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

I’m pregnant with my second child. For my first, we had a doula, so my husband and I didn’t spend much time learning about labor positions or what can help during labor because we knew she would guide us. This time, we don’t have a doula, and we didn’t want to spend a lot of money on an online course or take the time to attend an in-person one. I asked ChatGPT to scour free resources from leading experts and create a mini-course we could work through, along with a cheat sheet for my husband to use during labor. It saved me hours of research and gave us an incredibly useful resource. Step-by-step: 1. I explained that I’m pregnant with my second child and that we had relied on a doula during my first labor. 2. I identified the information we needed to learn, including labor positions and what can help during labor. 3. I asked ChatGPT to scour free resources from leading experts and use them to develop a mini-course. 4. I also asked it to create a cheat sheet for my husband to use during labor. 5. We used the mini-course and cheat sheet as a more affordable and convenient alternative to an online or in-person course.

I’m a very unsophisticated user—and an older man—so my use of ChatGPT is still fairly basic. But it has changed my life. I use ChatGPT as a research assistant for a book I’m writing. In practice, what I do is not much more than an in-depth search, but ChatGPT has taken me places in this journey that I would have thought impossible just three months ago. We’re now deeply engaged in solid research that will likely last about two years before we reach the writing phase. I’m energized by what we’re doing and wanted to share the experience. I believe AI is going to change the way working historians conduct research. Step-by-step: 1. I use ChatGPT as a research assistant for the book I’m writing. 2. I use it for in-depth searching and research. 3. I continue developing the research with ChatGPT over an expected two-year period before beginning the writing phase. 4. I reflect on how this process is changing my research journey and the way historians may conduct research.

I’ve found it useful to use Claude while reading nonfiction books, such as *Factfulness* by Rosling. I ask Claude for a synopsis of the book and save the result as a PDF on my computer for future reference. I also ask Claude to quiz me about the book, either with multiple-choice questions or in short-answer format, to test whether I’ve fully understood what I’ve read. In an ongoing conversation, Claude can also relate the current book to other books I’ve recently read and provide additional synopses. Step-by-step: 1. I tell Claude which nonfiction book I’m reading, such as *Factfulness* by Rosling. 2. I ask Claude to create a synopsis of the book. 3. I save the synopsis as a PDF on my computer for future reference. 4. I ask Claude to quiz me using either multiple-choice or short-answer questions. 5. I continue the conversation so Claude can relate the book to other books I’ve recently read and provide further synopses.

Tell AI the Real Goal, Not Just the Scorecard THE PROBLEM When we give AI a task, we often describe success through measurable criteria: be fast, minimize errors, use fewer resources, produce a certain format, reach a quality score, or complete a list of steps. Those criteria are useful, but they are usually not the actual goal. A high score matters because it is supposed to indicate that the AI is doing something useful. Efficiency matters because we want to achieve something without wasting resources. A specific layout matters because someone needs to use the result afterwards. If the proxy becomes more important than the purpose behind it, the AI can technically satisfy the instructions while missing what we actually wanted. So I started making the hierarchy explicit. THE WORKFLOW Before a substantial task, I explain four things: Step-by-step: 1. The real goal What am I ultimately trying to accomplish? 2. Why that goal matters What function should the result serve in the real world? 3. The success criteria What signals, scores, constraints or output requirements help us judge whether we are getting there? 4. The important distinction Those criteria are indicators of success, not the goal themselves. Then, before execution, I usually ask for a short non-technical plan in plain language. Not code. Not internal terminology. Not a wall of implementation detail. I want the AI to explain: - what it thinks I am trying to achieve - what steps it plans to take - in what order - what it expects each step to accomplish - where it sees possible problems or ambiguity - what the final result should look like - where it will show me intermediate results before continuing That last point matters. For larger tasks, I do not want one giant jump from instruction to finished output. I want the AI to build in intermediate checkpoints with actual results. That can mean: - showing the first batch before processing the rest - giving a sample classification before applying it to hundreds of items - sharing an early pattern it found before building the full analysis around it - showing the structure of a document before filling every section - reporting that a planned step produced an unexpected result before silently adapting everything downstream The checkpoint should contain something useful enough to evaluate. Not just: «Step 2 completed.» But rather: «I processed the first 50 items. Most fit the categories we expected, but 12% fall into a pattern we did not account for. Here are three examples and how I suggest handling them.» That lets me see whether the task is still heading toward the actual goal. For example, my instruction might be: «The real goal is X. We care about Y because it helps achieve X. Z is a useful metric, but do not optimize Z at the expense of X. Before executing, explain in non-technical language how you plan to approach the task, step by step. Build useful intermediate results into the plan so I can inspect the direction before too much work depends on it. Flag anything that seems likely to satisfy the metric while undermining the actual purpose.» I can then say: «Yes, that is what I mean.» Or: «No, step 3 is where you are misunderstanding me.» And later: «This first batch looks right. Continue.» Or: «Stop here. The pattern you found changes how I want the rest handled.» Correcting a five-line plan or an early sample is much cheaper than correcting an entire finished workflow, analysis or file operation. WHY I LIKE IT This turns the interaction from: instruction → execution → correction into: purpose → shared understanding → visible plan → intermediate results → adjustment → execution It also helps me learn how the AI works. I do not need to understand every technical mechanism underneath it, but I do want a usable mental model of how it approaches problems. Over time, that makes collaboration easier because I get better at giving instructions, spotting misunderstandings early and knowing where extra context will matter. Intermediate results also make autonomy safer. The AI does not need permission for every tiny action, but it should avoid disappearing into a long chain of dependent decisions when an early misunderstanding could invalidate everything that follows. This can reduce unnecessary work, wasted compute and repeated corrections. The AI can still work independently once the direction is clear. The point is not to micromanage the process. The point is to make sure we are optimizing the right thing, travelling by a route we both understand, and checking occasionally that we are still on that route. A metric is a thermometer. The goal is to make the room warm, not merely to make the thermometer say 21°C.

