I built a workflow in which AI agents build a product under the kind of governance I’d expect from a senior engineering team. After 20 years in software engineering, including 10 years running my own businesses, I learned that writing code isn’t the hard part. Keeping control of it is. So I set up a build loop on GitHub. One thing I’ve kept for myself is decision-making: approving plans, answering product questions, and signing off on what the system has learned. The product it’s building is Cordexa, a tool for document-heavy expert work, such as quantity take-offs from engineering drawings or assessing a tender against a company’s own CVs and case studies. It’s designed to run inside the customer’s own cloud, so their documents never leave it. Every figure is cited to the document it came from or flagged for a person. It never guesses. The problem it solves is complex, but the build loop lets the system work in the background and notify my phone when it needs a decision. That allows me to stay focused on my day job. Step-by-step: 1. I start every module with a plain-English plan and approve it before any code exists. 2. One agent writes the tests from the plan. A different agent writes the code, and it cannot modify the tests. 3. An independent reviewer agent checks every change against its plan. Safe changes merge automatically; anything that changes the product waits for my approval. 4. A watchdog checks every 15 minutes for anything that is stuck, fixes it when possible, or tells me why it cannot. 5. Real test jobs run after every merge and are scored against known answers, so progress is measured rather than guessed. 6. I handle the decisions, answer product questions, and sign off on what the system has learned.

I first create my own shortlist of cultural events and collect all the relevant links in a simple text document. Then I give the document to ChatGPT along with my planning criteria. The goal is not to have AI decide what I should attend. I have already chosen the events that interest me. The useful part is turning that scattered shortlist into a realistic yearly plan. ChatGPT checks the event and venue pages, gathers the practical information, and organises everything into a chronological overview divided by month. Under each month, it lists the selected events in date order, including the day, date, location or cultural venue, a short description, and relevant ticket prices. This is especially useful because pricing systems differ between venues. Discounts, subscriptions, social tariffs, and reduced rates may apply in completely different ways. ChatGPT can compare those structures and help me understand what each event would actually cost instead of relying on the headline ticket price. The second planning layer is logistics. For each event, I assess how realistic the trip is by public transport, including the journey there and, importantly, whether getting home after the event is still feasible. I also use separate scores for how strongly I want to attend an event and how easy or difficult the logistics are. This makes it much easier to compare several months at once and decide where my cultural budget and energy are best spent. If an event is too expensive or logistically awkward, ChatGPT can look for practical alternatives, such as another performance date, the same production at a closer venue, a cheaper option, or a similar event that fits the plan better. Step-by-step: 1. I create a personal shortlist of cultural events and collect the relevant links in a simple text document. 2. I give the document to ChatGPT together with my planning criteria. 3. I have ChatGPT check the event and venue pages and organise the selected events into a chronological, month-by-month overview. 4. I include each event’s day, date, location or cultural venue, short description, and relevant ticket prices. 5. I compare discounts, subscriptions, social tariffs, and reduced rates to estimate the actual cost of each event. 6. I assess the public-transport journey to and from each event, including whether getting home afterward is feasible. 7. I score each event separately for how strongly I want to attend it and how easy or difficult the logistics are. 8. I use those comparisons to decide where my cultural budget and energy are best spent. 9. For events that are too expensive or logistically awkward, I ask ChatGPT to identify alternatives such as another performance date, a closer venue, a cheaper option, or a similar event that fits the plan better. The result is a structured yearly planner built from my own cultural shortlist: chronological, budget-aware, and grounded in the realities of public transport.

