Workflow Hub

I build, test, ship, and promote an iPhone and iPad reading app with Claude Code agents, each with a specific job. I wanted a reader for my own PDFs and EPUBs where I could write notes in the margin next to the line they belonged to. Nothing I tried did that well, so I built Helicon, a free reader for iPhone and iPad. I use it every day. I do not write most of the code by hand. I run several Claude Code sessions, each with one responsibility. A development session builds the app in Swift. A marketing session reads the usage numbers and finds places to tell people about the app. A separate designer agent, which did not draw the screens, chooses between two or three prototype variants before any UI change is built. Read-only reviewer agents check finished work against the goals I wrote at the start. The part that made this work is turning every mistake into a check rather than a note. When an agent gets something wrong, we turn the lesson into a test, script, or guard that prevents the same bad step next time. For example, the post script reads the community rules again before every post and stops if they have changed. Today, the app lets me hold the margin so a pin drops beside the line. The pin opens a note that I can type or write with Apple Pencil. Review brings notes back days later, next to their lines. The app also includes dark page themes and a speed-reading guide. Listen, which reads the book aloud with on-device voices, is currently in testing. Step-by-step: 1. I wrote down the goals in plain language: installs, people opening a book, minutes read, and the number of days they return. 2. A development session builds each feature test-first and runs the iOS test suite on a simulator before every push. 3. Before any UI change, the agent draws two or three variants. A designer agent that did not draw them chooses one and explains why. 4. I send each build to TestFlight for a small group of testers. 5. A marketing session reads the PostHog numbers every two hours and tries a new channel whenever a round is flat. 6. I send feedback from posts back to the development session as to-do items. 7. I encode every mistake as a test, script, or guard so it does not happen twice. 8. I keep the irreversible steps for myself: App Store submissions, prices, accounts, and deploys wait for my approval. Helicon on the App Store: https://apps.apple.com/app/apple-store/id6811677202?pt=125973633&ct=rundown&mt=8 Built with help from AI coding tools.

I built Mailr, a newsletter that condenses the day's AI news into a 3-minute read for India's tech ecosystem. Almost all of it runs automatically, so I only step in for a few finishing touches. You can see it at mailr.tech. How the workflow runs: 1. An n8n cloud workflow reads RSS feeds from the major online publications in India. 2. It scores each story using a weighting based on the source and a set of predefined keywords. I keep those keywords in a Google Sheet so I can edit them anytime. 3. Claude, which powers the backend, picks the 4 best stories of the day: 1 global and 3 from India. 4. It adds weekly sections such as Read of the Week and Indian Founder of the Day. 5. The workflow builds the email in my predefined template. 6. It sends the email to Kit through an API call. The only manual steps I do are adding the subject line, editing the intro, and adding images. The result is a 3x weekly, AI-curated and human-edited newsletter that takes about 3 minutes to read.

I'm Wayne, founder of WazWorld, an independent music and content brand. My starting point is usually 1980s new wave, alternative, and synth-driven music: melodic bass, analog-style synths, guitars, and arrangements that leave room for the music. I use those influences to develop original WazWorld songs, not to reproduce existing recordings. This workflow is for artists who want AI to speed up experimentation while the creative decisions stay with them. 1. I define the emotion, instrumentation, structure, and vocal approach first. 2. I use ChatGPT (I call it Kai) to analyze arrangements and test directions against that brief. 3. For lyrics, I rewrite and refine the phrasing or provide my own verse and chorus ideas rather than accepting generated lyrics. 4. I turn the direction into musical versions in Suno and compare the results. 5. I use Suno Studio to work further on sections, arrangements, and regenerated parts. The first generation is rarely the final recording. 6. For PERFECT DAMAGE, I directed an album-cover concept contrasting a beautiful coastal setting with architectural destruction, then developed coordinated single artwork and promotional formats with AI assistance. 7. My WazWorld Command Center coordinates specialized AI help, including Kai, a Manager Agent, and YouTube and Streaming agents. Some of its capabilities are still in development. 8. I evaluate each version, request targeted changes, and approve the music, visuals, and release materials myself. The result is faster experimentation and coordination, but my musical taste, experience, and decisions shape the finished work.