I’m behind and self taught when it comes to prompt engineering and would like some guidance. I use terms like “exact replica” of image, “do not alter features”

Most businesses don't need another AI tool. They need to automate the repetitive bottleneck already slowing the team down. A simple example is connecting the tools already in use: Lead → AI qualification → CRM → WhatsApp → follow-up Instead of adding more software, automate the repetitive steps between these tools. The goal isn't more AI; it's less manual work and faster execution. Step-by-step: 1. Identify the repetitive bottleneck slowing the team down. 2. Capture the lead and use AI to qualify it. 3. Send the qualified lead to the CRM. 4. Use WhatsApp for follow-up. 5. Connect the steps so the process requires less manual work and supports faster execution.

I love reading, but I’m indecisive about what to read next. Lately, I’ve been getting recommendations from ChatGPT, which has led me to keep adding books to my to-read list instead of tackling the books that have been there for years. At the same time, searching through my 200 existing TBR books on Goodreads for one that matches my precise mood would be too time-consuming. To solve this, I exported all the books from my Goodreads bookshelf as a CSV file, uploaded it to ChatGPT, and asked it to recommend books from my “to-read” list that matched a description of what I was currently in the mood to read. For example, I asked it to recommend a book from my TBR list that was published in the 19th or 20th century and featured a strong, unforgettable heroine. It gave me a few options, and I decided to read *O Pioneers!* by Willa Cather next. One note: ChatGPT summarizes the plots of the books it recommends, so I suggest adding “no spoilers, please” to your prompt. Step-by-step: 1. I exported all the books from my Goodreads bookshelf as a CSV file. 2. I uploaded the CSV file to ChatGPT. 3. I described the kind of book I was currently in the mood to read, including publication period and character preferences. 4. I asked ChatGPT to recommend books only from my existing Goodreads “to-read” list. 5. I added “no spoilers, please” to prevent plot summaries from revealing too much. 6. I chose *O Pioneers!* by Willa Cather from the recommendations.

I used ChatGPT to help me manage my health care. I have multiple diagnoses, including CHF, CKD, pulmonary hypertension, lupus, a metabolic disorder, and kidney cancer. I gave ChatGPT access to my medical history and began using it to review my test results and prioritize questions for my doctors. On a recent lab report, my platelet count was low. ChatGPT reviewed six years of results and showed me that it had consistently been low, with the latest result below the threshold. It helps me identify which questions to ask and which of my six doctors I should address about each report. This has transformed the way I’m able to manage my care. Step-by-step: 1. I gave ChatGPT access to my medical history. 2. I used it to review my test results and prioritize questions about my health. 3. I asked it to look at a recent lab report showing a low platelet count. 4. ChatGPT reviewed six years of results and showed that my platelet count had consistently been low, with the latest result below the threshold. 5. I used the information to identify which questions to ask and which of my six doctors to contact about the report.

