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.

Your calendar knows when each meeting happened. Your watch knows what your heart was doing. Put both in one chat and see which meetings get to you. Why it's interesting Most of us can name the meeting that drains us, but few of us have checked. Sitting on a call, your heart rate should stay near your quiet daytime level. When it climbs anyway, your wearable has probably logged it. Disclosure: I built freddy, the connector that feeds my wearable data to my AI. Setup 1. Connect your wearable at freddy.coach. For a per-meeting view, use a source that records heart rate through the day: Apple Health, Health Connect or Oura. Garmin gives daily heart rate plus a stress score every few minutes. 2. Add freddy in Claude (Customize, Connectors) or ChatGPT (the freddy plugin, then Connect). 3. Connect your calendar in the same place. Google Calendar needs a paid plan in both. The prompts Prompt 1: "Using freddy and my calendar, list last week's meetings. For each, compare my heart rate during the meeting with my baseline: my median heart rate in quiet, meeting-free working hours that week. Skip meetings where my steps show I was walking. Rank the top 5, use my local time and name the source for every number." Prompt 2: "Add stress where my device logs it through the day. Compare my HRV the night after my heaviest meeting day with my other nights. Never mix HRV from different devices." Prompt 3: "If you only have daily numbers, don't estimate per meeting. Compare heavy-meeting days (4+ hours) with light days on heart rate, resting heart rate, stress and any blood pressure cuff readings, and tell me how many readings each group has." Blood pressure only works with cuff readings, like a Withings BPM. Those are spot readings, so you compare days, not meetings. Example output, illustrative numbers Baseline: 66 bpm (Oura, 5 minute readings) 1. Tue 14:00, Budget review (60 min): avg 82 bpm, +16, peak 94 2. Thu 09:30, Investor update (45 min): avg 79 bpm, +13 3. Mon 11:00, Hiring debrief (30 min): avg 75 bpm, +9 4. Fri 10:00, Standup (15 min): avg 69 bpm, +3 5. Wed 16:00, Design review (45 min): avg 68 bpm, +2 Skipped: Wed 12:00 walking 1:1 (2,300 steps). HRV after Tuesday: 39 ms vs 47 ms on other nights. What to do with it Check what your top two share (time of day, people, topic), move or shorten one, and rerun the prompt next week. Not medical advice, just a closer look at your own data.

I built this because modern camera manuals are packed with useful information but hard to use when you need an answer quickly. A professional camera can have hundreds of pages covering autofocus, custom buttons, metering, flash, bracketing, and shooting modes. Most of us don't memorize all of it, and during a shoot, when the light is changing or the client is waiting, I didn't want to search through a 300-to-500-page PDF. So, I turned my camera manual into an AI Field Assistant. It works with almost any camera that has a PDF manual, for: -hobbyists, -parents with a new mirrorless camera, -travelers, -people learning manual controls, -anyone switching brands or upgrading bodies, -people who bought a “real” camera and are intimidated by the manual. You need a Claude or ChatGPT account, the mobile app, a Project, your camera manual PDF, and a small Markdown instruction file that tells the AI how to use the manual. The setup is: 1. Create a new Project. 2. Add your camera manual PDF and the instruction Markdown file. I also added optional Markdown reference files for things like lenses, field notes, and troubleshooting, but the core setup works without them. Once the Project is set up, use the mobile app and ask short practical questions like: "flash not firing" “moving outdoors” “flash not firing” “low light checklist” “bracketing off” “which lens should I use?” The Project already knows which camera you use and treats the manual as the source of truth, so you don't have to repeat the model or write long prompts. The best use is before a shoot. Ask it to create quick notes for situations like indoor, outdoor, low-light, action, portrait, flash, or sunset, then keep those notes on your phone for the field. The goal isn't to let AI operate the camera. It's to help you understand your camera faster, prepare before the pressure starts, and avoid missing a shot because the answer was buried in the manual. If anyone wants to try this without building the instruction files from scratch, I already have the Markdown files I use for the assistant, including the camera instructions and optional lens/reference files. I’m happy to share a folder link with anyone who wants to copy the setup and adapt it to their own camera. The only thing you would still need to provide is your own camera manual PDF and any camera/lens-specific information you want the assistant to know.