When I create video content, I pull imagery from many different sources, so my editing folder often ends up with photos that may or may not work inside my editing program. For a handful of photos, converting them manually is fine. For larger projects with dozens of images, it eats into my time and focus. I wanted something simple, lightweight on compute power, that could batch convert photos. 1. I asked Claude to create an app that runs on my local machine and converts photos into formats I know will work in my video editor. 2. I asked for it to be able to batch convert photos. 3. Claude returned an app that worked exactly the way I needed. 4. I asked Claude to install it on my computer. It was installed and working within seconds. 5. I use the app to batch convert my photo folders before bringing them into the editor. There are plenty of traditional ways to do this, but with Claude I got a solution that fit my workflow perfectly, and large image batches no longer slow my editing down.

I built a live camera bubble that floats over my slides during Facebook Live presentations. Because Facebook Live does not let me switch between my camera and a shared screen, I wanted my face to stay visible while I presented. This is useful for anyone who streams presentations to a Facebook Group and wants viewers to see them speaking. Claude Code built the working app within about five minutes. I made one tweak to the camera bubble’s shape, and it was then a finished, usable product. When I’m ready to go live in the Facebook Group, I click the camera bubble app on my local desktop. It uses my laptop camera, and I can drag the bubble around the screen and choose the circle size that suits whatever I’m sharing. Before I go live, I select "share entire screen" in the Facebook Live settings. Viewers then see my slides or screen with my floating camera bubble, so they can see me speaking as I present. The result is a live stream that shows my slides and my face together, and it took about five minutes to build. Step-by-step: 1. I gave Claude Code the challenge of building a live camera bubble for Facebook Live presentations. 2. Claude Code built the working app within about five minutes. 3. I made one tweak to the shape of the camera bubble, creating a finished, usable product. 4. When I’m ready to go live in the Facebook Group, I click the camera bubble app on my local desktop and use my laptop camera. 5. I drag the bubble around the screen and choose the circle size that suits what I’m sharing. 6. In the Facebook Live settings, I select "share entire screen." 7. I present my slides or screen while viewers see my floating camera bubble and my face together.

I built a workflow for creating a living book that exists online and that I can add to, edit, and share whenever I like. I’m an occasional writer who publishes nonfiction essays about observations in life. I realized I could collect the essays into a book, but life doesn’t take an appropriate pause, so the book and the essays never really end. That raised the question: When should I publish it? I created a local Claude instance to access all the files on my laptop. Local is almost always better than a cloud instance, and you can ask Claude to enable remote control so you can access it from your phone as well. I used Opus 5.5 because I couldn’t be bothered experimenting with lower-level models to see whether they could do the task more cheaply. A friend who uses Claude professionally once told me to always use the highest model available and move down if I ran into usage limits. I’m on the monthly Pro plan. I gave Claude the locations of my existing writing on Substack and Medium.com. It downloaded all my essays and organized them into rough sections. I argued with it about the organization and approved the sections once it explained its logic. I then had Claude create a Ulysses folder for all my essays, organized into sections and chapters. I can use it to create a new essay, edit an old one, or reorganize and reorder the book, then tell Claude to update the online version. I could have had it scan the folder regularly and update the site automatically, but that seemed unnecessarily lazy. Claude created a section of a website I already owned where readers can access the living book: https://enwaken.com/read/ During the process, I also had Claude restructure and redesign my overall website several times. It’s amazing at that sort of task. I’m still amazed that I can say something like "I want blue and violet and black, but maximize the contrast between each of the colours" and it will actually pick colors that complement each other. I wish more website designers knew they could do this. Now I have a version of my book that is spectacularly easy to read online and that I can update whenever I like. It’s easier to navigate than an ePub on my Kindle and certainly easier to update. The whole process took two days, half of which was spent arguing about the organization of the chapters. Step-by-step: 1. I set up a local Claude instance with access to the writing files on my laptop and enabled remote control so I could access it from my phone. 2. I used Claude Opus 5.5 through the monthly Pro plan. 3. I gave Claude the locations of my existing essays on Substack and Medium.com and had it download them. 4. I reviewed Claude’s rough organization of the essays into sections, argued about its choices, and approved the structure once it explained its logic. 5. I had Claude create a Ulysses folder organized into sections and chapters so I could add, edit, and reorder essays. 6. I told Claude to update the online book when I changed the Ulysses folder. 7. I had Claude create the book as a section of my existing website and redesign the site as needed. 8. I now maintain a living online book that is easy to read, share, and update.

