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

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

I had a project that was perplexing me, so I asked an AI for help by simply typing, "I'm a stupid moron." The AI helped me with the issues I was having with my project. 1. I described my project-related difficulties by typing, "I'm a stupid moron." 2. I used the AI's help to address the issues I was having with my project.

I'm knitting a sweater for my baby nephew, and accidentally knitted extra rows, but didn't notice until I was 30 rows past it. I dropped the pattern I was using into ChatGPT and asked it to revise it so the stripes on the front & back aligned. Saved me from undoing my work and made sure the sweater stayed cute! Step-by-step: 1. I gave ChatGPT the original knitting pattern and explained where I had accidentally added the extra rows. 2. I told it how far I had continued knitting before noticing the mistake. 3. I asked it to recalculate the remaining pattern instead of telling me to undo 30 rows of work. 4. I checked that the revised stripe counts would align across the front and back. 5. I continued knitting from the corrected instructions while preserving the completed work.

I used AI to develop a simple daily care plan for my above-ground pool. I copied the links to the pool I bought online and asked which chemicals would be best and whether I should make any upgrades right away. Then I asked AI to create a daily routine to keep the pool sparkling throughout the summer. When the water started looking cloudy, I took pictures of the water tests I was running and shared them so AI could help me get the pool back where it needed to be. Step-by-step: 1. I copied the online links for the above-ground pool I bought. 2. I asked AI which chemicals would be best for the pool and whether I should make any upgrades. 3. I asked AI to create a daily pool-care routine for the summer months. 4. When the water became cloudy, I took pictures of the tests I was running on the water. 5. I shared the pictures with AI to get guidance on bringing the water back to the right condition.

I built a Driver Management System with ChatGPT and Google. It stores client and driver information, including links, and lets me schedule jobs through a one-click booking wizard. The system also provides reports, helps me search for available drivers by licence type and other criteria, tracks available jobs, and includes a dashboard showing unassigned drivers. This is my first project with AI, and I love what I’ve been able to build. Step-by-step: 1. I used ChatGPT and Google to build a Driver Management System. 2. I added client and driver information, including links. 3. I created a one-click booking wizard for scheduling jobs. 4. I added reports and search tools for finding available drivers by licence type and other criteria. 5. I set up job tracking and a dashboard showing unassigned drivers.

I used ChatGPT + Button to understand my dog’s blood work in language I could follow. Every couple of weeks, I uploaded all of my dog’s blood work PDF files and provided the information verbally that wasn’t included on the forms. It helped me understand which markers were important and compare the results from week to week, including where values were changing. That gave me a better foundation for conversations during veterinary appointments. During a difficult time, it also gave me peace of mind in a way nothing else could. It feels strange to say that, but it’s true. Step-by-step: 1. I uploaded all of my dog’s blood work PDF files to ChatGPT + Button every couple of weeks. 2. I provided the relevant information verbally when it wasn’t included on the forms. 3. I used it to identify which markers were important. 4. I compared the results from week to week and reviewed where the values were changing. 5. I used that understanding to have better conversations with the veterinarian.

I needed to create documentation for an insulation company, so I put together a set of images that people could understand within three to five seconds. The materials gave salespeople something to leave behind to help customers make a decision and understand how they could save money through rebates and tax incentives. Before this, salespeople were mainly dropping off the contract, and they were closing two out of 10 deals. Now they’re closing six out of 10. I think that number will go even higher as people get more time to organize the rebates and bids. Step-by-step: 1. I created documentation for the insulation company using images that people could understand within three to five seconds. 2. I made the materials useful for salespeople to leave behind after meeting with customers. 3. I included information to help customers understand potential savings from rebates and tax incentives. 4. I compared the results with the previous approach, when salespeople mainly dropped off the contract and closed two out of 10 deals. 5. After using the new materials, the sales team increased its close rate to six out of 10 deals. 6. I expect the close rate may increase further as customers have time to organize the rebates and bids.

I use AI to create personalized tools and social stories that help therapists and group-home staff better understand my son’s complex disability and support his independence as an adult. Step-by-step: 1. I use AI to create personalized tools for my son. 2. I create social stories that help therapists and group-home staff better understand his complex disability. 3. I use these resources to support his independence as an adult.