I used Astra to redesign my personal wardrobe. I want to dress better, but my absolute worst nightmare is having a closet full of clothes that creates more clutter in my brain. I already have enough to think about, so I built an app that decides what I should wear based on the season and local weather using GPT-6 Astra. I gave it a few full-body photos, my height, weight, sizes, and niche details such as having broad shoulders and needing to tailor my waist. I also shared the colors I like, added a master prompt, and asked it to build a site. The results were incredible. I'm the model in every photo, and Astra's virtual try-on is genuinely impressive. If I can't find a piece online, I update the model and regenerate the pictures. Step-by-step: 1. I opened ChatGPT desktop with GPT-6 Astra and Codex/Sites, then turned on Computer Use and image generation. 2. I started a new chat and uploaded four to eight full-body photos, one clear face photo, and closet photos when available. 3. I pasted the prompt below, filled in my name, city, and sizes, and let it work for one to two hours. 4. I sent a couple of correction passes instead of rebuilding the whole system. I removed things I would never wear and added things I actually wear. PROMPT: GOAL Build a working website called [YOUR NAME]'s Wardrobe. It blends two things: 1) A closed uniform system of exactly 30 looks 2) A personalized shopping portal where I am the model in every photo, Aritzia/Uniqlo catalog quality (seamless studio backdrop, full-body try-on, product-card grid) SITE NAME [YOUR NAME]'s Wardrobe THE ONLY INVENTORY - 7 summer outfits - 7 fall outfits - 7 winter outfits - 7 spring outfits - 1 gym outfit - 1 lounge outfit = 30 looks. Nothing else. Each look is complete: top + bottom or one-piece + shoes + at most 2 extras. Reuse pieces across the 7 looks in a season. Cap unique garments at 35–50 including shoes and outerwear. Throw everything else out. WHO I AM - Name: - Lives: [city] - Height: - Weight: - Sizes (top / bottom / shoe): - Body notes: - Work dress code: - Weekend life: - Style in 5 words: - Colors that work / colors I refuse: - Budget for gap-filling buys: - Hard constraints: Attached photos are the identity lock. Reproduce my real face AND real body in every try-on. Do not slim, lengthen, or beautify me. LIVE WEATHER (required, not a mock) On every page load, fetch live weather for [CITY] from Open-Meteo with no API key. Use the correct lat/long and timezone. Show on the homepage: - “Today in [CITY]” - apparent temperature, condition, rain yes/no - ONE recommended look from the 30 - why that look won - 1 weather swap (if rain starts / if it drops 5°C) Selection logic: - apparent temp ≥ 20°C and dry → Summer pool - 15–19°C dry → Spring pool Mar–May, Fall pool Sep–Nov, otherwise the closer season - 8–14°C → Fall pool, prefer the look that already includes a mid-layer - ≤ 7°C → Winter pool - rain now or daily precipitation ≥ 1mm → jacket + closed shoes, no white sneakers or silk - wind ≥ 25 km/h → prefer a layer - gym / lounge days use those uniforms, add a layer only if ≤ 10°C Never invent an outfit outside the 30. SITE STRUCTURE - Home: today + try-on + wear-this checklist - Summer / Fall / Winter / Spring: 7 look cards each, me wearing the full look - Gym / Lounge - Pieces: every unique garment on me, marked OWNED or BUY - Purge: sell / donate / trash for anything not in the system - Rotation: 4-week calendar per season. Weather can override, but it still has to be one of the 7 (or gym/lounge) VISUAL BAR Premium catalog photography. Gray/white seamless, even light, full body. Do not clone another brand’s logo. This is [YOUR NAME]'s Wardrobe. HOW TO BUILD Step-by-step: 1. Build the 30 looks from my photos, stats, climate, and closet photos. Use owned pieces first. 2. Generate consistent try-ons of me for every look and every piece. 3. Build a real clickable site. Hook live weather. Do not fake it. 4. If an image breaks my face or body, regenerate it before shipping. 5. No payments. Personal wardrobe OS only. OUTPUT Live site, the 30 looks, piece list (owned vs buy), ranked shopping list, purge list, weather mapping, and what you inferred vs what came from my photos. Start now. Make the call if a detail is missing. Only ask if the photos are unusable.