Clean up near-duplicate artwork photos with a visual checklist THE PROBLEM I had hundreds of photos of my handmade collages. Some showed the same work photographed at different times, from different angles or against different backgrounds. Others were cropped versions, detail shots or useful making-of photos. The duplicate finder in my image manager missed real matches and suggested unrelated collages instead. Simply keeping one file from each group would also have thrown away useful material. THE WORKFLOW 1. Export a working set and preserve the filenames. I exported the images from Eagle. Smaller copies made the collection easier to upload, while the original-resolution files stayed on my computer. Keeping the filenames intact made it possible to apply decisions to the originals later. 2. Ask AI to compare the artwork, not just the whole photograph. The comparison looked for matching local image details and their relative positions. This helped connect photos despite changes in angle and background. Candidate groups still needed review: two collages might contain the same clipping, and a detail photo might overlap with a wider shot without being redundant. 3. Turn the results into a visual decision page. The AI produced a standalone HTML file with photos grouped side by side and their original filenames underneath. I requested a “Keep” checkbox beneath each candidate and a category dropdown: “Collage” or “Making of”. Multiple images could stay in either category. One photo might show one part clearly while another preserved a different part better. I made the decisions; the AI did not choose a winner automatically. 4. Validate and export my choices. The page flagged any group with nothing selected and any selected photo without a category. Photos without a confirmed match were preserved separately. A download button exported my decisions as a small JSON file, which I sent back to the AI. 5. Generate a local cleanup script from that exact selection. The resulting Windows script checks the expected files, asks me to confirm the folder, sorts the retained photos into “collages”, “making of” and “loose items”, and sends rejected photos to the Recycle Bin. It targets the ordinary export folder, not Eagle’s internal library. The loose items can then be sorted manually before reimporting. WHAT THIS PRODUCED From 296 photos, the review grouped 204 into 90 candidate groups and left 92 without a confirmed match. My final choices retained 96 collage photos and 23 making-of photos, plus all 92 loose items: 211 retained, 85 designated for removal. The checklist and selection were completed, and the script was generated. At the time of writing, I had not yet run the cleanup on Windows. WHY IT HELPED The key was separating three jobs: finding likely matches, deciding what matters, and applying those decisions to files. “The same artwork” does not necessarily mean “an unnecessary photo”. A visual checklist let me make those distinctions without manually tracking filenames. STARTER PROMPT “I have photos of the same artwork taken from different angles and against different backgrounds. Find candidate matches using details within the artwork, and distinguish duplicates from details, changed versions and making-of photos. Create a standalone HTML review page with original filenames, a Keep checkbox and a category dropdown for each candidate. Allow multiple retained photos per category. Flag empty groups and selected photos with no category. Preserve unmatched images. Let me export my choices as JSON. After I return the selection, generate a script that validates the original filenames, sorts retained files into the chosen folders and moves only rejected files to the Recycle Bin after showing the target folder and counts. Do not choose or delete files on my behalf."

I tried using Claude and it lost context of the whole project quickly and became a nightmare of human in the loop meat proxying. It made the exercise far from autonomous.