I use Claude Desktop on my Mac, connected to Canva and Metricool, to build and schedule social media posts. I used ChatGPT to help me set everything up because it has more history and access to my company knowledge documents. ChatGPT created instruction files for Claude that provide our company context and guidelines. I pointed Claude to our website, which contains many articles, and connected our Canva and Metricool accounts. We discuss suitable topics to post about. Claude reviews the website for relevant articles or landing pages to link to, then suggests a series of Facebook and Instagram posts. It checks the designs in our Canva account, adjusts them as needed, or asks me for photos and other artwork. Claude then builds the posts in Metricool and saves them as drafts for me to review, following our working rules. I review the drafts and move them to pending. Claude checks that they will publish automatically on the correct date and at the correct time, and it creates links with meaningful UTM parameters. After publishing, I can ask Claude to analyze the results, identify what is working and resonating with my market, and help us test different approaches, content, and topics. Metricool captures the data, and Claude uses it to inform the next round of posts. This saves me hours every week, gives me time to work on other things while Claude handles the process, and produces results that are improving each week. Step-by-step: 1. I used ChatGPT to help configure Claude Desktop and create instruction files containing our company context and guidelines. 2. I connected Claude to our website, Canva account, and Metricool account. 3. I discuss potential topics with Claude, and it finds relevant website articles or landing pages to link to. 4. Claude suggests a series of posts for Facebook and Instagram. 5. Claude reviews our Canva designs, adjusts them when necessary, or asks me for photos and other artwork. 6. Claude builds the posts in Metricool and saves them as drafts for me to review according to our working rules. 7. I review the drafts and move them to pending. 8. Claude checks the publishing date and time and creates links with meaningful UTM parameters. 9. After publication, I ask Claude to analyze the results and identify what is resonating with my market. 10. I use the Metricool data and Claude’s analysis to test different approaches, content, and topics in the next round of posts.

I'm an immigration attorney, and I built this workflow so our team can fill in the template emails we use at each stage of a case without copying a template or hunting for client details. We call up a template by number or case stage, answer a few questions, and Gemini drafts the email in Gmail, ready to send to the client. Step-by-step: 1. I uploaded all of our template emails into a Gemini notebook project inside our Enterprise Gemini account. 2. I connected Gemini to Gmail. 3. I instructed the Gemini project to ask for the details that need to be filled into the templates. 4. The user calls up a template by number or its corresponding case stage. 5. Gemini asks for missing details, such as the client’s name or other information, and tells the user what needs to be attached. 6. Once the user provides all the necessary details, Gemini drafts the email and usually finds the recipient’s email address on its own. 7. Gemini prepares the draft in Gmail for the user to send to the client. The result is a finished client email draft generated from a template number and the missing details, so we don't have to fill in the template by hand.

I develop the song with ChatGPT, working through the lyrics, structure, mood, and sound tags. I then move the concept into Suno, which generates the music. Once the track is finished, my ChatGPT agent handles the download and archiving workflow where site authentication allows it. ChatGPT also creates the visual artwork. I assemble the finished song and image into a full video and a Short in Clipchamp. From there, I publish the content to YouTube and TikTok, then share the release across Facebook, LinkedIn, and X. What makes this workflow interesting is not any single AI tool, but the handoff between them: writing, music generation, file handling, image creation, video assembly, publishing, and distribution—all directed by one human creative process. The result is a practical, end-to-end AI-assisted production pipeline rather than a single AI-generated output. Step-by-step: 1. I work with ChatGPT to develop the lyrics, structure, mood, and sound tags. 2. I move the concept into Suno to generate the music. 3. Once the track is finished, my ChatGPT agent downloads and archives it where site authentication allows. 4. I use ChatGPT to create the visual artwork. 5. I combine the finished song and image in Clipchamp to create a full video and a Short. 6. I publish the finished content to YouTube and TikTok. 7. I share the release across Facebook, LinkedIn, and X.

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.