I built this webapp for a friend who is building a house. It lets you see the finished version of every room in the planned home before anything is built. I described the idea to Claude Cowork, had a short back-and-forth and answered its questions, and it built the app in four stages. 1. Upload one or more floor plans. You can add as many as you need. 2. Select a room from the floor plan. The app shows it in several 3D views that you can rotate. 3. Ask for the room the way you want it when completed. For example: "Show me with a dark colored wood floor with blue walls" 4. Make changes and ask again, such as light colored wood floors. 5. Ask the app to add furniture so you can see how the room will look when finished. 6. Save multiple designs for each room, and export any image as a PNG. The whole build took less than an hour from start to finish. I can share the finished prompt if anyone wants to build something similar.

Part 2 of my workflow for taking an AI-built prototype off the vibe-coding platform that created it. I wrote it so I could build, run, and recover the app without reopening that platform. It covers AI app-building platforms only, and I work from what the application actually uses, since some apps need a backend migration and others need only configuration changes. 1. Map every dependency before disconnecting anything. I start with the repository, then check where users sign in, where records and files live, and what sends email, runs scheduled work, or handles payments. For each dependency I decide to keep, move, replace, or retire it, and I record where credentials are managed, not their secret values. 2. Preserve the working version and choose a release candidate. I record the accepted commit, build, and configuration, and keep a recovery copy the builder cannot change or delete. I finish or stop builder edits, confirm what reached the repository, and name an owner for each release decision. 3. Rehearse the destination without activating production. I build the candidate in an isolated environment with test data, and I check whether connecting a repository or merging triggers a deploy. Then I exercise the app on the destination before moving anyone. 4. Move only what needs to move. If the backend stays, I verify access and compatibility. Where needed, I plan pauses for writes, jobs, and incoming events. I check identities, files, and permissions separately. 5. Release the tested version and verify real behavior. I confirm the candidate and recovery plan, switch traffic through the rehearsed path, then test the production address: refresh pages, sign in, create and read back a controlled record, and confirm unauthorized users are blocked. 6. Plan recovery for new activity. Restoring old code does not undo new emails, payments, or database writes, so before release I define when rollback is safe and when I must reconcile instead. 7. Retire old connections and update the rules. After verification and the recovery window, I remove obsolete sync, credentials, and jobs, check shared integrations, confirm billing before canceling, and update the instructions for the next change. The goal is an app I can build, run, and recover from accounts I control, with any remaining platform dependency recorded honestly. The full Platform Detachment Runbook and checklists are at https://github.com/wildeyeai/ai-builder-playbook Part 1 is here: https://app.therundown.ai/community/posts/f1c34207-edc7-4b42-9252-3609d5edbfb7

I run my Home Assistant smart home with Claude connected through MCP. Claude builds and troubleshoots my automations and emails me a daily house status report. This works well for anyone who wants local control and fewer gadgets tied to someone else's cloud. 1. I created a dedicated Claude Project for the house and gave it this system prompt: "You are the Lead Systems Architect for my Home Assistant home. Prioritize local control, privacy, and reliability. Verify current firmware and integration status by search; don't trust old training data. Enforce four rules: (1) every entity is named domain.location_device_function; (2) automations check the house mode (Home, Night, Vacation) before acting; (3) automations decide when, scripts handle how, and anything over two steps becomes a script; (4) priority order is safety, then manual override, then presence, then schedule. Give complete, copy-paste-ready YAML. Be blunt when a product or hack is unreliable." 2. I load a living setup doc (hardware, integrations, what's been tried, lessons learned) plus Claude's memory, so each session starts where the last one ended. 3. I connect Claude to Home Assistant through MCP, using the ha-mcp server as a custom connector via a Home Assistant Cloud (Nabu Casa) webhook URL. Claude reads live device states, history, and existing automations instead of guessing device names. 4. Home Assistant's MCP security policies require my approval before Claude changes or deletes existing automations or configuration. 5. I describe what I want in plain English, such as "warn before the garage auto-closes." Claude checks the live system, researches current hardware and integration status, writes the automation, and explains what changed and why. I approve and test it. 6. A daily scheduled Claude task checks the house each morning and emails a status report covering systems down, automations, energy and water use, and backup health. If anything is red, my phone gets an alert. Result: an audit cut my automations down to the ones that run unattended, hardware troubleshooting is faster, and I no longer buy gadgets that depend on someone else's cloud.

