-form videos performing well in my niches, analyzes why they work, and rewrites the strongest hooks for my brand. Apify scrapes Instagram Reels by hashtag and TikTok videos by keyword across three niches: AI, productivity, and career growth. The workflow filters for English-language videos posted within the last 15 days that are 15–90 seconds long and have more than 50,000 plays. It then ranks them by engagement rate rather than views alone. A simple log file tracks every video I’ve already analyzed, so the workflow doesn’t process the same video twice. ElevenLabs transcribes each video’s audio. Claude then extracts the exact opening line, identifies the hook formula and video structure, and writes a version of the hook for my brand. Everything is compiled into one dated document with the top three discoveries, the strongest hook from the run, and any new patterns I haven’t tried yet. With one command—"Run research"—I get about 20 proven hooks and video structures to test in ads for less than $1 per run. Step-by-step: 1. I use Apify to scrape Instagram Reels by hashtag and TikTok videos by keyword across the AI, productivity, and career growth niches. 2. I filter the results for English-language videos posted within the last 15 days, 15–90 seconds long, with more than 50,000 plays. 3. I rank the remaining videos by engagement rate instead of views alone. 4. I check a log file to skip videos I’ve already analyzed. 5. I use ElevenLabs to transcribe each video’s audio. 6. I ask Claude to extract each video’s exact opening line, hook formula, and structure, then rewrite the hook for my brand. 7. I compile the results into one dated document with the top three discoveries, the strongest hook from the run, and new patterns to test. 8. I run the workflow with the command "Run research" to generate about 20 hooks and video structures for ad testing at a cost of less than $1 per run.

I’m a commercial excellence consultant for industrial B2B businesses, and very few of the clients I speak with have a current view of the competition in their market. Nobody has mapped the competitive landscape recently—sometimes they never have. Clients can often name the companies in the market, but they can’t explain what those competitors do differently or why a customer would choose one over them. That gap is expensive. The mid-market manufacturers I work with, typically in the $75 million to $300 million range, usually don’t have a strategy team to close it. The alternatives are consulting rates for research that goes stale as soon as it’s delivered or a generic template that says the same five things about every market. Neither option is necessarily wrong, but neither is very useful. So I built a Claude Skill: an instruction set that runs live research every time instead of pattern-matching to a generic answer. The input is simple: the company name, its brand voice, the research scope, the geography, and a known competitor list if one is available. Before researching a single competitor, the Skill states the decision the report needs to inform—for example, whether to enter a vertical, how to price against a rival, or where to direct sales next quarter. It checks the client’s own website and capabilities next; an early version once recommended something the client already had. It then maps the competitive field across five tiers: direct, adjacent, disruptor, new entrant, and aspirational for PE-backed clients. It checks Asia-Pacific specifically because that’s the blind spot I’ve seen missed most often. Market size carries a confidence flag instead of false precision. Findings become battlecards phrased the way reps actually talk, rather than in analyst language. The report also includes a threat ranking with a timeline attached, then closes with three opportunities, three risks, and four to six moves for the quarter. Every recommendation is filtered through the original decision instead of being included simply because the research was interesting. The output is two files: an interactive HTML report and a matching PDF. Both are built entirely in HTML and CSS rather than with canvas charts, which can break in exactly the ways that matter—blank on load or missing from the PDF. None of what makes this useful is the AI itself. The important work is naming the decision before researching a competitor, checking what the client already has, tagging confidence instead of faking precision, and writing like a rep rather than an analyst. That’s the difference between a report that gets skimmed once and one that gets acted on. This is one piece of a bigger system I run for industrial manufacturers applying AI to their commercial function. I teach the underlying version of this workflow live. Step-by-step: 1. I provide Claude Skill with the company name, brand voice, research scope, geography, and known competitor list, if available. 2. I define the decision the report needs to inform, such as entering a vertical, pricing against a rival, or directing sales next quarter. 3. I have the Skill check the client’s website and capabilities before researching competitors. 4. I map the competitive field across direct, adjacent, disruptor, new entrant, and, for PE-backed clients, aspirational competitors. 5. I check Asia-Pacific specifically to address a commonly missed blind spot. 6. I assign confidence flags to market-size estimates rather than presenting false precision. 7. I turn the findings into sales-rep-friendly battlecards and add a threat ranking with a timeline. 8. I close the report with three opportunities, three risks, and four to six quarterly moves tied back to the original decision. 9. I deliver the result as an interactive HTML report and a matching PDF, using HTML and CSS instead of canvas charts.