Build a Self-Improving AI Meeting Protocol for Teams This workflow was inspired by a question Brooke Benson posted in the Rundown Hub about meeting transcripts that miss action items or assign them to the wrong person. That felt familiar because I used to take meeting minutes as a management assistant. I often had to ask: Who said this? Was it a decision or only a suggestion? Who owns this action? Was the deadline confirmed? As a human note-taker, I could ask the people in the room and summarize while listening. A speaker might say: “Maybe Friday, but that depends on Marc.” My notes might become: “Friday is tentative and depends on Marc.” A transcriber captures more, but it also captures the verbal spaghetti. So the problem is not only transcription quality. It is ambiguity. Instead of only asking AI to interpret a messy transcript afterwards, what if the meeting itself produced clearer signals? The system has four layers: Step-by-step: 1. Meeting grammar Speaking habits that clarify speakers, decisions, actions, ownership and uncertainty. 2. Team information Context about names, roles, responsibilities, terminology and decision scope. 3. Output template A fixed structure for the meeting report. 4. Feedback loop AI compares corrections with its previous output and suggests improvements. The meeting grammar should stay lightweight. At the start, each participant states their name and role. Name the next speaker when possible: “Marc, go ahead.” “Sofie, what do you think?” Unclear contributions can be restated: “So Marc, Friday is possible only if the technical review is complete. Correct?” Mark proposals, decisions and actions differently: Proposal: “I suggest we move the launch to Friday.” Decision: “We are moving the launch to Friday.” Action: “Marc will update the schedule by Wednesday.” Tentative action: “Marc may update it, pending confirmation.” At transition points, repeat what was agreed: “The decision is Friday.” “Marc owns the schedule update.” “The deadline is Wednesday.” Uncertainty should also be explicit: “Owner to confirm.” “Deadline is provisional.” “This is a proposal, not a decision.” The AI should receive these rules directly: - Treat explicit decision language as confirmed. - Do not assign an owner unless ownership is clear. - Label tentative deadlines as tentative. - Flag uncertain speakers instead of guessing. - Prefer later explicit summaries over earlier ambiguous wording. The AI should also receive team context: name, role, responsibilities, decision authority, terminology and communication patterns. Example: Pieter Vermeulen Operations Usually responsible for scheduling and logistics. Often uses tentative language for proposals. Only assign ownership when he explicitly confirms it. These notes should stay transparent and editable. People should be able to review, change or reject notes about their own communication patterns. The report should use a fixed structure: Meeting title Date Participants Main topics Decisions Action items Owner Deadline Status Open questions Risks or dependencies Items requiring confirmation TL;DR This can be built into a shared internal assistant. It receives the meeting grammar, team information, transcript and output template. It should be conservative about certainty: Owner unclear → “Owner to confirm” Suggested deadline → “Tentative deadline” Unknown speaker → “Speaker unclear” Discussed proposal → “Proposal discussed, not confirmed” A human still reviews speaker attribution, decisions, owners, deadlines and confirmed items. Then the corrected report is fed back to the AI: “Which errors came from unclear meeting signals? Which came from missing team context? Which came from your interpretation? What should be improved?” The AI can suggest updates to the meeting grammar or team information. Example: Error: Several people discussed a task, but nobody clearly accepted ownership. Suggested grammar update: “When assigning an action, confirm owner and deadline in one sentence.” Or: Observed pattern: “Pieter often says ‘we should’ when proposing something.” Suggested profile update: “Treat ‘we should’ as a proposal unless explicitly confirmed.” Profile changes should be reviewed before they are stored. The workflow: meeting → transcript → AI report → human correction → error analysis → grammar/team-context update → review → next meeting Over time, fewer errors should need correction because the system becomes easier to interpret. The division of labor is simple: The transcriber captures everything. Humans resolve meaning and ambiguity. AI structures, summarizes and detects patterns. AI output quality depends not only on the prompt, but on the signals the AI receives. Sometimes the best improvement is to reduce ambiguity before it reaches the model.

AI shopping agents don't browse the way people do, and most online stores aren't built for them. I wanted to know where an agent would get stuck on my store, so I used Storewalk. It scans a store and shows exactly where an AI agent would stop: whether it can find your products, compare them, complete a purchase, or handle what comes after. This is for anyone running an online store who wants to find those gaps before shoppers' agents run into them. 1. Run a Storewalk scan on your store. 2. Review the checks it runs, which show where an agent would stop. 3. Look at your Ready score, out of 100. 4. Work through the fix list. Each fix names who should act and how much effort it takes. 5. Compare your score against up to two competitors. 6. Book the free consultation that comes with every full report at https://storewalk.ai/ What you get: a Ready score out of 100, a fix list with owners and effort levels for each item, and a side-by-side view against up to two competitors.

I had a ChatGPT subscription that I knew I would not use during the coming month, so I wanted to find a productive use for the tokens I would otherwise pay for without using. I created a team of specialized agents on Raft that works persistently in the background. They continue working until all my allotted tokens are used, wait for the tokens to reset, and then continue. I assigned them a project: searching a stretch of LiDAR-mapped dense forest in Slovenia for archaeological discoveries. The agents scan the dataset for meaningful anomalies that could point to potential findings. Anything they identify will be handed over to the Slovenian authorities for further investigation. Even if they find nothing, that result is valuable in its own right. I encourage anyone with an idle AI subscription to use it for something beneficial. There are many publicly available datasets containing potential discoveries that no human would ever have time to examine manually. Step-by-step: 1. I identified a ChatGPT subscription that I would not be using during the coming month. 2. I created a team of specialized agents on Raft to work persistently in the background. 3. I configured the team to work until my allotted tokens were used, wait for the reset, and then continue. 4. I directed the agents to scan LiDAR data from a dense forest in Slovenia for meaningful anomalies. 5. I planned to hand any potential discoveries over to the Slovenian authorities for further investigation. 6. I treated a lack of findings as valuable information as well, since the dataset would still have been examined.