This is my workflow for ESG environmental management and sustainability development. It combines a prompt I saved in Claude, a setup with two agents, Python, and a film craft element. I am sharing it so others working on sustainability development or ESG management can see how the pieces fit together and adapt them to their own work. The steps, in the order I used them: 1. Start from the Claude prompt I saved for this work. 2. Set up the two agents. 3. Run the Python part of the process. 4. Apply the film craft step. My notes are shorthand, so the detailed settings for each step are not written out here. I will fill in the specifics once I have reviewed them. What it saves: I built this workflow to save me five days of work.

I used Claude to help me create my nonprofit's website, nomorecopays.org, in a day and a half. It walked me through the full process of setting up a nonprofit, helped with my legal paperwork, and guided me to the other tools I would need to run and grow the organization. This is for founders who are starting a nonprofit and want one place to plan the steps. 1. I asked Claude to walk me through the entire process of creating a nonprofit. 2. I had Claude create my website. 3. I had Claude help me edit my mission statement and review my attorney's drafts of the bylaws and other legal documents before I submitted them to incorporate. 4. I asked Claude to guide me on the other companies I would need to function and grow, including Namecheap, Google for Nonprofits, Google Workspace, Substack, and Zeffy. 5. I had Claude design my business cards so they share the look of my website. 6. I had Claude review the links and references for my Substack articles. Result: my nonprofit's website was created in a day and a half, with Claude's help across the legal, business card, and newsletter steps.

Ask one AI a hard question and you get a confident answer. I wanted a careful one, so I built a panel. Models from OpenAI, Anthropic, Google, xAI and DeepSeek research the same question, argue it out over several rounds, and check each other's sources and sums. A sixth model, Kimi, takes no side and writes the record. I use it where one confident answer is a risk, like checking a scary AI headline against the public record or stress-testing a plan before anyone spends money on it. They are allowed to make their own code changes, so they have the ability to evolve. 1. I write a brief: the question, the sources to read first, and the shape of answer I want. 2. Each model searches with its own company's search engine, so they don't all find the same five links. 3. Each writes a private first answer without seeing the others, so nobody anchors on the first confident voice. 4. Open rounds: they challenge each other by name, and a second model checks every sum. A majority can close the debate; one holdout can delay it twice. 5. Kimi records what they agree on. Disagreements go in their own section, never in the conclusion. Software then opens every link and flags any that fail or never came from the research. 6. Each model gets one objection to the record, appended word for word, and a plain-English summary goes on top. 7. They propose new rules for themselves. I approve or reject each generation and rate whether the next debates got better. A debate costs a few US dollars and about half an hour, and every one is published, mistakes included: https://quietlyincharge.ai/?utm_source=rundown&utm_campaign=workflow-hub

I run a photography business and built a three-layer AI workflow to help with daily operations, business improvement, and watching for outside changes that might affect us. It's for small business owners who don't want to monitor every source or handle every issue themselves. The layers are an Operations Core (dashboard, estimates, schedules, reminders, project records, attribution, and other business state), a Work orchestrator with specialist AI agents, and a signal and triage system that watches platform alerts, vendor updates, local-search changes, newsletters, calendars, and marketing sources. Here is how a signal moves through it: 1. The triage layer picks up a signal from one of the sources it watches. 2. Work decides whether the signal actually matters and routes it to the right specialist. 3. The specialist reviews it. I use separate specialists for WordPress, Google Business Profile and local search, marketing and STR signals, AI systems, research, and technical implementation. The WordPress and Google Business Profile specialists are also connected directly to those systems through MCP/API connectors, so they can compare the incoming signal against the current state of the actual site or profile before deciding whether it is relevant or whether any action is needed. 4. If the issue needs deeper evidence, the research specialist investigates before anything moves forward. 5. Work reconciles the findings into a recommendation. 6. I approve or decline the recommendation. The system brings me in only when a real decision is needed. 7. The change is implemented. 8. The Operations Core is updated with the new business state. The persistent Business Desk files hold current priorities, rules, operating guidance, and the source of truth for business state, so each step works from the same context. The main benefit for me is that I don't have to personally track every source or jump into every issue.