I design songs by giving different vocal parts different emotional jobs rather than writing one continuous lyric and deciding afterward who sings each section. I start with contrast. One voice might carry rhythm, detail, tension, or narrative through rap, while another opens the song emotionally through a melodic chorus. A sung section can create space after a dense verse, and a rap section can sharpen the story after a more atmospheric refrain. The contrast is functional as well as musical. Different voices can represent different perspectives, emotional registers, or levels of intimacy. The chorus can express the feeling that the verse struggles to name, while the verse can complicate what the chorus makes sound simple. A bridge can temporarily change the relationship between them. This is why songs that combine rap and fully sung passages can work: the parts are doing different jobs instead of simply stitching two styles together. The song “Airplanes” is useful as a structural inspiration because of its contrast between rhythmic narrative and a melodic, emotionally open refrain. The goal, however, is not imitation. It is to understand why that contrast works and build a new song around its own voices, themes, and emotional architecture. AI can help me develop lyrics, transitions, vocal roles, perspective shifts, and the points where the song needs to open up or contract. The result is a song designed not only around verses and choruses, but also around the relationship between different ways of speaking and singing. Step-by-step: 1. I identify the different vocal modes the song will use, such as rap, melodic singing, or a bridge. 2. I assign each vocal part a distinct emotional or narrative job, such as carrying rhythm, creating tension, opening emotionally, or introducing another perspective. 3. I use contrast to create movement: a sung section can follow a dense verse, while a rap section can sharpen the story after an atmospheric refrain. 4. I decide how the voices relate to one another, including what the chorus expresses, what the verse complicates, and whether the bridge changes their relationship. 5. I study the contrast between rhythmic narrative and melodic refrain in “Airplanes” as structural inspiration without imitating it. 6. I use AI to develop lyrics, transitions, vocal roles, perspective shifts, and the points where the song should open up or contract. 7. I shape the final song around the relationship between its different ways of speaking and singing, not only around its verses and choruses.

YouTube is one of the best free education platforms out there, but the problem is that it takes a ton of time to sit through long videos just to find the few ideas that actually matter. That's where Gemini has been really useful for me. Since it's built into Google, I can use it to quickly summarize a specific YouTube video, or even scan the last 5–10 videos from a creator to pull out the key takeaways. Instead of spending hours watching everything, I can quickly understand the main ideas, find the best nuggets, and decide what's worth digging into deeper. It's basically a shortcut for learning from long-form content without consuming every minute of it. Step-by-step: 1. I gave Gemini the URL of a specific YouTube video when I wanted a fast summary of one piece of content. 2. For a broader view, I asked it to scan the latest five to ten videos from the same creator. 3. I had it extract the main ideas and strongest takeaways from each video. 4. I compared the summaries to find recurring themes and the most useful nuggets. 5. I used that overview to decide which videos were worth watching in full.