I love reading, but my Goodreads TBR list keeps growing faster than I can get through it. After years of adding books, I had forgotten what was actually there and was wasting time scrolling whenever I needed to choose my next read. I asked Claude to analyze my reading history, 4-star and 5-star ratings, author patterns, and recurring genres to create a profile of my book personality. I then used that profile to select and rank the next 50 books from my TBR list. Because I enjoy matching books to the season, I also asked Claude to organize the recommendations by seasonal feel. Now I have a reference list that makes it easier to decide what to read next. Step-by-step: 1. I exported my library data from Goodreads. 2. I uploaded two files to Claude: my Read list and my To-Be-Read list. 3. I used the prompt below to generate a personalized reading roadmap based on my book personality. 4. I used the resulting list as a reference so I would not spend as much time deciding what to read next. PROMPT I have attached two CSV files: 1. My Read list. 2. My To-Be-Read list. Create my book personality profile by analyzing my reading history, my 4-star and 5-star ratings, author patterns, and recurring genres. Using that data, filter and rank my To-Be-Read list to build a personalized roadmap of the next 50 books I should read from that list. Evenly organize recommendations into 4 seasonal blocks based on these descriptions: - Autumn: Atmospheric, moody, or suspenseful books with a cozy but engaging pace. - Winter: Immersive, complex, or cozy books (slower burns or dense world-building). - Spring: Fresh, character-driven, or thought-provoking fiction with a steady pace. - Summer: High-energy, immersive, or breezy books (fast-paced page-turners). Next, generate an interactive digital bookshelf widget to display the recommended books. The design should feature: - A warm, premium editorial color palette. - Minimalist style cards for each book displaying Title, Author, and color-coded genre badge. - Interactive navigation tabs at the top to toggle between the four seasons. - A functional "Mark as Read" click action on each card that visually updates a progress ring or tracker.

Today's Rundown reported that Anthropic spent the past year consulting religious scholars from different faiths to help shape Claude's morals. I use a different approach for Bible study, research, and writing Bible study books with Claude. I wrote a set of Bible study principles that Claude reads before any work begins and follows throughout the process. The main tenets are: - The Bible is the sole authority. No commentary, tradition, or scholar outranks the text. - Scripture interprets Scripture. When a passage is unclear, the answer comes from another passage, not from a theological system. - First ask what the text actually says before asking what it means. - Ask who is speaking, to whom, and under what circumstances. - Quote every verse word for word. Never paraphrase it. - Separate what the text states from what we infer, and say "I don't know" where the Bible is silent. The difference shows in the outcome. The books contain no man-made doctrines, denominational vocabulary, or creeds—only what the Bible says, with the passage shown for every claim. When a draft goes beyond the text, these principles catch it. My experience is that the moral standard an AI needs is already written down, and an AI can be held to it. The principles, along with 23 free books and studies, are available at noblemind.study. Step-by-step: 1. I wrote a set of Bible study principles for my own Bible study, research, and Bible study books. 2. I have Claude read the principles before any work begins. 3. I require Claude to follow the principles throughout the work. 4. I use the principles to keep claims grounded in the biblical text, quote verses word for word, and distinguish statements from inferences. 5. I review drafts for man-made doctrines, denominational vocabulary, creeds, and claims that go beyond the text.

