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

My AI digest looked perfect and was quietly wrong. What actually fixed it. Every run succeeded. Every dashboard was green. And the content was still wrong. My digest invented "AI Moat Brief", a newsletter that does not exist. It reported scan counts nobody measured. It resurfaced week-old stories as fresh headlines. Here is what broke, and what fixed it. The sorting used to happen in my head: skimmed subject lines, unopened tabs, quiet guilt. The Signal is one email at 08:00: a single Make scenario calling Claude Sonnet through OpenRouter. It reads the last 24 hours of my RSS feeds and newsletters, keeps what touches what I am actively building plus the domains I need to stay current in, and arrives in the language I actually think in. Core items end with what it means for my work. Five to ten minutes, and I know where to go deep today. Structurally it looks like this, minus the content, rendered in English for this post (Image 1). No real edition is shown; section names and sample lines are illustrative. The dangerous failures were never pipeline failures. They were content failures, and the cause is structural: an LLM summarizing newsletters that already summarize primary sources is third hand by construction. Every hop strips attribution and adds confidence, and when data goes missing the model fills the gap the way LLMs do: fluently. Valid HTML, confident tone, green pipeline, wrong content. Image 2 is that whole failure class in one frame. Three rules closed the gaps I caught, all live in production: Step-by-step: 1. Verbatim or nothing. A source name is copied character for character, and a link exists only if that exact URL is in the input. The model copies; it never composes. 2. The model never generates metrics. Every count the report shows is injected by the pipeline after the model returns. 3. Recycled news gets demoted. A recap of recaps gets one line at most, and is dropped when the underlying story falls outside the collection window. Rules 1 and 3 lean on the prompt, and that is why the counters exist. The pipeline writes a hidden HTML comment into every email it sends: items, links, urls, cost, finish status. That line caught what I could not see. In one run, the published-links counter and the leftover-urls counter read 45 and 435: the only sign a new cleanup step was a silent no-op. Another morning the model stopped at 15,999 tokens against a 16,000 cap, one token from an email cut off mid-sentence. On the morning I wrote this they agreed, 21 links and 21 urls, and boring is the goal. Image 3 is that morning's actual comment, with the same two counters from the no-op run. The run itself has a dead man's switch on Healthchecks.io, so a missing 08:00 email reaches me before I notice. Honest limits: the $0.31 per report is a fresh measurement I am still validating, and I have not proven these rules hold as the source set scales. There is more behind every part of this; I would rather share it where it is wanted. Ask and I will put it in the comments: the three rules in full, the exact cost and what drives it, what this replaced in my day, how it compares to what is on the market, or the ugliest of the 15 documented bugs. I am sharing this because I doubt I am the only one building fragile things behind the scenes, and monitoring text is harder than monitoring uptime. What content-level checks do you run on LLM output, the kind pipeline monitoring cannot see? Real thresholds and embarrassing failures especially welcome.

I regularly use ChatGPT for lesson planning and materials development with students ranging from EFL learners to UK undergraduates. I keep a separate anonymous thread for each student, so GPT can track the context and suggest the best direction for the next session. I also contribute my experience as a tutor while using AI to create fresh worksheets based on typical materials from various UK exam boards. Today, I had a successful interview for a lecturer role. Gemini helped me design and plan my demo seminar, and it looks like I’ve landed the job. Step-by-step: 1. I create a separate anonymous thread for each student. 2. I use ChatGPT to track each student’s context and suggest the best direction for the next session. 3. I combine AI-generated ideas with my experience as a tutor when planning lessons and developing materials. 4. I use typical materials from various UK exam boards as the basis for creating fresh worksheets. 5. For my lecturer interview, I used Gemini to design and plan my demo seminar. 6. I had a successful interview, and it looks like I’ve landed the job.

I created a Gemini Gem with custom instructions. When I paste a link to the previous Sunday’s sermon, the Gem “watches” the video and creates five messages—one for each weekday. Each message uses a specific engagement method, such as a link to watch the sermon for anyone who missed it, a graphic featuring a verse from the sermon, or a reflection question tied to the sermon’s theme. After I approve the copy, the Gem creates a properly formatted Google Sheet in my Google Drive, ready to be dragged and dropped into our text provider. Within five minutes, I have content deployed that extends the impact of the 45-minute sermon throughout the week. Step-by-step: 1. I paste a link to the previous Sunday’s sermon into my Gemini Gem. 2. The Gem watches the video and creates five weekday messages. 3. I review and approve the copy for each message. 4. The Gem creates a correctly formatted Google Sheet in my Google Drive. 5. I drag and drop the content into our text provider for deployment.