Every Friday, I inspect random parts of my company the way a factory owner walks the floor: looking for errors, slow processes, and handoffs that shouldn’t exist. The inspection takes 30–60 minutes, but the preparation used to take longer—choosing what to check, finding the right links, and remembering what I flagged the previous week. I turned the entire preparation process into one scheduled Claude task. It runs before I wake up on Fridays, builds the full inspection report in Notion, verifies whether last week’s findings were resolved by checking Slack for evidence, and sends me the link by DM. I arrive to a finished briefing and focus only on judgment. You need Claude with scheduled tasks, plus Notion (or your company’s notes page) and Slack connected. If you use different tools, the prompt can be adapted; the structure is what matters. Step-by-step: 1. Create a page or database in Notion where the weekly reports will live. 2. In Claude, create a new scheduled task, set it to run early Friday morning in your time zone, and paste the prompt below. 3. Replace every bracketed section with your own details. 4. Customize the checklist and wildcard pool for your business. Mine is built for a media company; yours might inspect deployments, client deliverables, or a sales pipeline. 5. Run the task once immediately to identify configuration issues before relying on it on Friday. I use this prompt: ```text You are preparing [your name]’s weekly Digital Factory Inspection report. Context: [your name] runs [your company — one line on what it is and team size]. Every Friday they “walk the factory floor” digitally: inspecting parts of the company looking for errors, slow processes, unnecessary handoffs, and automation opportunities. Your job is to prepare the inspection report in advance so their 30-60 minutes is pure judgment, not gathering. You prepare; they inspect and decide. All reports live in [link to your Notion inspections database or page]. Do not create pages anywhere else. Steps: Read the most recent report. Collect: (a) any findings not clearly marked resolved, and (b) which wildcard areas were used in the last two reports. Create this week’s report as a new entry there, dated today, matching the existing format. Build the content in this order: A. “Follow-ups from last week”: every unresolved finding, each with its owner and a status check — search Slack public channels for evidence it was addressed and mark it “looks resolved”, “no activity found”, or “unclear”. If none, write “No open follow-ups.” B. The standard checklist — include ALL of these every week. Under each: random samples with direct links, 3-5 recent data points you can actually reach, and 2-3 sharp inspection questions: What is slow here? Which handoffs could disappear? What should be automated? What would make this 10 percent better this month? Where something sits behind a login you don’t have, do not attempt access — link it and list what to look for. Randomize sample picks genuinely, and never reuse a specific sample from the previous two reports. [Your standard areas — mine: 3 random published pieces of content, 3 random newsletters, 3 random social posts, ad performance, growth dashboards and funnels, product dev work, live events/workshops, community activity, the team’s weekly reports] C. “Wildcards this week”: pick exactly 2 at random from this pool, never repeating either of the last two weeks’ picks: [Your wildcard pool — mine: random customer support conversations, the public sign-up flow walked as a new user, one specific finance item to verify, one email automation sequence, ads on a secondary channel, one random SOP compared against how the team actually works now, one recent client/sponsor deliverable] D. “Notes \u0026 findings”: empty except the line “[Your name] fills this in during inspection — tag each finding with an owner and Open/Resolved.” E. “Wildcards used”: list the 2 wildcard names, for future rotation. Send [your name] a Slack DM (member ID [find yours in your Slack profile menu]) with the report link, the count of open follow-ups, and the 2 wildcards. Nothing else. Hard rules: this report contains candid internal assessments — the DM goes ONLY to [your name], never to any channel, and you never message anyone else. Read-only everywhere except the one report you create and the single DM. Do not reply to emails, do not post, do not modify existing pages. If Notion is unreachable, send the full report as the DM. If Slack is unreachable, still create the report. If both fail, do nothing. ``` The follow-up section is the whole point. I keep the workflow read-only: the agent gathers and drafts, but it never messages my team or touches live systems. Any feedback after the inspection comes from me, in my own words. Randomness is a feature, not laziness.

I built an AI-assisted Lightroom Classic workflow that lets photographers create branded marketing images without leaving Lightroom. The problem I wanted to solve was simple: photographers often finish editing an image, export it, open another design tool to add a logo, watermark, text, or promotional graphic, and then export it again. I wanted that entire branding step to happen inside Lightroom. Using AI-assisted development, I built Brandstamp Pro, a Lightroom Classic plugin that lets me add branding, preview the result, save reusable presets, and export the finished image from the same workflow. The result is a much simpler process: edit photo → add branding → preview → export Instead of: edit photo → export → open another design app → add branding → export again I originally built it for my own real-estate photography workflow, but the same idea works for photographers who need branded social images, booking graphics, promotional images, watermarks, or client-ready marketing photos. The biggest benefit is not that AI adds the branding automatically. It helped me build a tool that removes a repetitive step from an existing photography workflow. Step-by-step: 1. I selected an edited photo in Lightroom Classic. 2. I opened the Brandstamp panel. 3. I added a logo, watermark, text, or other branding. 4. I adjusted the size, position, opacity, color, and placement. 5. I previewed the branded result before exporting. 6. I saved reusable presets for branding I use repeatedly. 7. I exported the finished branded image directly from the same Lightroom workflow.