BiteTrack makes calorie tracking simple with AI. Step-by-step: 1. Log a meal using a photo, voice, text, barcode, or food search. 2. BiteTrack’s AI identifies the food and estimates its calories, protein, carbohydrates, and fats. 3. Track daily nutrition, weight, and progress in one place. 4. Receive personalized nutrition recommendations based on health and fitness goals. 5. Monitor progress over time with detailed analytics to stay on track. Whether you're trying to lose weight, gain muscle, or maintain a healthy lifestyle, BiteTrack helps you make smarter nutrition decisions every day.

Customer events trigger AI workflows that classify requests, automate actions, update systems, and keep teams in sync without manual intervention. Step-by-step: 1. Customer events trigger the AI workflows. 2. The workflows classify requests. 3. They automate actions and update systems. 4. They keep teams in sync without manual intervention.

I use ChatGPT as a label-reading filter for packaged snacks, uploading product photos and asking it to flag hidden sugars, oils like palm, and preservatives, then compare options against a strict checklist of clean ingredients, minimal processing, and decent macros. It's especially useful for decoding lesser-known, jargon-heavy terms on the back label, translating things like INS numbers, stabilizers, and emulsifiers into plain English so it's clear what's actually being consumed. Instead of trusting front-of-pack claims like "multigrain" or "sugar-free," it breaks down what's inside, surfaces trade-offs, and narrows choices to the best options available online Step-by-step: 1. I photographed the ingredient labels on the packaged snacks I was considering. 2. I gave ChatGPT a strict checklist covering hidden sugars, oils such as palm oil, preservatives, processing, and macros. 3. I asked it to translate ingredient jargon such as INS numbers, stabilizers, and emulsifiers into plain language. 4. I had it compare the products based on what was actually inside rather than the claims on the front of the package. 5. I used the trade-offs it surfaced to narrow the list to the best available options.

Copy and paste the ChatGPT prompt. A screen video is included.

I wanted to see what Awish would automate first if I gave it a real client business instead of a predefined workflow. I used Martolia Marble, one of my previous clients, and gave Awish the website. I asked it to analyze the business, suggest automations that could support growth, and build them only after I approved them. Awish analyzed the website and proposed several opportunities. I chose two: a lead generation and email outreach workflow, and an Instagram workflow that tracks relevant trends, plans content, creates posts, and publishes them. Step-by-step: 1. I gave Awish the Martolia Marble website and asked it to analyze the business. 2. Awish identified areas where automation could support growth and suggested workflows. 3. I approved a lead generation workflow that finds relevant prospects and prepares personalized email outreach. 4. Awish selected the required apps, I connected the accounts, and the agents built the workflow. 5. I also approved an Instagram workflow that analyzes relevant trends, plans upcoming content, creates the posts, and publishes them. 6. Once the accounts were connected, both automations were ready to run without me manually building each step. What I liked most was starting with the business rather than with an automation idea. I gave Awish the website, reviewed its suggestions, and approved only the workflows that made sense for the client.

子どもが気に入って毎日読んでいる絵本の付属品が、破れたり紛失したりしてボロボロになっていました。そこで、付属品を写真に撮ってChatGPTに送り、似たものを複製してもらいました。 さらに、もともとは付属していなかったものの、子どもがあったら喜びそうな付属品も追加で作ってもらいました。完成したものをハサミで切ってラミネート加工し、絵本と一緒に渡しました。 ポイントは、絵本のページをいくつか写真でChatGPTに送り、同じようなデザインやテイストのイラストを生成してもらうことです。そうすることで、絵本の世界観を崩さずに付属品を作れます。 Step-by-step: 1. 破れたり紛失したりした絵本の付属品を写真に撮る。 2. 絵本のページをいくつか写真に撮り、ChatGPTに送る。 3. 絵本と同じようなデザインやテイストで、付属品を複製してもらう。 4. 子どもが喜びそうな、もともとは付属していなかった付属品も追加で作ってもらう。 5. 作成した付属品をハサミで切ってラミネート加工し、絵本と一緒に渡す。

I created a skill that helps me submit a garment reimbursement every month. It handles the long forms and the upload of thousands of different documents required for the reimbursement. Step-by-step: 1. I created a skill for submitting my garment reimbursement. 2. I use it every month to complete the required long forms. 3. I upload the different types of documents needed for the submission.