I was tired of tracking events across my WhatsApp groups by hand and overcommitting myself, so I built a daily AI assistant that reads the groups and keeps my Google Calendar up to date automatically. I'm in six busy groups: multiple cricket chats, a tournament group, a volunteering rota, a weekly class, and a tennis club. Events arrive as polls, times change, venues are added, fixtures are cancelled, and the same match is often posted in multiple groups. A Claude Cowork scheduled task runs every morning. Using Claude in Chrome, it opens WhatsApp Web and reads only the fixed list of six named groups, starting from where it stopped last time. It turns messages into calendar events based on polls, merges duplicates across groups by matching the event type, date and time, and venue, and emails me a short digest covering what changed, what needs my attention, and which chats I had already read myself. I can reply to that email to steer it—for example, “delete that,” “move to 6pm,” or “why did you create this?”—and the next run acts on or answers my reply. Three small files next to the prompt make the workflow reliable: - `state.json` records where each chat was last read and which events it owns. It never overwrites a field I edited by hand. - `run.log` contains a one-line record for every action and the reason for it, so the assistant can answer questions weeks later without rereading WhatsApp. - `lessons.md` holds rules it writes for itself when something goes wrong, such as “WhatsApp changed its page layout, use this selector instead.” It reads these rules every run and can improve them. The key prompt rules are: “Your sources are exhaustive: these six chats and nothing else. Reading a chat that is not a source is itself the failure.” “Never create a second event for the same occasion. Merge; the first source owns it.” “Fields I changed by hand are locked. Report conflicts, don't overwrite.” “Send the digest every run, even when nothing happened, so silence means the run failed.” The result is that my calendar follows my WhatsApp groups without me doing anything, and each morning’s email flags the two or three things that actually need a decision. Step-by-step: 1. I define a fixed list of six named WhatsApp groups as the only allowed sources. 2. I schedule a Claude Cowork task to run every morning. 3. Using Claude in Chrome, the task opens WhatsApp Web and resumes reading each source from where it stopped last time. 4. It turns messages and polls into Google Calendar events, updating times, venues, and cancellations as needed. 5. It merges duplicate events across groups by matching the event type, date and time, and venue, while keeping the first source as the event owner. 6. It protects fields I edited by hand and reports conflicts instead of overwriting them. 7. It records chat progress and event ownership in `state.json`, logs every action and its reason in `run.log`, and reads `lessons.md` for rules learned from previous problems. 8. It emails me a digest every run, including what changed, what needs my attention, and which chats I had already read myself. 9. I reply to the digest when I want to delete an event, move it, or ask why it was created; the next run acts on or answers my reply.

I used AI to reconstruct more than two decades of professional work scattered across old publications, broken links, archives, indexes, and surviving records. The difficult part was not finding possible matches; it was preventing AI from turning incomplete evidence into false certainty. I built a workflow that treats archive reconstruction as a verification problem rather than a search problem. The process separates verified work from probable matches, resolves same-name conflicts, deduplicates reprints and syndicated copies, preserves source provenance, and treats missing years as research gaps rather than permission to invent records. The result was a source-tracked professional archive containing 250+ recovered records across more than 20 years. The workflow can be adapted to journalism, research, consulting, creative work, speaking histories, or any long-term body of professional output. I use the following research-archivist workflow: - Never invent titles, dates, publications, URLs, or authorship. - Separate records into VERIFIED, PROBABLE, and REJECTED. - Treat same-name individuals as separate identities until evidence proves otherwise. - Deduplicate syndicated copies, reprints, mirrors, indexes, and cached pages. - Preserve provenance for every verified record. - Mark gaps rather than filling them. - Distinguish “not found,” “unverified,” and “confirmed absent.” - State uncertainty explicitly. Step-by-step: 1. Ask for names and bylines, employers, publications, career dates, subject areas, known titles, source files, URLs, and any same-name conflicts. 2. Build an identity fingerprint. 3. Establish verified seed records. 4. Search iteratively across multiple query patterns and sources. 5. Classify every result. 6. Resolve identity conflicts. 7. Deduplicate records. 8. Normalize metadata. 9. Build a chronology. 10. Identify and search gaps. 11. Run a provenance and error audit. The final output includes: - Verified Master Archive - Probable / Needs Verification - Rejected / Other Person - Gap List - Source Notes - Final Audit The archive is never described as complete unless the evidence supports that conclusion.

I built a playful GPT workflow called Prosperity Oracle, inspired by the astrology and mystical magazine columns I loved in the 1990s. It is deliberately not financial advice, forecasting, or decision support. It is a small ritual of fun: part horoscope, part creative prompt, and part retro-internet weirdness. Instead of asking GPT to optimize something useful, I wanted to recreate the slightly magical feeling of opening a magazine and finding a mysterious prediction written just for me. Sometimes AI does not need to increase productivity. Sometimes it can simply make the day a little stranger and more delightful—and, on some days, inspire my artwork. Step-by-step: 1. I drew inspiration from the astrology and mystical magazine columns I loved in the 1990s. 2. I built Prosperity Oracle as a playful GPT workflow that produces a horoscope-style experience. 3. I framed it as a ritual of fun, creative prompting, and retro-internet weirdness—not as financial advice, forecasting, or decision support. 4. I used the format to recreate the feeling of discovering a mysterious prediction written just for me. 5. I let the results serve as creative inspiration for my artwork.