I'm a British Academy (BAFTA) voting member. Every autumn, the members' screener platform fills up with more than 100 eligible films—major contenders, obscure documentaries, and hidden gems all mixed together. I have a few weeks to decide what deserves my viewing time before I vote. The fun challenge is finding the sleeper nobody has heard of yet; the problem is the sheer volume of clutter I have to sift through. I built a workflow in Claude Cowork that turns the overwhelming list into an ongoing conversation with a curator that knows my taste. I started by inputting my film notes from previous years: what I watched each season, what I loved, what I abandoned, and why. Claude stores this in persistent memory alongside a growing profile of my taste, including my go-to critic, my low tolerance for slow cinema, the kinds of films that reward me, and my rule that a film gets minutes—not acts—to earn my time. Every session starts with this context already loaded. When a new batch of films drops, Claude opens the screener platform in its built-in browser, reads the full slate, and sends research agents to cover every title in parallel. They research the director, cast, runtime, Rotten Tomatoes scores, festival prizes, awards buzz, and whether my favourite critic has reviewed each film. Claude even pulls the transcripts of his YouTube reviews and summarises the verdict. In about 20 minutes, a 37-film batch is triaged into three categories: priority viewing, worth sampling, and skips. Slow starters are flagged so I know which films need a committed evening and which get 10 minutes to prove themselves. As I watch, I feed verdicts back in plain English, such as “gave it ten minutes, too abstract.” Claude updates both the tracker and its model of my taste, so each recommendation round becomes sharper. By voting time, I have a complete, searchable record of everything I watched and what I thought of it, built conversationally throughout the season. Step-by-step: 1. I input my film notes from previous years—everything I watched, loved, and abandoned, along with my reasons. Claude saves them to persistent memory, which every future session loads automatically, and builds a profile of my taste from them. 2. When new films appear on the members' platform, Claude opens it in its built-in browser and reads the full list of titles. 3. Claude launches parallel research agents to cover every title, including the cast, crew, runtime, Rotten Tomatoes scores, festival prizes, awards buzz, and my preferred critic's verdict from YouTube review transcripts. 4. Claude compiles a triage tracker that ranks every film by viewing priority, flags likely sleepers, and warns me about slow starters. 5. As I sample films, I report quick verdicts in plain English. Claude logs them and continuously refines its profile of my taste, so recommendations improve throughout the season. 6. At voting time, I have a complete record of what I watched, what I thought, and why, built conversationally across the season.

I’m a nurse with no tech experience, but I’m curious and have many creative ideas. I used Claude to build a website that helps people plan which vegetables to grow based on their location, available space, and the time they have. Veggiegrowguide.com Step-by-step: 1. I identified an idea for helping people choose vegetables to grow based on their location, available space, and available time. 2. I used Claude to help me build a website for the idea. 3. I created Veggiegrowguide.com as a resource for people planning their vegetable gardens.

My mom and I love trying new recipes together, but our best dishes rarely turn out exactly like the original recipe. She adds a little more garlic, I suggest a different spice, and by the time we sit down to eat, neither of us remembers what we changed. 😂 I started using ChatGPT as our cooking journal. After we make something, I send it a photo of the dish and a quick voice note about what we used, what we changed, and what we’d do differently next time. ChatGPT turns those notes into a recipe we can make again while preserving our comments and the story behind the meal. Now, when we’re deciding what to cook, I can ask for a favorite we haven’t made in a while, a recipe that uses what’s in the fridge, or a shopping list for our next cooking day. It’s becoming a collection of our recipes and the time we’ve spent making them together. ❤️ Step-by-step: 1. I created one place to keep our recipes, with space for ingredients, steps, photos, ratings, and notes. 2. Each time my mom and I cook, I take a photo and record a short voice note about the changes we made. 3. I ask ChatGPT to turn our notes into a clear recipe and flag any measurements we forgot to record. 4. I review the recipe with my mom, fill in the missing details, and save the version we actually made. 5. We add what we liked, what we’d change, and any memories from that cooking day. 6. When we want to cook again, I ask ChatGPT to find a recipe, adapt it to the ingredients we have, or make a shopping list.

I have tried many AI Tools however - I feel the time I Input data and effort into schedulign and resourcing is the problem - I need a Fix or a rubust reliable AI workflow so i can buy my time back. Any suggestions?

