Share your best AI workflow. We could show it to 2M+ people.

I took a picture of my wife's spice rack, uploaded it to Grok, and asked it to organize the contents into three categories: Must Have, Keep, and Discard, based on age or lack of common usage. Step-by-step: 1. I took a picture of my wife's spice rack. 2. I uploaded the picture to Grok. 3. I asked Grok to categorize the contents as Must Have, Keep, or Discard based on age or lack of common usage.

I built a personal daily tracking system called Artifact. It gives me a way to log my days and turn the data into decisions over time. To use it, I copy everything attached—or screenshot the included “green orange red” example—and paste it into my AI assistant, preferably Claude. The assistant briefly interviews me and then builds a personalized daily tracking system.

It's finally gardening season in the Midwest, and I wanted to do a big overhaul of my space with a new large in-ground bed and a more organized layout of crops. I first took some images of the space and had ChatGPT / Codex generate some visualizations of what it could look like based on my rambling list of requirements and measurements. After deciding on the vision, I asked for help creating a materials list, a step-by-step guide to building the bed (with instructions on sawing, drilling, etc.). I also provided a list of what we wanted to grow, and was able to get a well-planned map of where to place each plant, optimizing for aspects like shade vs. sun, companion plants, vining, etc. Several trips to Home Depot and a couple of days of work later, we have an awesome, refreshed space and a thoughtful, organized garden for the season! Step-by-step: 1. I photographed the existing garden space and wrote down the measurements, requirements, and rough ideas I had in mind. 2. I gave the images and requirements to ChatGPT and Codex and asked for several visualizations of the finished space. 3. Once I chose a direction, I asked for a materials list and step-by-step instructions for building the in-ground bed. 4. I supplied the full list of plants and asked for a placement map based on sun, shade, companion planting, and vining behavior. 5. I used the plan to buy materials, build the bed, and install a more organized garden layout.

I recently bought a house & had an inspection done as a closing condition. I uploaded the inspection report (80 pages) to Claude and asked it to make a list of home maintenance tasks by timeline (closing week, seasonally, etc.). Then, based on that list, I had it create one-off or annually recurring calendar events in my personal Google Calendar, with my husband invited to each event. It was super helpful because the inspection report clearly noted when the maintenance tasks were completed and suggested a frequency for the future. Step-by-step: 1. I uploaded the full 80-page home inspection report to Claude. 2. I asked it to extract every maintenance item and organize the work by closing week, season, and recurring frequency. 3. I had it use the report’s completion dates and recommended intervals to calculate when each task should happen next. 4. I reviewed the list for anything that needed to be corrected or combined. 5. I asked Claude to create one-off and annually recurring Google Calendar events and invite my husband to each one.

I first tried to build Rumbly.xyz about six months ago using Lovable, but I ran into several issues and kept getting errors, so I temporarily gave up. Then I discovered Replit. AI had also matured over those six months, which likely helped. I entered a three- or four-paragraph prompt describing exactly what I wanted, and about 75% of the app was built immediately. The problem I wanted to solve was simple: on an average Tuesday or Wednesday, my wife and I talk about where we want to eat. We know our friends have recommended countless places, and we keep saying we're going to try them, but we can only think of the two or three restaurants we always visit. So we end up going to the same places again. I built Rumbly.xyz as a simple web app. It lets you record a recommended restaurant, who recommended it, and what type of food it serves. Rumbly connects each restaurant to the Google Maps database, giving you the exact name and a map view, and you can add notes. Then I realized there was no reason to save only restaurant recommendations. People also recommend streaming series and books, and they tell jokes. I can never remember a joke two months later when someone asks, “Do you know any good jokes?”—even if I thought the last five were hilarious. Rumbly.xyz lets you save any of these recommendations from your friends and share them with friends who are already on Rumbly or have not joined yet. I connected it to email and enabled it to send mobile messages to your phone. I built all of this through Replit. Step-by-step: 1. I described the problem and the app I wanted in a three- or four-paragraph prompt in Replit. 2. I built a web app that records restaurant recommendations, the person who made each recommendation, the type of food, and additional notes. 3. I connected restaurant entries to the Google Maps database for exact names and a map view. 4. I expanded the app to save recommendations for streaming series, books, and jokes—not just restaurants. 5. I connected Rumbly.xyz to email and mobile messaging so recommendations can be shared with friends who are on Rumbly or have not joined yet.

My Downloads folder had been filled with random files for the last six months, and I'd been procrastinating on cleaning it up. So I gave Claude Cowork access to the folder, and asked it to "help me organize this folder." In a few minutes, it went through almost 100GB of files, arranged them by file type and folders, and removed duplicate files in just a few minutes, something that could have cost me hours of work. Step-by-step: 1. I gave Claude Cowork access to the Downloads folder that had accumulated files for roughly six months. 2. I asked it to inspect the folder and propose a sensible organization rather than specifying every destination myself. 3. I had it group the files into folders based on type and content. 4. I asked it to identify and remove duplicate files. 5. I let the workflow process the full folder, which was nearly 100GB, in one pass.

