Workflow Hub

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 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.

After nearly 20 years in France, I’m finally applying for citizenship. I’ve spent the past year preparing documents and studying for the required tests, and my final interview is a few weeks away. Alongside the official study materials, I’ve been using ChatGPT to drill key facts and historical dates, run mock oral interviews in voice mode, and create quizzes from YouTube videos I link whenever they cover the right material. ChatGPT sometimes speaks French with a rather heavy accent, but the interactive back-and-forth helps me remember hundreds of details that are difficult to retain by simply reading a page. It’s tedious, but I find rote memorization challenging. We’ll see how it goes under pressure.

I used AI to help investigate a family mystery that had remained unresolved for decades: identifying the biological family of my maternal grandfather. The challenge was not a lack of information. It was almost the opposite. I had DNA matches, family trees, names, dates, historical records, old photographs, obituaries, Facebook genealogy groups, and conversations with possible relatives. The difficult part was connecting all these scattered clues without jumping to conclusions. I built a research workflow in which AI acts as an investigation partner, not as the source of truth. Step-by-step: 1. I gathered the information I already had from genealogy platforms, DNA matches, family trees, historical documents, and family records. 2. I used ChatGPT to organize the evidence into people, dates, locations, relationships, DNA connections, documents, and unresolved questions. 3. I separated the information into three categories: confirmed facts, hypotheses, and missing information. 4. Instead of asking AI, “Who was my grandfather's biological father?”, I asked it to analyze possible family connections and identify which hypotheses were compatible with the available evidence. 5. For each hypothesis, I looked for supporting evidence, contradictory evidence, and information that was still needed. 6. I treated AI-generated connections as leads rather than genealogical proof. The goal was to use AI to decide what to investigate next, not to have it find the answer. 7. I used AI to compare family branches, surnames, generations, locations, and possible relationships among DNA matches whose family connections I did not immediately recognize. 8. When a promising connection appeared, I returned to the original genealogy and DNA sources to verify it. This gradually turned a long list of DNA matches into a smaller number of research paths. 9. I used AI to draft respectful, personalized messages to DNA matches and members of genealogy communities, including people in another country and language. 10. In each message, I explained what I was researching, what connection I suspected, what information I already had, and what I hoped the recipient might be able to confirm or rule out. 11. I treated their responses as new evidence and repeated the investigation loop: evidence → AI analysis → hypothesis → verification → human contact → new evidence → updated hypothesis. The final result is not an “AI-generated family tree.” It is a human-led investigation in which AI helps manage complexity, ask better questions, and identify the next useful action. The most important lesson I learned is that AI is particularly useful in genealogy when you do not ask it to give you the answer. Ask it to help you build the investigation.

I wanted to reduce the time and mental effort it takes each morning to figure out what needs my attention across my inbox and calendar. I used Codex Automations to build Briefly, a daily AI-powered email and calendar brief that is automatically delivered to my inbox every day. Instead of manually searching through emails and checking separate calendar events, I can open one message from Briefly and immediately see what is happening, what needs action, and what is coming up. It has become a simple way for me to use AI proactively—not only when I ask a question, but as an automated system that helps me stay ahead of my emails, tasks, and schedule each day. Step-by-step: 1. I connected the email and calendar sources I wanted the automation to review. 2. I created a Codex Automation that runs each morning. 3. I instructed it to review recent and important emails, identify messages that need attention or follow-up, and check my calendar for upcoming meetings and commitments. 4. I had it turn that information into a concise daily brief. 5. I configured the brief to be delivered to my email automatically.

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.