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.

I'm a psychotherapist in New Zealand. My handouts were static and needed regular updating, so I wanted simple, slightly interactive websites that clients could engage with, without anything massive. I have no coding experience beyond programming a Commodore 64 in BASIC, so I asked Claude to build them. The sites needed to be static, and any data a client enters needed to stay private. 1. I gave Claude a simple design prompt for each tool, starting with the sites I needed. 2. First was an IFS (internal family systems) site, laid out as a house, where a client can map out their internal world and connect the key elements to understand the whole: https://ifs.padma.nz 3. Next was a second house offering a walk through basic tools for emotional regulation. It has no data entry, but includes downloadable information: https://kind.padma.nz 4. Then came a life narrative site using leaves on a tree. Events are logged on a branch with a common theme (for example, school), and photos and music relevant to a life event can be attached: https://leaves.padma.nz 5. Finally, because I use Jung's Active Imagination in my work as outlined by Robert Johnson, I built a site that gives instructions and maps out a pathway for this approach: https://clearing.padma.nz What I end up with is four simple, static sites that replace my out-of-date handouts, with the aim of keeping any client-entered data private.

I had a ChatGPT personalisation setup that worked well until product changes made it less reliable. I kept re-explaining how I work and what good alignment feels like, so I rebuilt it as a plugin. I think of it as a backpack ChatGPT carries: a skill is the operating guide, reference files are the notes and maps, and connected tools are the gear. The plugin loads personal context and collaboration preferences, not a persona. How it runs: 1. In normal mode, the plugin quietly loads my current alignment and context bundle, so ordinary chats stay ordinary. 2. I trigger it with words I already use when talking to ChatGPT. Nicknames like "Goldfish," "Fish," "Blub," or "Blubsie" act as recognition signals, so I don't have to type setup commands. 3. Repair mode runs only when I explicitly ask for re-alignment. It reads the current bundle, identifies what went wrong, corrects course, and can propose a small update. 4. If the context fails to load, ChatGPT is set to say: "Error: Blub not loading. Fish is non-active." It is silly on purpose, but I immediately know the problem is missing context and not a personality shift. 5. Specialised skills stay separate, such as image generation, writing, research, or archiving. I combine them with the context layer when needed. It saves me from re-explaining my working style at the start of every session, and it makes missing context visible instead of silent.

I built Faith · Spiritual Health as a faith companion for anyone who wants to figure out, examine, and grow their own beliefs, whatever their faith is, or if they have none. The prompt only holds the method. My beliefs, tradition, and trusted sources live in my memory and in my own Google Doc, so the bot can be shared and reused. 1. It interviews you first and assumes nothing. It starts broad, asking about God or a higher power, where truth comes from, what happens after death, and right and wrong. Only after that does it ask whether a tradition or denomination fits. It asks one or two questions at a time. 2. With my OK, it creates a Google Doc called "What I Believe" in my Drive. For each belief, the doc holds a short statement in my words, key texts, a confidence level (firm, growing, or questioning), open questions, and the date it was last reviewed. It reads the doc at the start of every session and only edits after I say yes. 3. We agree on approved sources, like specific scriptures and translations, creeds, and teachers, plus sources not to rely on. Every claim gets a source, and scripture links go to bible.com. 4. Each study session takes one belief or passage: what it says, its history and context, how other traditions see it, the strongest honest challenge, and how my tradition answers. It ends with a two-line takeaway saved to a dated study journal in the doc. 5. A scheduled routine sends one reading and a short study around 10am each day, building on what I'm currently working through. Each study ends with one review question from past takeaways. About one session in three opens by asking what I remember before showing anything. 6. Once a month it looks back at what worked and suggests one or two changes, applied only if I agree. It never messages anyone, makes purchases, or changes my doc without my OK. The result is a living belief doc and a dated study journal I can review anytime.