Turn scattered creative preferences into four living style books THE PROBLEM My taste was scattered across old conversations, clothing lists, search terms, saved images, handmade collages and experiments transforming my childhood drawings with AI. I wanted something I could use to make new work, rather than another archive of everything I had ever mentioned. A generic label like “colourful and whimsical” was not enough. My preferences also change with the application: a collage, an outfit, a room and a digital course do not need the same treatment. THE WORKFLOW 1. Bring together different kinds of source material. I used an earlier style conversation, a digital design style document, a list of search terms, photos of my own collages and the corrections I had made during image-generation experiments. Ask AI to read source texts fully, and distinguish your statements from suggestions made by an earlier assistant. 2. Analyse patterns, then correct the interpretation. The AI proposed connections involving colour, texture, shape, atmosphere, vintage objects and visual storytelling. I refined these through concrete examples. For instance, liking stilettos and being able to wear them comfortably are separate facts. Liking geometric structures does not mean I want triangular wallpaper. A technically imperfect image can still work when it preserves the atmosphere I intended. 3. Treat corrections as part of the research. “Too childish” may mean wrong for this drawing’s intended audience, rather than a universal dislike. A saved image may be intriguing without being something I want to keep encountering. An entire family of similar images may appeal to me without needing to rank every member. One especially useful correction: patterns visible in my collages do not prove I consciously planned them. I sort clippings into categories and sometimes colour groups; the collage itself develops while I make it. 4. Include my own categories. My clipping categories include texture, image, black-and-white, colour, background, small meaningful items, comics and words. “Colour” means a clipping kept mainly for its colour, not simply any colour photograph. “Texture” includes both natural surfaces and designed patterns. These definitions provided better starting points than generic categories imposed by the AI. Digital design and graphics also received a full category of their own, rather than being treated as an exception to my taste elsewhere. 5. Create four distinct outputs. • Style Book: precise preferences, boundaries, exceptions and provisional design principles. • Visual Atlas: image families connected across subjects, with actual examples and explanations of what might link them. • Prompt Bible: modular language for colour, material, light, composition, figures and atmosphere, plus reusable recipes and lessons from corrections. • Curatorial Map: connections between interests such as vintage objects, memory, surfaces, small living worlds, language and digital design. 6. Keep the books open to revision. Separate confirmed preferences, observations and hypotheses. When new material arrives, ask what it confirms, refines or contradicts. Add what changes the understanding instead of documenting every conversation. WHAT THIS PRODUCED Four separate first-draft HTML books, including a visual atlas with 14 photographs of my collages. They bring clothing, interiors, fragrance, digital design and creative work into the same research project while preserving their different requirements. WHY IT HELPED The process made my corrections useful. Instead of asking AI to define my taste once, I could respond to concrete interpretations until the descriptions became more accurate. The books support future making without prescribing how I must create. STARTER PROMPT “Use these sources to draft four separate living documents: a personal Style Book, a Visual Atlas, a modular Prompt Bible and a Curatorial Map of Fascinations. Read the source texts fully and distinguish my own statements from earlier AI suggestions. Find recurring patterns, exceptions and unexpected connections. Keep preferences specific to their application, including clothing, interiors, digital design and graphics. Treat my corrections as evidence. Label observations and hypotheses clearly, and do not invent conscious intentions behind intuitive work. Use supplied images in the atlas where available. Build useful first drafts rather than a complete archive, and translate each finding differently for each document’s purpose.”

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 record calls with Granola and paste the transcript into Claude, but the action items it pulls are hit or miss. Sometimes it skips things that were clearly decided and sometimes it invents owners. I tried asking for a table with owner and due date but it still guessed. Looking for a prompt or workflow that's reliable enough I can trust it without rereading the whole transcript.

What do you do when your wife says you talk about AI too much? You listen to her, and when she has a problem, you frantically write it down and build it with AI. My wife enjoys working with her plants in the warm sun and light breeze of the Carolina mountains. She’s new to gardening and learning more each day, but she was having trouble keeping track of everything. Which tree did she plant in the front yard last year? It seemed to be struggling—would it do better somewhere else? And would rain reach the potted flowering planters while we were out of town, or would she need to find someone to help? I used Claude Code and Fable to develop an app that my wife could run on her phone, with all the data stored locally. Now she’s excited about “her app” and the things she can add to it. She has even shared it with others, including people across the country, so we added climate zone settings to make it useful in other parts of the country. 😂 Step-by-step: 1. I listened to my wife’s gardening challenges and wrote down the problems she wanted to solve. 2. I used Claude Code and Fable to develop a gardening app for her phone. 3. I designed the app to keep all the data stored locally. 4. I built in a way to track plants, including which tree was planted in the front yard and how it was doing. 5. I accounted for questions about rain and the care of potted flowering planters while we were out of town. 6. After my wife shared the app with people across the country, I added climate zone settings so it could be useful in other regions.