I built a custom news agent that skips the Google News and Apple News walled gardens. Eight prompts turn Claude into a personal news editor that reads my trusted RSS feeds, scores every story with a decision model, and delivers a clean daily page for about a dime a month. Each week, pulling two or three good stories for my newsletter digest meant searching multiple sites by hand—hours of clicking and scrolling for a handful of usable links. RSS feeds already deliver that content; the missing piece was a judgment layer that could separate worthwhile stories from noise without the cost or latency of running everything through a full LLM. I used Claude Cowork, Jev from TypeSafe AI, Vercel AI Gateway, RSS feeds, Python, and SQLite. Jev is a decision model rather than a chatbot: it returns a probability and confidence score instead of prose, does not hallucinate facts, and scores a story in a fraction of a second. That makes an automated daily judgment call inexpensive enough to run continuously. Step-by-step: 1. I set up a Claude project to hold the scripts, taste guide, database, and page. 2. I defined the goal and sections, then had Claude interview me to create a short “taste guide” describing what counts as a good story. 3. I found and live-tested the RSS feed for each trusted source instead of guessing feed URLs. 4. I fetched all working feeds into a deduplicated SQLite database and logged failures. 5. I used Jev through Vercel AI Gateway to score every story: first filtering ads and promotions, then ranking stories by section against my taste guide. 6. I selected the winners for each section, with Jev identifying near-duplicate stories so they would not appear twice. 7. I generated one-line summaries and fact-checked them against the source so nothing was invented. 8. I rendered a simple HTML page and scheduled the entire workflow to run every morning. A few details matter. I used Cowork rather than a plain chat because several steps require Claude to work with files, run code, and access the network. I also created a Vercel account and AI Gateway API key manually before the scoring step. Finally, I saved everything to the Claude project instead of a local folder, which allows the morning run to happen in the cloud on its own schedule. Scoring costs roughly $0.10 per month with Jev, compared with a few dollars for a full LLM doing the same job. The workflow turns a two-hour weekly slog into a page that is ready every morning, with each link going directly to the original publisher rather than a Google or Apple aggregator. Full build walkthrough: onabetternote.substack.com/p/build-your-own-news-agent-with-claude — the Substack post includes the exact eight prompts to copy and paste, plus more detail on why a model like Jev matters for cost containment as agents become routine.

Design taste is hard to put into words. I may know immediately that one website, presentation, report, or graphic feels right and another doesn't, but still struggle to explain whether the difference comes from the typography, spacing, colors, density, layout, or overall aesthetic. That makes working with AI frustrating. If I can't describe what I want, the AI has to guess. Instead of trying to explain my design taste upfront, I turned the process into an iterative visual feedback loop. I first asked the AI to suggest existing websites with different design styles so I could identify examples I liked. Once it had those references, I asked it to create three substantially different HTML mockups for the same content. I picked the direction I liked best, explained what I liked and disliked, and had the AI generate another set of alternatives based on that feedback. After about three rounds, the AI had a much better understanding of my design preferences than I could have given it in a written prompt. The basic loop is: show me examples → I choose → generate alternatives → I react → refine → repeat. This is essentially preference elicitation through examples. Research on human-AI interaction has similarly found that people can refine difficult-to-articulate preferences by reacting to concrete alternatives rather than specifying everything upfront. Step-by-step: 1. I asked the AI for several visual references, including websites or designs that represented distinctly different styles. 2. I reviewed the examples and identified the ones I liked. I didn't need sophisticated design terminology; I simply described what I preferred and anything obvious that I liked or disliked. 3. I gave the AI something real to design. I used an actual report I was working on so I could evaluate the styles in context. 4. I asked the AI to create three substantially different visual directions rather than minor variations of the same design. 5. I chose the direction closest to my taste and explained what I liked, what I didn't, and which elements from the other versions I wanted to incorporate. 6. I asked the AI to generate three new alternatives using everything it had learned so far. 7. I repeated the process until the designs began to converge. I did roughly three rounds, with each round narrowing the design space and giving the AI more information about my preferences. 8. I asked the AI to summarize what it had learned into reusable design guidelines so future projects could start with those preferences. Instead of trying to translate an aesthetic preference into design terminology, I let the AI learn my taste from my choices. The important shift is simple: don't describe what you like—show, choose, react, and refine. This can work for websites, presentations, reports, branding, graphics, interior design, clothing, invitations, or almost anything else where I know what I like when I see it.