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 used Claude and Nano Banana 2 to create a detailed landscaping plan for my property. The plan included precise recommendations for plant types and locations, soil testing, purchase lists, local suppliers, expected wholesale pricing, and photorealistic images of the mature planting beds. I refined the plan through 20–30 iterations, incorporating all of my requirements. Because I have previous experience working with landscape architects, I was able to use the AI-generated plan effectively and legitimately saved $5,000 in fees. Step-by-step: 1. I used Claude and Nano Banana 2 to develop a landscaping plan for my property. 2. I included requirements for plant types and locations, soil testing, purchase lists, local suppliers, expected wholesale pricing, and photorealistic images of the mature planting beds. 3. I refined the plan through 20–30 iterations until all of my requirements were incorporated. 4. I used my previous experience working with landscape architects to evaluate and apply the plan. 5. I saved $5,000 in landscape architecture fees.

I love playing poker, both online and live. One month, I performed poorly. Although it felt like the cards were running badly, I wondered whether I had developed a problem in my game and was blaming my losses on bad luck. I asked around, including asking AI, whether a tool existed that could measure luck from poker hand histories. The unwelcome answer was that it did not. I'm not a coder, but after doing some research into vibe coding, I started building a luck-detection app in a Claude chat. Claude built the UI directly in the chat window and advised me on the formulas I was using to calculate luck for the cards dealt, my performance on the flop, and my performance when I went all in. All three metrics have strong averages, and luck is what varies them. I used a bell curve to model hand outcomes and a Monte Carlo simulator, which Claude suggested and executed, to evaluate all possible outcomes. The result astonished me because it was so useful. I immediately fixed two major leaks in my game and felt better knowing that bad luck really was the main problem affecting my results. I liked the tool so much that I decided to turn it into a full web app with Claude Code, and now an iPhone app that I may let other people use for free. I also had a lot of fun building it—except for learning how to use Xcode. That was a pain, even with step-by-step guidance from Claude. Step-by-step: 1. I reviewed a month of poor poker results and questioned whether bad luck or problems in my game were causing the losses. 2. I researched whether a tool existed that could measure luck from poker hand histories and learned that I would need to build one myself. 3. I used vibe coding to start building a luck-detection app in a Claude chat. 4. I had Claude create the UI and advise on formulas for evaluating cards dealt, flop performance, and all-in performance. 5. I used a bell curve to model hand outcomes and a Monte Carlo simulator to evaluate possible outcomes. 6. I used the results to identify and fix two major leaks in my game and confirm that bad luck was also affecting my results. 7. I expanded the project into a full web app with Claude Code and then began building an iPhone app, working through the added challenge of learning Xcode.

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.

My father-in-law has had some close calls with phishing attacks, so I built a digital bodyguard with Claude Code to watch over their email around the clock. It’s designed to catch scam and phishing attempts that are specifically crafted to fool people: fake bank alerts, urgent “click here” links, and messages pretending to be from someone they trust. When it spots one, it pulls the message out of the inbox into a separate folder and sends me an alert so I know it happened. I wrote up the full system, including the prompting and context, in GitHub: https://onabetternote.substack.com/p/using-ai-to-guard-against-email-scams?r=6ihgge&utm_campaign=post-expanded-share&utm_medium=web Step-by-step: 1. I built a digital email bodyguard with Claude Code to monitor my father-in-law’s email around the clock. 2. I configured it to look for phishing and scam messages, including fake bank alerts, urgent “click here” links, and messages impersonating trusted people. 3. When it identifies a suspicious message, it moves it from the inbox into a separate folder. 4. It sends me an alert whenever it takes action. 5. I documented the full system, including the prompting and context, in GitHub.

As a busy father, I was tired of not having the fitness features I needed, so I used Lovable to create an accountability schedule for workouts and nutrition. Step-by-step: 1. I identified the fitness features I needed as a busy father. 2. I used Lovable to build a fitness app around those needs. 3. I created an accountability schedule for working out and nutrition.

My best friend from high school got married last weekend, and as the groomsmen, we wanted to create a gift that felt personal and nostalgic. We collected our old photos together and used Seedance to animate them—bringing each still image to life from the first frame— and then stitched several clips into one final video. The result was amazing: the groom was deeply touched, and we all shared a heartfelt moment watching it together on the wedding day, reliving our memories in a way that felt both timeless and new. Step-by-step: 1. I collected old photos of the groom and the friends who had known him since high school. 2. I used each still image as the first frame for a Seedance animation. 3. I generated short clips that brought the individual memories to life. 4. I selected the strongest outputs and stitched them into one continuous video. 5. I shared the finished piece at the wedding as a personal, nostalgic gift.