I built Show Hole to solve my family’s classic streaming problem: we spend too much time deciding what to watch, and the answer changes depending on who is actually on the couch. We each have different tastes, but the more interesting problem is that our tastes overlap differently in different combinations. I watch one kind of thing with my spouse, my spouse watches something different with our kid, and my kid and I have our own lane too. Most recommendation tools flatten that into one account profile, one watch history, or broad genre buckets, so they miss the real context of a household. Show Hole treats people and viewing contexts as first-class citizens. It recommends titles “in the vein of” something we liked, filters recommendations to the streaming services we actually subscribe to, avoids titles that the people present have already seen or vetoed, and explains why a recommendation fits tonight. Instead of relying mainly on genres such as comedy, drama, or sci-fi, Show Hole looks at more human taste signals: pacing, world building, humor, emotional weight, complexity, tone, and similar dimensions. It also learns from what we actually do after a recommendation: what we watch, skip, save for later, love, and drop. The result is a personal household recommender that understands “who is watching tonight?” as part of the question, instead of pretending one streaming profile can represent everyone. I designed the app using Claude design, then used those designs with Claude Code to build it. Step-by-step: 1. I identified the household viewing problem and accounted for the different combinations of people who might be watching together. 2. I designed Show Hole around people and viewing contexts instead of treating the household as one account profile, watch history, or set of broad genre preferences. 3. I had it recommend titles “in the vein of” something we liked, filter them to the streaming services we subscribe to, exclude titles already seen or vetoed by the people present, and explain why each recommendation fits that night. 4. I used taste signals such as pacing, world building, humor, emotional weight, complexity, tone, and similar dimensions instead of relying mainly on genres. 5. I made the recommender learn from what we watch, skip, save for later, love, and drop after receiving a recommendation. 6. I designed the app using Claude design and used those designs with Claude Code to build it.

I write murder mysteries, and like every author, I need an editor to help carry a story from the first raw idea to a finished, publishable script. The trouble is that good editors are rare. The insightful, reliable ones are expensive, and they are often slow. My first murder mystery took the better part of six months to edit. Even after all that time, I still found typos and clumsy sentences that should have been caught during the line edit and proofreading. That is not a criticism of editors; it is the reality of a manual, human-paced process that does not scale to the way I want to work. I do not use AI to write my stories. The voice, plot, and subtext are mine. But line editing and proofreading are different jobs, and that is where I started using AI. Basic paid ChatGPT got me part of the way, but it was not enough. In February, I switched to Claude, and it was a quantum leap: sharper suggestions, better reasoning, and output I could actually trust. I wanted more than a clever assistant. I wanted a process. Rather than wait for the perfect human editor—affordable, brilliant, and available precisely when I needed them—I built my own. My Claude Editor-in-Chief contains my entire editing workflow, along with a few innovations of my own. At its heart is a framework I developed: the Tension Coefficient (TC), ReaderGrip, and StoryDrift. These three lenses show whether a scene is pulling its weight, whether it keeps its grip on the reader, and whether the story is quietly wandering off course. Everything feeds into a dashboard, so I can see at a glance what is working and what needs fixing. The result is a workflow that turns editing from a six-month slog into something that takes a fraction of the time and, more importantly, produces a cleaner, tighter manuscript. I stopped waiting for help and built the editor I always wished I could hire. Step-by-step: 1. I kept the creative work—my story’s voice, plot, and subtext—in my own hands and used AI specifically for line editing and proofreading. 2. I started with basic paid ChatGPT, then switched to Claude in February after finding that it provided sharper suggestions, better reasoning, and output I could trust. 3. I built a Claude Editor-in-Chief around my full editing workflow instead of relying on Claude as a general-purpose assistant. 4. I added my Tension Coefficient (TC), ReaderGrip, and StoryDrift frameworks to evaluate whether scenes are effective, maintain reader engagement, and stay on course. 5. I connected those evaluations to a dashboard that shows what is working and what needs fixing. 6. I use the workflow to reduce editing time and produce a cleaner, tighter manuscript.