I built Shots2Points, a golf scoring app for iPhone and Android, using AI as my development partner. The idea came from organising and playing in golf society events. Stableford scoring itself isn’t particularly complicated, but running an event can be. Organisers have to prepare groups, handicaps, and courses; collect scores from different groups; calculate results; manage withdrawals and ties; and eventually produce a leaderboard. I wanted to simplify that process while also providing an easy scoring app for ordinary casual rounds. The unusual part is how I built it. I’m not a professional software developer, and I don’t have a development team. I started by describing what I wanted the app to do to AI and gradually turned the idea into a working product. My workflow evolved into this cycle: idea → discussion → specification → implementation → real-world test → refinement. I repeat it for each feature. Step-by-step: 1. I define the problem and user experience with ChatGPT. I discuss ideas, challenge assumptions, work through workflows, and decide how a feature should behave before changing the code. 2. Once the behaviour is clear, I turn the idea into an implementation task. I use AI to specify exactly what needs to change, including edge cases and how the new feature should interact with existing functionality. 3. I build and inspect the code with Cursor. Cursor works directly with the project codebase, allowing AI to investigate existing code, implement changes, and report exactly what it changed. I test the result rather than simply accepting AI-generated code. 4. I test development versions on real iOS and Android devices. I follow the actual user journey, take screenshots or capture errors when something isn’t right, and bring those results back into the AI workflow. 5. I use AI to diagnose problems, make another targeted change, and test again. The result is a real cross-platform application rather than a prototype. Shots2Points includes free casual Stableford scoring and an Event Mode designed for golf societies and groups. Organisers can create events, import players, allocate groups, and allow each group to enter scores while everyone follows a live leaderboard. Building the app has required much more than generating code. AI has helped me work through database design, APIs, authentication, in-app purchases, App Store and Google Play requirements, debugging, user-interface decisions, testing, and release management. The biggest lesson for me has been that AI doesn’t remove the need to understand the problem or make decisions. It gives one person access to capabilities that would traditionally have required several different specialists. I provide the product knowledge, requirements, judgement, and testing; AI provides much of the technical capability and an extraordinarily fast feedback loop. That combination allowed me to take a personal idea for improving golf scoring and event management and turn it into a functioning iOS and Android product.

I built a workflow to select music for a senior fitness class that suits the participants’ general age range and meets the program’s criteria of approximately 120 BPM. I also require the music to be danceable and have a 4/4 beat. After a successful summer using AI-suggested, danceable Motown songs from the 1970s, I continued using AI to help with music selection. I don’t have a music background or the knowledge to do this myself, so I appreciate the help. Yesterday, a participant commented on how enthusiastic she was about the music. Her response was simple: “I love the music.” Step-by-step: 1. I considered the general age range of the senior fitness class participants. 2. I used the program’s target of approximately 120 BPM as a selection criterion. 3. I added my own requirements that the songs be danceable and have a 4/4 beat. 4. I used AI to suggest songs that fit those criteria, including danceable Motown songs from the 1970s during the summer. 5. I used participant feedback to confirm that the music was well received.

I’m sharing “The Architects of Reality,” a short film created as part of an experiment with a multi-agent AI workflow for long-form content creation. Off-the-shelf AI video platforms are brilliant for short clips, but as the duration increases, the challenges compound: character inconsistency, narrative drift, visual discontinuity, and expensive iterations when the output doesn’t match the creative vision. Instead of asking one AI to make a film, I created an AI film crew. Specialised agents and sub-agents take on roles including Director, DOP, Cameraman, VFX Supervisor, Sound Engineer, VO Artist, and Audio Mixer to support the filmmaking process. Creative review and approval are built into every stage, so individual elements can be regenerated before expensive final rendering. This helps optimise tokens, budget, and creative control. It’s been a fun journey building these agents—and even more fascinating to watch the output improve in capability and efficiency as they learn every day. Step-by-step: 1. I set up a multi-agent AI workflow for long-form content creation. 2. I assigned specialised filmmaking roles to agents and sub-agents, including Director, DOP, Cameraman, VFX Supervisor, Sound Engineer, VO Artist, and Audio Mixer. 3. I built creative review and approval into every stage of the process. 4. I regenerate individual elements when they do not match the creative vision, before moving to expensive final rendering. 5. I use the workflow to optimise tokens, budget, and creative control while producing the short film “The Architects of Reality.” 6. I observe how the output’s capabilities and efficiencies improve as the agents learn every day.