Sometimes I want something good to read but don’t know exactly what. Finding the right book, article, or story means searching through existing content and hoping something matches my current mood and interests. Generative AI creates another option: instead of finding something to read, I can create exactly what I want to read right now. I created a personalized Reading Experience Generator that acts as an on-demand writer rather than a recommendation engine. When I tell it I want something to read, it asks me a few questions—one at a time—to understand what I’m in the mood for. It determines whether I want fiction or nonfiction, the tone and mood, the subject or setting, and any particular angle I’m interested in. Once it knows enough, it writes an original 1,000–2,000-word piece specifically for that moment. The key instruction is that it never recommends existing books, authors, stories, or articles. Its only job is to create something new. Step-by-step: 1. I create instructions that give the AI a single role: when I want something to read, it should write something original, not recommend existing content. 2. I tell it to begin each new reading experience by asking 2–4 questions, one at a time, and to stop asking as soon as it has enough information. 3. I have the questions establish whether I want fiction or nonfiction, my desired mood or tone, the subject, setting, or genre, and any particular angle I’m interested in. 4. I explicitly prohibit recommendations of existing books, authors, articles, or stories. This prevents the assistant from turning the experience into a conventional recommendation engine. 5. I define a target length of roughly 1,000–2,000 words—long enough to become immersed without requiring a major time commitment. 6. I tell the AI to begin writing immediately once it understands what I want. There should be no outline, explanation, or preamble; the next thing I see should be the piece itself. 7. When I want something different, I start again. The AI repeats the short interview and creates a completely new reading experience based on what I’m interested in at that moment. Instead of choosing from a fixed library of things other people have already written, I get an effectively unlimited supply of original reading material personalized to my interests and mood. The interesting shift is that I’m not using AI to help me write. I’m using AI as the writer, and I’m the audience.

AI chatbots have limitations around memory, numbers and types of attachments, connectors, storage, and other resources. The underlying LLMs also change over time, and data leakage is a concern. Code-based versions such as Claude Code and Grok Build can store essentially unlimited files on your computer, organize them with databases and files, connect to public and private MCPs, and even host interfaces for reviewing results. You can choose between a hosted LLM such as Claude, Grok, or ChatGPT and a local LLM if you prefer. The best part is that these code-based versions have no memory between sessions: everything is stored on your computer, assuming a basic subscription. You start by prompting the system about the domain, what you want to store, how you want to access it, and other requirements. Then it creates the system for you. I started with my own personal health archive. I'm comfortable using the terminal interface for Claude Code and Grok Build, so I use that directly. When I built one for my wife, she couldn't use the terminal, so I had it build a basic website with Q&A interfaces, data access, and upload functionality. I hosted it on my Mac, and I wrote no code. We loaded hundreds of documents in various formats into each of our instances without any trouble. When we have new files, we can simply drop them in. For specific questions or health events we're tracking, the system has perfect memory and no memory limits within the archive. For my archive, I use a Garmin watch and a food tracker. Because public MCPs weren't available for those services, I had the system build local MCP servers by reverse-engineering them. My health tracker now has a continual feed of my food, fitness, sleep, and other data. My wife has some chronic health issues, and we had reached a point where the standard chatbots were hitting their limits. We were struggling and didn't know what to do, so I discussed it with Claude, and we came up with this approach. The best part, besides getting a better handle on our health, is that I can launch any LLM within the project—Claude, Grok, or others—and use it for that session. The project isn't tied to or limited to a single LLM. That lets me manage costs, switch to better LLMs as they improve, and use specialized models for deep research, all while working with one data set. Step-by-step: 1. I prompted a code-based AI about the health domain, the information I wanted to store, and how I wanted to access it. 2. I created a personal health archive and loaded hundreds of documents in various formats into it. 3. I built a second archive for my wife with a basic website, Q&A interfaces, data access, and upload functionality, then hosted it on my Mac. 4. I added new files by dropping them into the appropriate archive. 5. I had the system build local MCP servers for my Garmin watch and food tracker by reverse-engineering those services when public MCPs weren't available. 6. I used the resulting health tracker to maintain a continual feed of food, fitness, sleep, and other health data. 7. I launched different hosted or local LLMs within the same project as needed for each session, including using specialized models for deep research.

I've basically had the exact same haircut since high school, so this year I finally decided to experiment a bit with Nano Banana 2 and see what a different look might feel like. I uploaded my own portraits and started merging them with different models' hairstyles. After 10+ rounds of virtual makeovers, I found out that the hairstyle that suited me best was… my current one. Step-by-step: 1. I uploaded my own portrait photos to Nano Banana 2. 2. I gathered examples of different hairstyles I wanted to test. 3. I asked the model to merge each hairstyle with my portraits while keeping my identity recognizable. 4. I repeated the process for more than ten virtual makeovers. 5. I compared the results side by side and learned that my current haircut still suited me best.