I was charged with leading my book club’s discussion of *Shrines of Gaiety* by Kate Atkinson. The book has many well-developed characters and murder-mystery plotlines, so I decided to create a “Who Is This Character?” game using simple supplies from my home office: envelopes, printed clues, a stapler, and markers. I asked ChatGPT to help design the game. It came up with eight potential characters, then selected the five most important so the game would still work if some book club members were absent. For each character, it created five clues and a simple rules sheet. Characters were assigned numbers and read in order. Players heard each clue without asking questions, but they could guess after every clue. Many characters were identified, and the game led to a meaningful discussion of each character’s motivations. ChatGPT also provided a discussion question for each character, which made the activity easy for me to run. As a bonus, ChatGPT found a 1920s cocktail recipe for the Mother’s Milk drink mentioned on page 336. It included appropriate warnings, nonalcoholic options, and a sample size suitable for an afternoon book club for senior women. Step-by-step: 1. I chose a “Who Is This Character?” game for my discussion of *Shrines of Gaiety* because of its many characters and murder-mystery plotlines. 2. I gathered envelopes, printed clues, a stapler, and markers from my home office. 3. I asked ChatGPT to suggest eight potential characters and select the five most important in case some members were absent. 4. I asked ChatGPT to create five clues for each selected character, along with rules explaining that the characters would be read in numerical order, with guesses allowed after each clue and no questions during the clues. 5. I used the clues and rules to run the game during the book club discussion. 6. I used ChatGPT’s character-motivation questions to guide the discussion after the game. 7. I also used ChatGPT’s 1920s Mother’s Milk cocktail recipe, including its warnings and nonalcoholic options, for the afternoon gathering.

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.

I built a daily AI story-scouting workflow that finds potentially viral stories for Instagram Reels, YouTube Shorts, and TikTok without recycling topics we’ve already covered. First, the workflow reviewed Rowan’s public short-form archive once to create a coverage map of past topics and editorial taste. It uses that map as a filter, helping distinguish a genuinely new angle from another version of the same AI launch, robot demo, or research story. Every morning, it scans priority sources, including AI and technology coverage from major newspapers and tech blogs, The Rundown newsletters, company announcements, research papers, and public updates from major AI and robotics companies. The workflow is not limited to same-day news. It also looks back over the past one to six weeks for stories that have not been extensively covered in the media. Each potential story is checked for four things: a clear visual hook, a technical idea that can be explained in 45–90 seconds, broad audience interest, and meaningful novelty compared with Rowan’s past coverage and the previous week’s recommendations. It keeps every story that clears the bar rather than forcing a fixed number. The final brief is ranked by strength and sent as one compact Slack DM at 10 AM each day. Step-by-step: 1. The workflow reviews Rowan’s public short-form archive once and builds a map of past topics and editorial taste. 2. Each morning, it scans priority sources, including major newspapers, tech blogs, The Rundown newsletters, company announcements, research papers, and public updates from major AI and robotics companies. 3. It searches both same-day news and stories from the previous one to six weeks that have not been extensively covered in the media. 4. It filters out topics that substantially repeat Rowan’s past coverage or the previous week’s recommendations, while identifying genuinely new angles. 5. It evaluates each potential story for a clear visual hook, a technical idea explainable in 45–90 seconds, broad audience interest, and meaningful novelty. 6. It keeps every story that meets those criteria instead of forcing a fixed number of recommendations. 7. It ranks the final brief by strength and sends it as one compact Slack DM at 10 AM each day.