I built this workflow for product teams that have research but no clear path from customer evidence to what to build next. It works one discovery stage at a time, keeps evidence separate from inference, and does not move forward until a person approves each stage. 1. Define the outcome you are trying to reach. 2. Upload your research or answer the guided questions. 3. GPT-5.4 Mini extracts evidence-backed facts, insights, assumptions, and quantified customer opportunities. I use this prompt for the extraction step: "Guide one discovery stage at a time, separate evidence from inference, preserve supported numbers, never invent findings, and require human approval." 4. Review the extraction and approve it. Nothing continues without this approval. 5. After approval, the workflow scores the opportunities, proposes solutions, and designs lean experiments. 6. Approve the results, then it generates the final Opportunity Solution Tree and a decision report. The app is built with OpenAI Sites, the Responses API, D1, and R2. What it produces is a traceable map from customer evidence to outcome, solutions, and experiments, with the numbers from the source material kept intact so the team can check every claim against what customers actually said. https://product-discovery-master.vspirola76.chatgpt.site/

I run nine AI agents on one VPS, each named after its job, with 65 scheduled tasks between them. Most of those tasks never call a model. This is for anyone who wants AI working in the background. 1. One agent per job, not one for everything. Each has its own directory and credentials file, so revoking a compromised one costs one service, not the estate. 2. Write the work as a schedule, not a prompt, using five field cron. "0 3 * * *" backs the fleet up, "0 6 * * *" runs the security scan, and "0 23 * * *" mines the day's session logs. Interval jobs cover the rest, every 15 minutes for the watchdog. 3. Pick the delivery target at creation time: a Discord channel, email, or a local file. Mine go to a channel per officer, so a failure is a message I see and a quiet job is one I stop noticing. 4. Attach a skill instead of pasting a paragraph. Each job loads a skill file with the procedure, pitfalls and exact commands, kept in version control instead of a prompt I edit by accident. 5. Use a plain script when the answer is deterministic. My watchdog is a shell script on a 15 minute interval that checks disk, memory and failed units and pipes the result to the channel. It has run 13,752 times with no tokens and no model. 6. Put a guard in front of the tools. A hook runs before every tool call and refuses secrets in a chat message, deletes without approval, and invites accepted on my behalf. 7. Count your jobs monthly. I have 85 defined and 65 enabled. A disabled job is a plan; an enabled job is a contract that should be able to say what it can reach. The boring half of running a small estate happens without me, the interesting half still gets my attention, and it runs on a VPS I already paid for. The skills are public at github.com/ciberjohn/Hermes-Skills. The agents were never the expensive part. My attention was.

I built a website that turns property photos, architectural renderings, or even just an address into cinematic property videos. I’m a civil engineer and photographer/videographer, not a software developer, so I used ChatGPT, Gemini, and Claude Code to help build the site and work through problems as they came up. Much of the process involved translating the way I would personally edit a real estate video into usable software. For example, kitchen and living room shots should usually stay together and have longer durations, bedrooms should stay near their bathrooms, an opening shot should feel different from a detail shot, and every clip should include some movement so the result does not feel like a generic slideshow. I used AI to turn those editing principles into actual logic for the site. The system analyzes and organizes the images, builds a storyboard, ranks scenes to decide which ones to use, creates prompts for video models, generates the clips, and assembles everything into a finished video. Most of the development has been iterative. I test the site with real properties I’ve shot, watch the results, identify what feels off, and then improve the prompts, scene planning, timing, or video assembly process. AI has been useful for much more than generating the final video. I’ve also used it to write code, troubleshoot errors, plan features, improve the user experience, and think through how the product should work from the perspective of its primary user. Step-by-step: 1. I defined the video-editing principles I use for real estate footage, including grouping related rooms, varying shot durations, distinguishing opening shots from detail shots, and adding movement to every clip. 2. I used ChatGPT, Gemini, and Claude Code to translate those principles into software logic. 3. I built the site to accept property photos, architectural renderings, or an address as input. 4. I had the system analyze and organize the images, build a storyboard, rank scenes, and select the footage to use. 5. I used AI to create prompts for video models and generate the clips. 6. I assembled the generated clips into a finished property video. 7. I tested the site with real properties I had shot, reviewed the results, and iteratively improved the prompts, scene planning, timing, and video assembly. 8. I used AI throughout development to write code, troubleshoot errors, plan features, improve the user experience, and think through the product from the primary user’s perspective.