I built an interactive AI recommender for Medium publications and packaged it as a Gemini Gem. Medium writers who want their articles to be discovered can submit their pieces to a publication, which is like a digital magazine focused on a specific topic. However, there are hundreds of publications, so it can be difficult to find the right one for a particular article. A key resource is "Medium's Huge List of Publications Accepting Submissions." It contains basic information about each publication, but the list is difficult to navigate because of its size. My solution was to organize that information and use it as the source for an AI recommender. I packaged the system as a Gem because the interface is cleaner, and users do not need to see the sources I used. Step-by-step: 1. I asked Gemini to compile and format basic information for each publication, including its topic, size by number of followers, and a short description. 2. I consolidated that information in a Google Sheet. 3. I used the spreadsheet as a source for a Google Notebook (formerly NotebookLM). 4. I added instructions for the AI, like the following: "You are an expert guiding the user to find the ideal publications for their articles in Medium. Ask the user to write down what their interests, topics, etc., are; whether they are beginner writers; whether they want to start with a small publication (less than 1,000 followers), mid-size (a few thousand), or only the biggest (tens or hundreds of thousands). Ask them for any other personal information and details about their writing, and take that into account." 5. I packaged the system as a Gemini Gem instead of distributing it as a Notebook so users could access it through a cleaner interface without seeing the sources. It can be accessed at the following link: https://gemini.google.com/gem/1HDPzcE6Jls76V4I2tFZhIn-SbeeDe-_-?usp=sharing

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.

Build a custom WordPress plugin with Claude to showcase real estate properties. The example shown in the screenshot is designed with an elegant, precise presentation and includes custom search filters, property cards, bookmarking, and sharing capabilities. Instead of paying for an existing plugin, you can build your own with Claude or another LLM, such as Gemini. Step-by-step: 1. Define the scope and plan the plugin’s features. 2. Set up a local testing environment. 3. Prompt Claude to generate the code. You can also use another LLM, such as Gemini. 4. Create the plugin directory and files. 5. Test the plugin and iterate.

I created an online app where my friends can select the gigs they plan to attend. It shows who is going to each gig and when, along with a clear festival-wide timeline. The festival host only provides stage-based schedules, which are difficult to read and coordinate. My app brings the information together in a more practical format for planning with friends. Step-by-step: 1. I created an online app for coordinating festival plans. 2. I added a way for friends to select the gigs they plan to attend. 3. I organized the selections to show who is going to each gig and when. 4. I created a clear timeline that combines the festival’s stage-based schedules. 5. I used the combined timeline to make planning and coordination easier.

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.

I used ChatGPT to help create a book in a specialized area of hypnosis. It still needs some refining. The book provides a verbal account of the actions parents need to take to accomplish their goal. It supports both the parents and the child through positive reinforcement. As the parents speak their part, the message becomes ingrained in them as well. Step-by-step: 1. I used ChatGPT to help create the book. 2. I focused the content on the actions parents need to take to accomplish their goal. 3. I used positive reinforcement to support both the parents and the child. 4. I had the parents speak their part so the message would become ingrained in them as well.

Last year, my daughter was diagnosed with a rare autoimmune disease. Like any parent in that situation, I wanted to understand everything I could so we could make the best decisions for her care. I used both Gemini and ChatGPT to help me sort through the medical literature, treatment options, possible side effects, and how other countries approach treatment. I also turned to ChatGPT to identify the leading specialists in the country — thankfully, our referred doctor turned out to be one of them, which gave us even more reassurance. More than anything, it helped demystify the disease and make us feel confident that we were doing everything we could. She's doing really well on her medications, and seeing her recover has been an enormous relief. Step-by-step: 1. I gathered the diagnosis, questions, and medical context I needed to understand more clearly. 2. I used Gemini and ChatGPT to work through medical literature, treatment options, possible side effects, and approaches used in other countries. 3. I asked ChatGPT to identify leading specialists and explain why their experience was relevant. 4. I compared the research with the care team we had already been referred to. 5. I used the findings to prepare better questions and support discussions with clinicians, not to replace medical care.