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

I live in a state experiencing extreme drought conditions, and my water provider recently notified us of new fees for excess usage. That prompted me to dictate nearly 10 years of monthly water bills to Manus by reading each date and gallon total aloud. I then asked it to cross-reference my usage with local temperature and precipitation records for Eden, Utah. The analysis found that temperature explains 51% of the variation in my water usage, while precipitation explains 19%. That suggests roughly 30% is driven by my own choices—a significant opportunity for conscious water stewardship. It took about an hour of conversation to build the entire dataset from scratch. Step-by-step: 1. I read the date and gallon total from each monthly water bill aloud to Manus. 2. I asked Manus to organize nearly 10 years of usage data into a dataset. 3. I asked it to cross-reference my usage with local temperature and precipitation records for Eden, Utah. 4. I reviewed the analysis showing that temperature explained 51% of usage variation, precipitation explained 19%, and roughly 30% was associated with my own choices. 5. I identified that remaining 30% as an opportunity for more conscious water stewardship.

As a hobby/non-work-related creative outlet, I've started to write and create YouTube videos about retro football (soccer) stories. Part of the visuals are vintage stickers of the players mentioned. This used to be a time-intensive Google/eBay search when I was looking for 20+ players at a time. So I used Claude to build a local "Sticker Search" tool. It lets me enter the player, season, and team, find their sticker from that year, and download it to my working folder with one click. It's made my hobby way more fun and sped up the tiresome bit. P.S. I used Billy's guide on Manus to create the animated logo for the videos! Step-by-step: 1. I listed the inputs I needed for each search: player, team, and season. 2. I used Claude to build the local Sticker Search interface and search logic. 3. I added recent-search shortcuts so I could repeat or refine searches quickly. 4. I made each result downloadable with one click to my working folder. 5. I used Billy's Manus guide to create the animated logo for the videos.

I like to chart the tendencies of the Little League hitters I coach. I track their hot zones, how they perform when they’re ahead or behind in the count, and where they chase pitches outside the strike zone. Manus built an app that lets me use a phone or tablet to chart every pitch in each at-bat. It compiles the data into CSV files and visual charts showing swing percentage, whiff percentage, contact percentage, and on-base percentage. The hitters can view the charts during games. Step-by-step: 1. I identify the hitting tendencies I want to track, including hot zones, performance by count, and pitches chased outside the strike zone. 2. I use a phone or tablet to chart every pitch in each at-bat. 3. I use the app to compile the data into CSV files and visual charts. 4. I have the hitters review the charts during games.

Je veux créer N’ose Digital IA, un SaaS international dédié à l’automatisation et conçu de A à Z comme un véritable business SaaS, avec l’IA au cœur de la plateforme. Le projet comprend un dashboard IA de service client ainsi qu’un agent vocal qui répond aux clients et s’appelle « Client ». Step-by-step: 1. Créer le SaaS N’ose Digital IA. 2. Optimiser la plateforme autour de l’automatisation. 3. Concevoir un dashboard IA dédié au service client. 4. Intégrer un agent vocal appelé « Client » pour répondre aux clients. 5. Développer la plateforme comme un business SaaS international, avec l’IA au cœur du projet.

My sister asked me to check if my niece's name appeared in the preliminary school enrollment results. But the list uploaded online was a PDF with 50+ page photographs. Going through all of it would have been a headache — so I put Manus to work. I provided a link to the results, and Manus searched through all of it, checking each document page by page. After about 15 minutes, it found her name and all the relevant details. This saved me from having to manually search through pages of results across multiple categories. Step-by-step: 1. I gave Manus the link to the school’s preliminary enrollment results. 2. I supplied the exact name I needed to find and the context that the PDF contained photographed pages. 3. I asked Manus to inspect the document page by page rather than relying on normal searchable PDF text. 4. I let it search across more than 50 pages and multiple categories. 5. I reviewed the page and details it returned to confirm that it had found the correct person.