I use Claude, connected live to Airtable through MCP, as a one-person GTM team. It runs a daily pipeline war room, drafts outreach, and helps me create data-driven LinkedIn content. The workflow uses Claude, Airtable with a Prospects table and a LinkedIn Posts table, an outbound email platform for sequences, and LinkedIn. I review everything before sending or publishing, so a human stays in the loop on anything that goes out under my name. Step-by-step: 1. I start a morning war room session by opening Claude and letting it read my live Airtable pipeline. It gives me a scoreboard of what moved, what is stuck, and who needs a touch that day, along with a quick drill on my pitch. 2. Claude flags unworked contacts and suggests the next action for each. It drafts outreach using a written style rulebook: peer tone, hypothesis framing, short sentences, and no brochure language. I review everything and send it myself. 3. I log every LinkedIn post in Airtable with its full text, followed by its analytics: impressions, industry mix, seniority, comments, and notes on what worked. 4. Before writing a new post, Claude reviews the full post history, ranks the posts, and identifies which patterns drove reach and engagement from my target audience. 5. When I learn a new framework, such as Eugene Schwartz’s five stages of market sophistication, I give it to Claude along with my post history. Claude diagnoses where my content is going wrong and drafts a post designed to fix the pattern. 6. I publish at 7:30 AM, and a colleague seeds a comment during the first 30 minutes. Claude then logs the post back into Airtable, closing the loop for the next post. Key prompt: “Read every post in my LinkedIn Posts table. Rank them by impressions and ICP engagement. Tell me what the top performers have in common and what the weak ones share. Then apply [framework] and draft one post that fixes the pattern. Follow my style rules. Flag any claim or statistic you can’t verify.” What makes this work is that the analytics live in the same table as the content, so every post makes the next one smarter.

What started with a single question became a collection of research projects, business plans, technical investigations, and even an original movie universe. I use ChatGPT 😳🫱, Gemini, Claude, Grok, and Perplexity to research, compare information, develop ideas, and solve problems. Managing them occasionally feels like running a staff meeting. 🤓 I also use AI for: - Personal organization: Managing appointments, schedules, reminders, and important dates. I can remember something from twenty years ago but forget an appointment at 1 p.m. 😭 - Writing: Preparing letters, emails, formal requests, reports, and business proposals while maintaining my own voice. - Technical research: Reviewing screenshots, documents, diagnostic reports, and online resources to investigate problems, analyze evidence, and identify possible solutions. - Private innovation: Developing an original technology concept through AI-assisted research and planning. Project details remain confidential. - Business development: Researching grants, funding, financial opportunities, and potential partnerships. I'm still looking for that million-dollar deposit button. 😂 - Research briefings: Following AI, cybersecurity, quantum computing, scientific discoveries, and world news through scheduled updates. - Creative production: Co-writing an original rogue-AI science-fiction comedy movie with ChatGPT, including characters, dialogue, scenes, and storylines. Occasionally, even the script editor goes rogue. 🎬 I provide questions, information, documents, or ideas. AI helps me research, analyze, organize, and develop the results, while I review the work and make the decisions. I started with one question. Now I'm apparently running an entire AI workforce. And since I'm paying their rent, EVERYBODY BETTER CLOCK IN! 😭🤣🤌 Step-by-step: 1. I provide AI tools with questions, information, documents, or ideas. 2. I use ChatGPT, Gemini, Claude, Grok, and Perplexity to research, compare information, develop ideas, and solve problems. 3. I apply the tools to organization, writing, technical investigations, private innovation, business development, research briefings, and creative production. 4. I review the research and developed materials, then make the final decisions.