I wanted lyrics for original music that did not rely on random invented syllables, so I developed a fictional “crystal language” with its own sound, atmosphere, recurring words, and internal logic. The starting point was musical rather than academic. I considered which sounds belonged in this world, which consonants felt sharp, soft, ancient, luminous, or fragile, which vowels sang well, and which word shapes fit the music’s rhythm and emotional tone. As I repeated sounds, they began to acquire repeated meanings. Words started to relate to one another, and certain phonetic patterns became associated with ideas, emotions, or imagery. The language gradually developed enough consistency that listeners could feel it belonged to one world, even without understanding it. That internal structure keeps the invented lyrics from sounding like decorative nonsense. The words begin to carry memory: a phrase can reappear later and mean something, and a sound used in one song can echo another. The fictional language becomes part of the music’s identity. The aim is not necessarily to construct a complete language with full grammar. It is to create enough recurring logic that the lyrics feel intentional, recognizable, and alive—not gibberish with nice vowels, but a tiny musical culture. Step-by-step: 1. I started with the music and defined the kind of world its language needed to evoke. 2. I selected sounds, consonants, vowels, and word shapes based on their emotional qualities, singability, rhythm, and atmosphere. 3. I repeated sounds until some began to acquire recurring meanings. 4. I connected related words and associated phonetic patterns with ideas, emotions, or imagery. 5. I reused phrases and sounds across songs so they could carry memory and create echoes between pieces. 6. I developed only as much structure as necessary for the lyrics to feel intentional, recognizable, and alive.

I built a custom web app that uses chance to combine random images and texts into new, unplanned pairings. It recreates a Dadaist technique I use often when making photobooks, which I previously did manually with physical prints. I used Replit to create a digital version of the game. It was easy to connect the app to Project Gutenberg for random texts and the Library of Congress photography archive for images. More importantly, I made it possible for users to work with their own image and text archives. So far, it has produced many new and interesting results, and other artists have used it too. Step-by-step: 1. I identified the manual process I use when making photobooks: combining printed images and texts by chance. 2. I used Replit to build a digital version of this process as a web app. 3. I connected the app to Project Gutenberg to pull random texts. 4. I connected it to the Library of Congress photography archive to pull images. 5. I allowed users to work with their own image and text archives. 6. I used the app to create new pairings and shared it with other artists, who used it as well.

Sometimes AI produces an image you love without your having asked for that exact result. The colours work, the texture feels right, and the atmosphere is exactly what you wanted but could not quite describe. Before moving on, use that image to develop a reusable prompt. Step-by-step: 1. Show the image you are happy with to an AI tool and ask: “How would you describe the visual style of this image? Pay attention to colour, texture, lighting, shapes, composition, detail and atmosphere. Separate the style from the specific subject.” This helps turn “I love this” into something you can name. You are asking for a description of the visible result, not the exact process that originally produced it. 2. Read the description and compare it with the image. Check whether the AI noticed the qualities you love or focused on something incidental. Clarify ambiguous terms—for example, whether “soft” means gentle lighting, blurred edges, or muted colours. Correct the description where needed. You might write: “The uneven shapes and paper texture matter. The pastel palette does not. I want to keep the slightly strange atmosphere without making everything cute.” Your response turns a general description into a record of your taste. 3. Ask: “Write a reusable image prompt based on this description. Keep the visual qualities we identified, but make the subject replaceable. Distinguish essential features from optional ones.” The prompt should describe what makes the result useful to you rather than simply retell what is pictured. A woodland scene might contain the style you love, but that does not mean every future image needs a forest. 4. Apply the prompt to another source image or a different subject. This is the useful test: can the prompt carry the qualities you wanted into new material? A second version of almost the same scene may hide weaknesses in the prompt. A different subject makes them easier to see. 5. Compare the new result against your goal. Ask yourself: - Does this new result have the qualities I loved? - Does the style suit the new subject? - Did the prompt preserve what mattered in the new source? - Did it reproduce incidental details from the first image? - Would I actually use this result? A reusable prompt should transfer the visual direction while giving the new image room to remain itself. 6. If the result misses the mark, identify the specific difference and refine the prompt. For example: - Too smooth? Name the texture. - Too cute? Describe the shapes and expressions more precisely. - Too realistic? Clarify the degree of stylization. - Too similar to the first scene? Remove subject-specific details. Test again when those changes matter. Save the prompt alongside the original result and a successful test image. Note the tool or model used, since the same wording can behave differently elsewhere. One successful test is encouraging, but several varied tests give you a clearer sense of where the prompt works. An unexpected result can help you discover a preference you did not yet have words for. Describe it, decide what matters, turn those choices into instructions, and test whether they travel. You do not need to know the perfect prompt before making something you love. Sometimes the image comes first, and the language follows.