For too many years, I had always wanted to frame a series of photos of our favorite view of our cabin to capture it in all four seasons. But I never had the framing just right. So I simply uploaded the versions I had to Gemini's Nano Banana Pro along with an example of a painting style that I liked, and within a few iterations I got something that captured my vision perfectly. Try It: Start with the new super fast, and cheap Nano Banana 2 Lite to get several options to consider quickly. Then pass it off to Nano Banana Pro (Set to 4K - High Thinking) to get a file with enough resolution to send to a printer. Step-by-step: 1. I gathered the best photo I had for each season and chose a painting style reference that matched the look I wanted. 2. I uploaded the seasonal photos and style reference to Gemini and asked it to create one cohesive four-season composition. 3. I generated several fast variations with Nano Banana 2 Lite so I could compare framing and treatment without over-investing in the first idea. 4. I iterated on the strongest direction until the composition and style felt consistent across all four images. 5. I passed the final direction to Nano Banana Pro with 4K and High Thinking enabled to create a print-ready file.

I used AI to help investigate a family mystery that had remained unresolved for decades: identifying the biological family of my maternal grandfather. The challenge was not a lack of information. It was almost the opposite. I had DNA matches, family trees, names, dates, historical records, old photographs, obituaries, Facebook genealogy groups, and conversations with possible relatives. The difficult part was connecting all these scattered clues without jumping to conclusions. I built a research workflow in which AI acts as an investigation partner, not as the source of truth. Step-by-step: 1. I gathered the information I already had from genealogy platforms, DNA matches, family trees, historical documents, and family records. 2. I used ChatGPT to organize the evidence into people, dates, locations, relationships, DNA connections, documents, and unresolved questions. 3. I separated the information into three categories: confirmed facts, hypotheses, and missing information. 4. Instead of asking AI, “Who was my grandfather's biological father?”, I asked it to analyze possible family connections and identify which hypotheses were compatible with the available evidence. 5. For each hypothesis, I looked for supporting evidence, contradictory evidence, and information that was still needed. 6. I treated AI-generated connections as leads rather than genealogical proof. The goal was to use AI to decide what to investigate next, not to have it find the answer. 7. I used AI to compare family branches, surnames, generations, locations, and possible relationships among DNA matches whose family connections I did not immediately recognize. 8. When a promising connection appeared, I returned to the original genealogy and DNA sources to verify it. This gradually turned a long list of DNA matches into a smaller number of research paths. 9. I used AI to draft respectful, personalized messages to DNA matches and members of genealogy communities, including people in another country and language. 10. In each message, I explained what I was researching, what connection I suspected, what information I already had, and what I hoped the recipient might be able to confirm or rule out. 11. I treated their responses as new evidence and repeated the investigation loop: evidence → AI analysis → hypothesis → verification → human contact → new evidence → updated hypothesis. The final result is not an “AI-generated family tree.” It is a human-led investigation in which AI helps manage complexity, ask better questions, and identify the next useful action. The most important lesson I learned is that AI is particularly useful in genealogy when you do not ask it to give you the answer. Ask it to help you build the investigation.

I adopted three kittens last week when they were just four weeks old. At first, they were overwhelmed by the new environment and refused to eat, which really worried me. I turned to ChatGPT for help and got clear, practical guidance on what to feed them, how to keep them hydrated, and how to set up a comfortable space so they could adjust more easily. I followed a simple feeding plan and kept track of their behavior daily. Gradually, they started eating, became more active, and settled in. Now they're happy, playful, and fully adapted to their new home. Step-by-step: 1. I described the kittens’ age, the move into a new environment, and the fact that they were refusing to eat. 2. I asked ChatGPT for practical guidance on feeding, hydration, and making the space feel safe and comfortable. 3. I turned the advice into a simple feeding and care plan I could follow consistently. 4. I tracked their eating, hydration, activity, and behavior each day. 5. I used those daily observations to confirm that they were gradually eating more, becoming active, and adapting.

I have an electric car, solar panels on my home, and a home battery. On cloudy days, charging my car drained the battery and drew power from the grid, which I wanted to avoid. I used Claude to write code for my EV charger and inverter. The code monitors my solar panels’ output and adjusts the charging speed so the battery still receives some charge without drawing power from the grid. Step-by-step: 1. I identified that charging my EV on cloudy days was draining the home battery and drawing power from the grid. 2. I asked Claude to write code for my EV charger and inverter. 3. I set up the code to monitor the output from my solar panels. 4. I configured it to adjust the EV’s charging speed based on that output. 5. I used the adjusted charging speed to ensure the home battery received some charge while avoiding grid power draw.