A reusable Claude Skill called `trust-due-diligence`, packaged as a `.skill` file. It is not a single report; it is a methodology made up of a `SKILL.md` file and three reference documents that teach Claude a repeatable process for investigating a named person, company, coach, or offer before you commit money or trust to them. Once installed, it activates automatically whenever you ask something like “deep dive on X” or “is this legit,” so you do not need to explain the process each time. Step-by-step: 1. Package the `trust-due-diligence` Claude Skill as a `.skill` file. 2. Include a `SKILL.md` file and three reference documents. 3. Use the files together to teach Claude a repeatable due-diligence methodology. 4. Install the Skill so it activates automatically for prompts such as “deep dive on X” or “is this legit.” 5. Use it to investigate a named person, company, coach, or offer before committing money or trust.

I moved from public school to a private school with no autism-specific training, and I found students on the spectrum struggling with one-size-fits-all lessons. AI helped close that gap for both me and my students in about five minutes per lesson. I take a standard lesson and rebuild it around the individual student. I upload only the blank assignment—never any student data—and prompt AI to adapt it to that learner. I include their favorite colors and niche interests, replace abstract examples with personalized ones, add sentence starters, and allow them to draw responses instead of writing dense paragraphs. Step-by-step: 1. I take an existing lesson and create a blank version of the assignment. 2. I upload only the blank assignment to my AI tool, without including any student data. 3. I provide the student’s interests, preferred colors, and reading level. 4. I ask the AI to rebuild the lesson for that specific student. 5. I use personalized examples, sentence starters, and drawing-based response options to make the lesson more accessible. The result is no shutdowns, no walls, and a genuinely engaged and grateful student. One untrained teacher can now individualize any lesson for a unique learner in minutes.

I was overwhelmed by the thousands of emails I receive in my Outlook inbox every month. I didn’t have time to analyze them all, generate relevant responses, or track the replies and progress of each case. I used an Outlook feature and the virtual assistant Perplexity to help handle the task. Here’s the process: Step-by-step: 1. In Outlook, open the correct folder and select all the emails. 2. Go to Export/Import and follow all the required steps. 3. Export the emails as a `.csv` file, name the file, and save it in a specific location. 4. In Perplexity, attach the `.csv` file. 5. Use a prompt such as: I am a strategy manager and would like to propose a collaboration to my colleague David. The dashboard should list all topics discussed, proposed actions for each topic, and the remaining work to be done.

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 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.

We built an evidence-driven Agentic AI workflow for extracting trustworthy investment intelligence from messy real-estate documents. The problem wasn't simply getting an LLM to read PDFs. Real-estate investment information can be distributed across reports, underwriting documents, valuation materials, rent schedules, spreadsheets, tables, and multiple versions of the same information. A metric such as IRR can also appear several times with different scenarios, dates, classifications, or meanings. Instead of building another "chat with your documents" agent, we designed a controlled agentic workflow around one principle: Don't make the agent smarter. Make the workflow harder to fool. Step-by-step: 1. I start with the business question. The agent receives a request for a specific investment metric for an asset and determines the business context instead of immediately searching for matching words. 2. I resolve the entity by normalizing the asset or entity using aliases, identifiers, relationships, and hierarchy information. This prevents ambiguous names from sending retrieval in the wrong direction. 3. I build a metric-specific plan using governed definitions for important metrics. A definition can include the metric's business meaning, terminology, preferred sources, classifier information, negative cues, and extraction rules. The agent starts with a contextualized retrieval and extraction plan rather than a vague instruction such as "find IRR." 4. I discover the right documents by narrowing candidate source documents with metadata and path-level information before searching the entire corpus semantically. The goal is: Find the right document before finding the right chunk. 5. I retrieve evidence within the selected documents. Only when scoped retrieval is insufficient does the workflow fall back to broader semantic retrieval, keeping the agent's search controlled and auditable. 6. I inspect structured information when necessary. Important investment information frequently lives in tables rather than paragraphs, so the workflow escalates to table-aware processing to inspect rows, columns, schedules, and structured financial evidence. 7. I extract a structured result instead of a long free-form answer. The result preserves the metric, value, unit or context, source document, page or location, and citation information. 8. I validate the evidence by checking the extracted value against the metric definition and relevant validation rules. Depending on the metric, these checks can include unit, scenario, chronology, plausibility, and table-to-text consistency. 9. I resolve conflicts explicitly. If multiple plausible values are found, the agent does not simply select the first result. The workflow applies rules for source precedence, chronology, scenario classification, and evidence strength. If a conflict cannot be safely resolved, the ambiguity is preserved rather than hidden. 10. I produce an evidence-backed result containing the selected metric, supporting evidence, context, and lineage. The result can then become a structured business artifact for downstream analytics, reporting, or decision-support workflows. This is not simply Question → RAG → Answer. The workflow is Question → Understand → Ground → Plan → Retrieve → Inspect → Extract → Validate → Resolve → Evidence-backed output. Retrieval is one capability inside the workflow. The agent coordinates the process, chooses the appropriate tools, follows the retrieval policy, handles structured evidence, and moves the result through validation and resolution. The biggest improvement did not come from giving the model more freedom. It came from giving the model better boundaries, better domain knowledge, better tools, and explicit decision rules. This pattern can be applied beyond real estate to financial research, insurance, compliance, legal documents, due diligence, and other enterprise workflows where an answer needs to be not only useful, but defensible and traceable.