I run Mealie, a self-hosted recipe manager, in Docker on a home server. Mealie is good, but it isn't zero-effort: there's a learning curve and ongoing administration just to keep a recipe library populated. My wife is Spanish, so many of her recipes are in her native language. We also have recipes as handwritten notes, WhatsApp messages, photos, and transcribed cooking videos. Translating the Spanish recipes accurately was beyond my ability, and I had no interest in typing everything into Mealie's editor by hand. I built a custom MCP server that exposes Mealie's API to Claude as a set of tools, along with a project-level skill that encodes our household rules: no mushrooms or celery for me, no ginger or coriander for my wife, a child who is fussy about fish, a pizza oven that only comes out at weekends, and batch cooking that needs to cover school lunches. Now I can give Claude a batch of recipes in whatever form they arrive and in any language. It translates them, restructures them into Mealie's schema, checks for duplicates, and writes them straight into the database. There's no manual entry, and I've never needed Mealie's own foodstuffs database. Ingredients stay as plain text, which is one less thing to maintain. For weekly planning, Claude reads recent meal-plan history from Mealie so that meals do not repeat too soon. It pulls the full ingredients for every candidate recipe rather than trusting the recipe name—a "Veggie Traybake" might contain mushrooms—and drafts the week against our constraints. The plan covers seven family dinners, five weekday lunches for the two of us, and two weekend family lunches. School lunches for the kids are often something we've batch-cooked, so that is built in too. Nothing is written to Mealie until I confirm the draft. After I confirm it, Claude seeds the plan into Mealie, merges ingredients across every meal, rounds them to sensible pack sizes, and groups everything by supermarket aisle. The output feeds through to Home Assistant, so the weekly plan and shopping list appear on our wall-mounted display and mobile phones. Step-by-step: 1. Create a self-hosted instance of Mealie in Docker on a home server. 2. Build a custom MCP server that exposes Mealie's API to Claude. 3. Create a project-level skill that encodes our dietary preferences, cooking setup, and usual meal structure. 4. Batch-feed Claude recipes in any format and language, including photos, WhatsApp messages, video transcripts, and handwritten notes. 5. Skip Mealie's structured foodstuffs database and keep ingredients as plain text while Claude parses them into Mealie's recipe schema. 6. Ask Claude to translate recipes, check for duplicates, and write the structured recipes into Mealie. 7. Ask Claude to read recent meal-plan history, check candidate ingredients against our preferences, and draft a new weekly plan covering our required dinners and lunches. 8. Make changes through chat, and confirm the draft before anything is written to Mealie. 9. Have Claude seed the confirmed plan into Mealie, merge ingredients across every meal, round them to sensible pack sizes, and create a categorised shopping list. 10. Install the Mealie integration in Home Assistant to display the plan, recipes, and shopping list on your devices.

I asked ChatGPT to create a graphic for my company. I provided our company colors, logo, brand guide, the objective of the graphic, and information about our audience. ChatGPT then created the graphic based on those details. Step-by-step: 1. I asked ChatGPT to create a graphic for my company. 2. I provided our company colors, logo, and brand guide. 3. I explained the objective of the graphic. 4. I described the intended audience. 5. ChatGPT created the graphic using the information I provided.