Earlier in my career, I spent a significant amount of time delivering security risk assessments. These engagements typically took 8–12 weeks from the initial client meeting to the final report, with complex projects often stretching to 3–4 months. Today, I can produce reports of comparable quality in 1–2 days. The automation runs end-to-end in about 15 minutes; I spend the remaining time reviewing and validating the output. The workflow starts with a structured questionnaire and uses ChatGPT, Perplexity, Claude, Make.com, Google Drive, and Gamma.ai to research, draft, format, and deliver the report. This compresses the delivery timeline while preserving quality and lets me focus on expert judgment, validation, and client communication instead of manual report production. Step-by-step: 1. I have the client visit a web page and complete a structured questionnaire built on Lovable.dev. 2. The submitted information triggers an automated Make.com workflow. 3. ChatGPT analyzes the client’s responses. 4. Perplexity conducts targeted research tailored to the client’s industry, context, and risk profile. 5. Claude drafts the report and saves it to Google Drive. 6. The draft is passed to Gamma.ai, which generates the final client-ready report. 7. I receive the report by email, perform a thorough review, and send it to the client once I approve it. 8. I use the time saved to focus on expert judgment, output validation, and client communication.

This year, we only have one day—eight hours—at the Fringe, so we needed to decide what to see. We first scanned the roughly 800 available shows and made a shortlist of 38. After a second round, we narrowed it to 21. I gave the shortlist to ChatGPT, including the show times and locations, and asked it to create five itineraries that fit in as many shows as possible, allowed enough time to travel between venues, and finished with a particular show: a Johnny Cash tribute. The five options quickly became two. After one small tweak, we had our plan: five shows, minimal walking, and time to eat in George Square. Step-by-step: 1. I scanned the roughly 800 available shows and created a shortlist of 38. 2. I reviewed the shortlist and narrowed it to 21 shows. 3. I gave ChatGPT the remaining shows, including their times and locations. 4. I asked ChatGPT to create five itineraries that fit in as many shows as possible, allowed time to travel between venues, and finished with the Johnny Cash tribute. 5. I narrowed the options to two, made one small tweak, and chose an itinerary for five shows with minimal walking and time to eat in George Square.

The new ChatGPT Chrome extension is surprisingly good at navigating complicated technical settings. My favorite use case so far has been using it to create the special DNS records for a new website. This has always been confusing, even though I’ve done it dozens of times. The process varies across platforms, every DNS registrar uses different names for records such as A and CNAME records, and the interfaces are constantly changing. It’s tedious and easy to get wrong. For this kind of one-off, highly detailed technical task, I copy and paste the specific instructions from my website host provider into the extension while I’m logged in to my DNS provider. GPT then takes control of the mouse and fills in the required fields. The use cases are endless, from filling out an expense report to handling other tedious tasks in legacy or old-school software that doesn’t have a simple CLI, MCP, or API connection. If AI can’t control a system directly through the backend, browser control closes another gap. These legacy systems often lack newer integrations, which also makes them annoying, tedious, and frustrating to use. That makes them particularly good tasks to give to AI—especially now that the ChatGPT Chrome extension is good at following instructions and completing actions in the browser. Step-by-step: 1. I log in to my DNS provider. 2. I copy and paste the specific DNS instructions from my website host provider into the ChatGPT Chrome extension. 3. I let GPT navigate the DNS provider’s interface and take control of the mouse. 4. GPT fills in the required fields for records such as A or CNAME records, accounting for the registrar’s particular interface. 5. I use the same approach for other detailed, repetitive tasks in legacy software that lacks CLI, MCP, or API connections.

I have been looking around at new apartment development projects, looking to potentially buy in the next two years. I used ChatGPT Deep Research to help compare the cost, the quality of the appliances and materials the builders are using, and chart out the overall cost. Step-by-step: 1. I listed the apartment developments I was considering and the roughly two-year purchase horizon. 2. I asked ChatGPT Deep Research to compare the purchase cost of the options. 3. I had it research the quality of the appliances and materials each builder was using. 4. I asked it to chart the overall cost so the differences were easier to see. 5. I used the combined research and visuals to compare projects on more than the advertised price.

This World Cup 2026 poetry generator scraped the web for match information and called LLMs to help users generate match-specific poems. 1. A daily schedule triggered web scraping to collect match information. 2. When a user requested a poem, the generator used that match information to create a new match-specific poem with help from LLMs.