I’m sharing “The Architects of Reality,” a short film created as part of an experiment with a multi-agent AI workflow for long-form content creation. Off-the-shelf AI video platforms are brilliant for short clips, but as the duration increases, the challenges compound: character inconsistency, narrative drift, visual discontinuity, and expensive iterations when the output doesn’t match the creative vision. Instead of asking one AI to make a film, I created an AI film crew. Specialised agents and sub-agents take on roles including Director, DOP, Cameraman, VFX Supervisor, Sound Engineer, VO Artist, and Audio Mixer to support the filmmaking process. Creative review and approval are built into every stage, so individual elements can be regenerated before expensive final rendering. This helps optimise tokens, budget, and creative control. It’s been a fun journey building these agents—and even more fascinating to watch the output improve in capability and efficiency as they learn every day. Step-by-step: 1. I set up a multi-agent AI workflow for long-form content creation. 2. I assigned specialised filmmaking roles to agents and sub-agents, including Director, DOP, Cameraman, VFX Supervisor, Sound Engineer, VO Artist, and Audio Mixer. 3. I built creative review and approval into every stage of the process. 4. I regenerate individual elements when they do not match the creative vision, before moving to expensive final rendering. 5. I use the workflow to optimise tokens, budget, and creative control while producing the short film “The Architects of Reality.” 6. I observe how the output’s capabilities and efficiencies improve as the agents learn every day.

I built a custom news agent that skips the Google News and Apple News walled gardens. Eight prompts turn Claude into a personal news editor that reads my trusted RSS feeds, scores every story with a decision model, and delivers a clean daily page for about a dime a month. Each week, pulling two or three good stories for my newsletter digest meant searching multiple sites by hand—hours of clicking and scrolling for a handful of usable links. RSS feeds already deliver that content; the missing piece was a judgment layer that could separate worthwhile stories from noise without the cost or latency of running everything through a full LLM. I used Claude Cowork, Jev from TypeSafe AI, Vercel AI Gateway, RSS feeds, Python, and SQLite. Jev is a decision model rather than a chatbot: it returns a probability and confidence score instead of prose, does not hallucinate facts, and scores a story in a fraction of a second. That makes an automated daily judgment call inexpensive enough to run continuously. Step-by-step: 1. I set up a Claude project to hold the scripts, taste guide, database, and page. 2. I defined the goal and sections, then had Claude interview me to create a short “taste guide” describing what counts as a good story. 3. I found and live-tested the RSS feed for each trusted source instead of guessing feed URLs. 4. I fetched all working feeds into a deduplicated SQLite database and logged failures. 5. I used Jev through Vercel AI Gateway to score every story: first filtering ads and promotions, then ranking stories by section against my taste guide. 6. I selected the winners for each section, with Jev identifying near-duplicate stories so they would not appear twice. 7. I generated one-line summaries and fact-checked them against the source so nothing was invented. 8. I rendered a simple HTML page and scheduled the entire workflow to run every morning. A few details matter. I used Cowork rather than a plain chat because several steps require Claude to work with files, run code, and access the network. I also created a Vercel account and AI Gateway API key manually before the scoring step. Finally, I saved everything to the Claude project instead of a local folder, which allows the morning run to happen in the cloud on its own schedule. Scoring costs roughly $0.10 per month with Jev, compared with a few dollars for a full LLM doing the same job. The workflow turns a two-hour weekly slog into a page that is ready every morning, with each link going directly to the original publisher rather than a Google or Apple aggregator. Full build walkthrough: onabetternote.substack.com/p/build-your-own-news-agent-with-claude — the Substack post includes the exact eight prompts to copy and paste, plus more detail on why a model like Jev matters for cost containment as agents become routine.