I use ChatGPT to analyse and redesign the underlying structure of a messy computer archive. I first generate a folder tree locally with a Python script provided by ChatGPT and saved as a BAT file. The tree shows the hierarchy of folders and filenames, giving ChatGPT a broad view of how the archive is currently organised. From that structure, ChatGPT can identify where the organisation is too fragmented or too broad. For example, a client folder may contain ten nested subfolders with only a few text files in each, making the structure more complicated than the content requires. Elsewhere, hundreds of photos, screenshots, or documents may all sit in one folder, suggesting that more meaningful categories would help. ChatGPT can then propose a revised structure with more or fewer levels, depending on the actual content. It can also suggest more consistent naming conventions for folders and files, identify recurring subjects or topics of interest across the archive, and point out categories that already exist implicitly but have never been organised deliberately. For larger changes, I can ask ChatGPT to help create a copied version of the archive using the proposed structure rather than immediately reorganising the original files. This gives me a working prototype of the new system. I can browse it in Windows Explorer, see whether the categories make sense in practice, and adjust the structure before making any permanent changes. The result is not just a cleaner folder tree. It is a way to use AI to discover the information architecture hidden inside years of accumulated files and turn it into a structure that better reflects how the content is actually used. Step-by-step: 1. I use ChatGPT to generate a Python script that creates a folder tree locally, then save the script as a BAT file. 2. I use the folder tree to show ChatGPT the archive’s hierarchy of folders and filenames. 3. I ask ChatGPT to identify areas that are too fragmented or too broad, such as deeply nested client folders or folders containing hundreds of mixed files. 4. I ask ChatGPT to propose a revised structure with an appropriate number of levels, along with more consistent folder and file naming conventions. 5. I ask ChatGPT to identify recurring subjects and categories that already exist implicitly in the archive. 6. For larger changes, I ask ChatGPT to help create a copied version of the archive using the proposed structure instead of changing the original files immediately. 7. I browse the copied structure in Windows Explorer, assess whether the categories make sense in practice, and adjust the system before making permanent changes.