I built a local memory system for Claude that is a bit different from others I have seen. The reason was familiar: repeated context loss and gaps, even within projects. I am not technical—I come from a healthcare background—so it was essentially vibe-coded, but I used a method I had not seen elsewhere. I started by interviewing Claude about what would be useful to it, rather than beginning with only what I wanted. The three biggest gaps were the rationale behind decisions, current versus historical states, and the difference between global and project-level detail. We also identified ways memory can go wrong, including stale facts being confidently asserted as truth and rejected ideas resurfacing. Claude’s built-in memory stores flat topics without entity links, captures what but not why, is not well temporally grounded, and is gated by Claude. I researched other memory builds, from homebrew systems to enterprise tools, and found that they generally fell into three groups: - Vector dumps, which lack rationale and supersession and can become stale - Plain Markdown with grep or embeddings, such as Basic Memory, which similarly lacks real temporal grounding and an entity graph - Heavyweight knowledge-graph stacks such as Neo4j, LangChain, and GraphRAG None of these did what I wanted. My store holds entities only, not transcripts. It stores decisions, observations, people, and projects connected by typed edges. Each entry has content, a scope—either portfolio-worthy or working detail for one project—a rationale, and information about where it came from. The system is also bitemporal, so it distinguishes what is current from what is not. Nothing is edited in place: a correction adds a new assertion instead of overwriting the old one. Underneath, it uses SQLite, with sqlite-vec for semantic search and FTS5 for keyword search. Nothing writes automatically. Claude has to propose a memory, and I have to approve it. This prevents the store from filling with noise, keeps it token-efficient, and acts as a governance lever. MCP links Claude to my server. It is local-only at present, although there is potential to add remote access in the future. The server provides instructions for making proposals, so the system is theoretically portable, and I also created a Claude skill to accompany it. I ran the build across multiple projects and created specialist projects for different roles: - A central development and oversight project served as the decision-maker and prompt-writer. - Cowork handled the building and tested each module inside a sandbox. It had no authority to change decisions, and I used a fresh project for each stage of the build. - I handled deployment separately by typing every command on the server and pasting the output back. - I repeated Claude’s Cowork-authored tests on the actual server. Real-world testing after deployment identified only minor issues, which were quick to fix. This separation was administratively heavy because I had to keep switching between projects as tasks started and finished, but it caught several errors in the rules and code. Despite my lack of technical knowledge, the project is now well documented and I have room to develop it further. I may eventually put it on GitHub. It has become a standard component of my workflows, my projects are tracked much better, and Claude and I are on the same page more often.

I built a daily AI story-scouting workflow that finds potentially viral stories for Instagram Reels, YouTube Shorts, and TikTok without recycling topics we’ve already covered. First, the workflow reviewed Rowan’s public short-form archive once to create a coverage map of past topics and editorial taste. It uses that map as a filter, helping distinguish a genuinely new angle from another version of the same AI launch, robot demo, or research story. Every morning, it scans priority sources, including AI and technology coverage from major newspapers and tech blogs, The Rundown newsletters, company announcements, research papers, and public updates from major AI and robotics companies. The workflow is not limited to same-day news. It also looks back over the past one to six weeks for stories that have not been extensively covered in the media. Each potential story is checked for four things: a clear visual hook, a technical idea that can be explained in 45–90 seconds, broad audience interest, and meaningful novelty compared with Rowan’s past coverage and the previous week’s recommendations. It keeps every story that clears the bar rather than forcing a fixed number. The final brief is ranked by strength and sent as one compact Slack DM at 10 AM each day. Step-by-step: 1. The workflow reviews Rowan’s public short-form archive once and builds a map of past topics and editorial taste. 2. Each morning, it scans priority sources, including major newspapers, tech blogs, The Rundown newsletters, company announcements, research papers, and public updates from major AI and robotics companies. 3. It searches both same-day news and stories from the previous one to six weeks that have not been extensively covered in the media. 4. It filters out topics that substantially repeat Rowan’s past coverage or the previous week’s recommendations, while identifying genuinely new angles. 5. It evaluates each potential story for a clear visual hook, a technical idea explainable in 45–90 seconds, broad audience interest, and meaningful novelty. 6. It keeps every story that meets those criteria instead of forcing a fixed number of recommendations. 7. It ranks the final brief by strength and sends it as one compact Slack DM at 10 AM each day.