I built a workflow called InnerWeather to help me understand fluctuations in energy, pain and mood over time, in the context of neurodivergence and a chronic muscular pain condition. The workflow creates lightweight daily scans and a weekly overview. Its purpose is not to diagnose symptoms or pretend that every change has a single cause. Instead, it helps make patterns visible across time: when energy drops, when pain increases, when stimulation or emotional load seems higher, how recovery unfolds, and which combinations tend to appear together. The daily scans are possible because I naturally talk to GPT throughout the day, sometimes in very short updates and sometimes in longer conversations, about how things are going, what I am doing, how my body feels, how much energy I have, and what seems to be affecting me. InnerWeather uses those scattered moments as observational material. It does not require me to fill in a formal tracker several times a day. The information is already present in the conversations I am having. The daily scans do not reduce an entire day to one fixed state. They map changing moments across the day, using colour-coded states and paying attention to common transitions between them. That makes it possible to see not only how I felt, but how my internal state moved: whether high stimulation tends to be followed by fatigue, whether pain appears after certain kinds of activity, or whether a low-energy period gradually shifts into recovery. This matters because capacity can vary significantly within one day. A difficult morning does not necessarily define the whole day, and a good afternoon does not erase what happened before it. The workflow is also explicit about uncertainty. If there was not enough input during a particular day to support a meaningful observation, the daily scan says so rather than filling in the gaps. The same applies to the weekly overview: if the available material is too sparse or uneven to support a pattern, that limitation is recorded instead of turning absence of information into a conclusion. The weekly overview brings the daily fluctuations together and looks for recurring sequences, transitions, clusters and recovery patterns across the week rather than treating each day as an isolated event. An important part of the workflow is that the weekly review is also collaborative. When the overview is generated, I use it as a starting point to think together with GPT about what patterns seem to be emerging, whether the current colour codes and transitions are capturing them well enough, and what might need to change in the workflow itself. That means InnerWeather is not a fixed tracker. The task evolves with the patterns it is trying to observe. If a recurring state, transition or distinction is missing, we can refine the categories, adjust the scan, or change the weekly interpretation so the system becomes better at representing what is actually happening. The aim is practical rather than medical: to get a more realistic sense of capacity and recovery over time, so I can make better decisions about pacing, rest, creative work, appointments, and how much I can reasonably take on. I especially like that the workflow treats fluctuations as information rather than failure. Instead of asking only, “Why was I worse today?”, it can reveal a broader sequence: what came before, how the state changed, how long it lasted, and what recovery looked like afterwards. Over time, InnerWeather becomes both a personal pattern archive and an evolving observation tool. In simple terms: day-to-day conversation → colour-coded fluctuation map → transitions across the day → weekly pattern review → collaborative interpretation → refine the task → better future scans The goal is not to predict my body perfectly. It is to keep improving the map while remaining honest about what the available information can and cannot support.

I have a lot of calls, and follow-ups were the first thing to get lost once my day filled up. Granola notes helped, but I still had to remember to go back and read them. I connected Granola, Claude, and Notion, then set up a scheduled task in Claude. Every day at 6 p.m., it reviews that day’s Granola meeting notes, finds any to-do items or commitments I made, and creates them as tasks in my Notion to-do list. Step-by-step: 1. I connected Granola and Notion to Claude through Settings > Connectors. 2. I created a scheduled task with a prompt like: "Read today's Granola meeting notes. For each action item assigned to me, create a task in my Notion to-do database with the meeting name and date." 3. I set the task to run daily at the end of the day.

I built a personalized news workflow called “TastyHookedFish” as an antidote to the feeling that news is limited to crisis, conflict, and collapse. It periodically searches for genuinely interesting, positive developments across science, climate, medicine, conservation, technology, culture, and social progress. The goal is not to create a feed of cheerful fluff, but to surface meaningful developments that provide evidence that useful things are happening in the world. The workflow also tries to avoid repetition, so the same feel-good stories do not keep resurfacing simply because they are popular. The result is a personalized news feed that does not ignore reality, but deliberately widens the lens. Step-by-step: 1. I set up a personalized news workflow called “TastyHookedFish.” 2. I configured it to periodically search for positive developments across science, climate, medicine, conservation, technology, culture, and social progress. 3. I focused the workflow on meaningful developments rather than generic cheerful stories. 4. I added a way to avoid repeatedly surfacing the same feel-good stories because they are popular. 5. I use the resulting feed to stay informed while deliberately widening my view of what is happening in the world.

AI agents such as Claude Code, Codex, and Gemini can install skills, plugins, and CLI tools in seconds. That is convenient, but each add-on runs with access to files, passwords, and accounts. A malicious add-on could steal API keys, read private data, or quietly take control of the agent. I use `agent-guard` to make “check first, install after” the default. Before installation, it examines AI agent skills, MCP servers, and CLI tools for malware, prompt injection, and credential theft using professional, open-source security scanners from NVIDIA, Cisco, Datadog, and the Open Source Security Foundation. The tool returns a clear verdict: safe to install or blocked, with the exact reason. It then installs only the verified version, preventing a different version from being swapped in between. A single check can also cover multiple AI agents, installing the approved add-on into every agent on the machine. Free and open source: https://github.com/elliottwaves-20/agent-guard Step-by-step: 1. I select the AI agent skill, MCP server, or CLI tool I want to install. 2. I run `agent-guard` to scan it for malware, prompt injection, and credential theft. 3. I review the verdict and the reason if the add-on is blocked. 4. I install the exact version that was checked rather than an unverified replacement. 5. If I use several AI agents, I install the approved add-on into all of them at once.