Spotify can tell me what I played, but it rarely explains what music does in my life. I use exported listening data, playlists, and personal context to explore taste, memory, regulation, identity, and continuity. I look at both observable listening behavior and the meanings I attach to it, without forcing every track into a biography. Step-by-step: 1. Start with the data. I export streaming history, tracks, artists, timestamps, listening duration, saved songs, and playlists where available. I check the period covered and remember that missing history does not mean a song never mattered. I start with behavior: a supposed favorite may barely appear, while another track may have played hundreds of times quietly. 2. Separate tracks from artists. I count unique tracks, unique artists, and tracks per artist. One artist with dozens of songs and hundreds of artists represented by one track suggest different listening styles: exploring discographies versus collecting exceptional songs. 3. Find lasting favorites. I distinguish temporary high-volume artists from favorites that return across years, playlists, and life phases. I look for persistent songs: tracks spanning years, returning after long gaps, or appearing in several playlists. Persistence can matter more than total plays. Some songs never win a monthly ranking yet refuse to disappear. 4. Connect music to life. I add relevant personal context, such as teenage years, university, a move, a relationship, or rebuilding. I ask which songs became landmarks and which were described as “my song.” Dates show when music appeared; I explain what that timing means instead of forcing every track into a biography. 5. Discover playlist functions. Repeated songs are not always favorites. Sometimes music has a job: providing strength, calm, concentration, singing, emotional release, or a way to reconnect with myself. I read playlist names alongside their tracks and listening patterns. “Power” might mean, “I do not feel strong, so I need external strength.” “Gold” might mean, “I want to feel my own golden heart again.” These meanings matter more than a generic genre label. 6. Treat corrections as evidence. AI suggests interpretations, but I decide whether they fit. For example: “This song is not nostalgic. It reminds me that I remain myself regardless of what another person does.” Corrections like this can change the meaning of an entire playlist, so I keep them alongside the data. 7. Look for regulation patterns. I find songs played daily for weeks, tracks repeated within one day, and playlists used at consistent times. I ask whether they accompany difficult tasks, low energy, singing, or calming down. Repetition is a clue, not proof of an emotional function. 8. Look beyond genre. Pop, rock, electronic music, mantra, and soundtracks can share dramatic builds, layered vocals, melodic hooks, powerful voices, intimate production, or mantra-like repetition. These qualities can explain why apparently unrelated songs belong together. I let myself name the patterns; “Post-Classical Electroacoustic Intimate Futurism” may be more useful for discovery than a standard genre. 9. Separate nostalgia from continuity. An old song returning is not necessarily nostalgia. I ask whether it is remembered or still actively used. Some music belongs to the past, while some music simply has a very long present. I keep different musical worlds separate: anthemic pop and meditative mantra may serve different parts of the same person. 10. Build a traceable profile. I include core artists, persistent songs, personal anthems, life-phase associations, functional playlists, regulation patterns, musical qualities, and unexpected findings. I link interpretations to dates, play counts, playlist appearances, and my explanations. I separate observed behavior, AI hypotheses, and confirmed meanings, and keep the profile easy to correct. 11. Recommend for the person. Instead of asking for “songs similar to Coldplay,” I ask: “Find the emotional build I like in Coldplay, the vocal force I like in Sia, and the intimate electronic texture in my meditation playlists.” I can also ask: “Find tracks for Power that could survive repeated listening without copying its existing artists.” 12. Update over time. I add new data and look for new favorites, returning anchors, changing playlist functions, and stable patterns. The ongoing cycle is: export → analyse → find persistent songs → map functions → add personal context and corrections → build the profile → recommend → update. Listening history records what I played. AI helps me explore why something kept returning. I remain the only person who can finally say: “Yes. That is what this song means to me.”

I built a custom GPT with the personalities of Einstein, Lorentz, Planck, and Compton. Starting with Einstein’s 1920 Leiden lecture, I developed an ontology for physical space based on his description of the “new ether.” I began with E=mc2, E=hf, and my ontological modeling assumptions. I then repeatedly pushed ChatGPT to challenge those assumptions and interpretations logically and mathematically. We used numerous tool calls and reference sites to write and test the math. After many months of working on it in my spare time, the GPT now unifies equations that balance from the atomic scale to the black hole scale, with some remarkable revelations. I summarized much of the work in a paper written by my GPT and am happy to share it so others can expand, improve, and test the work. AI rocks. Step-by-step: 1. I built a custom GPT with the personalities of Einstein, Lorentz, Planck, and Compton. 2. I used Einstein’s 1920 Leiden lecture and his description of the “new ether” to develop an ontology for physical space. 3. I started with E=mc2, E=hf, and my ontological modeling assumptions. 4. I repeatedly challenged the assumptions and interpretations with ChatGPT, focusing on logical and mathematical consistency. 5. I used numerous tool calls and reference sites to write and test the math. 6. After many months of working on the project in my spare time, I summarized much of it in a paper written by my GPT. 7. I am sharing the work so others can expand, improve, and test it.