Workflow Hub

AI agents are much more useful when they can remember important context across sessions. However, giving every agent access to one giant memory creates a different problem: irrelevant information accumulates, context becomes noisy, and agents waste time sorting through details that do not apply to their task. The challenge is not only giving AI memory. It is deciding what should be remembered, which agent should remember it, and where that memory belongs. I use a three-tier memory system that separates knowledge by scope: - Global memory: Information that should be available across the entire AI system - Agent memory: Knowledge specific to an individual specialist and how it should work - Project memory: Decisions, constraints, discoveries, and context that matter only within a particular project Instead of copying everything into every agent’s context, I store information at the narrowest level where it remains useful. Step-by-step: 1. Create a global memory layer for durable information that is useful across many agents and projects, such as important user preferences, shared conventions, and system-wide decisions. 2. Give each specialist its own memory. Store knowledge that helps a particular agent perform its role better, such as recurring preferences, domain lessons, and patterns learned from previous work. 3. Create project-specific memory for decisions, constraints, terminology, discoveries, current state, and other context that belongs with the project rather than in global memory. 4. Classify new information by scope. Whenever something worth remembering is learned, ask: - Does the whole system need this? - Does only this agent need it? - Does it matter only for this project? 5. Store the information at the narrowest useful level. Avoid promoting project-specific details into global memory unless they are genuinely reusable elsewhere. 6. Have agents load relevant memory before they work. A specialist can combine its accumulated knowledge with the current project context instead of starting every session cold. 7. Update memory as important decisions are made. Persist decisions and reusable lessons rather than relying on conversation history to remain available indefinitely. 8. Keep historical artifacts separate from active memory. Run logs, old handoffs, and detailed history can remain available for reference without automatically loading into every future interaction. Instead of treating memory as one giant bucket, I create a hierarchy: `Global → Agent → Project` Each agent gets the context it actually needs while unrelated information stays out of its working context. This provides better continuity across sessions, reduces repeated explanations, keeps context cleaner, and helps AI agents accumulate useful knowledge without requiring every agent to remember everything.

An AI “executive brain” needs two things: intelligence that, combined with your context, forms the system’s “brain,” and a harness that gives it “hands”—the agentic capabilities to act on your behalf. Claude Code and Codex are two popular options. Their apps provide both the model and the harness in an easy-to-use interface. My workspace is GitHub because popular AI models already understand it and can handle its setup and administration for me. GitHub also syncs automatically with the local file system on my MacBook, so I retain complete ownership and control. If I ever wanted to leave GitHub, I could do so without lock-in. The same setup can work in any file system, from your local file system or Google Drive to a more sophisticated option like Obsidian. A good manager has a structured process for onboarding and staying aligned with a team. You need the same structure to work effectively with AI. My “executive brain” has four layers: the company layer, project folders, operations folders, and the process layer. The company layer contains the mission, vision, values, brand guidelines, and decision-making principles. Project folders contain one folder per project, including its specification, plan, open questions, and decision log. Operations folders cover ongoing areas of the business, such as marketing, finance, and support. They have the same shape as project folders, but they never finish: projects ship, while operations run. The process layer contains standard operating procedures for how we work together, such as processing a meeting, planning a project, publishing a post, and closing out the week. For AI to work successfully, your company has to be “legible” to it. If information is not written down and accurate, it is not legible, and the AI cannot help you with it. This is like onboarding a great new hire: explain what the company is trying to do, what each project is for, what has already been decided and why, and how you like to work. You do not need to write everything alone or all at once. The AI can interview you, draft the documents, and file them in the right place based on the structure you set up. An employee without logins cannot do much, and AI works the same way. Start with the places where you communicate. At my company, we primarily communicate through Zoom and our community forums, so my AI system is connected to both. This allows it to stay up to date as we progress and participate in discussions as an equal participant when asked. Once the AI is connected to your communications, give it access to the places where you want it to execute on your behalf. You can connect it directly through an API or MCP, or it can use a browser to interact with a tool the same way you do by clicking and typing. You decide what it can access, and you can start small. Each connection turns a category of “things I have to do myself” into “things I can delegate.” The final step is incorporating what the AI learns. After every working session and meeting, it updates the record: decisions are logged, task lists are reconciled, and project documents are brought up to date. When we learn something, it goes into the SOP, so every future run is sharper than the last. That is how the AI becomes more useful every week: its knowledge compounds inside the business instead of starting from zero in every conversation. Step-by-step: 1. Choose the intelligence and harness that will power your AI system. Claude Code and Codex are two popular options whose apps provide both in an easy-to-use interface. 2. Create a workspace for alignment, planning, feedback, and learnings. I use GitHub because AI models understand it, it handles setup and administration, and it syncs with my local MacBook file system without locking me in. 3. Organize the workspace into four layers: company information, project folders, operations folders, and process documentation. 4. Make the company legible by documenting its goals, projects, decisions, working preferences, and other relevant context. Have the AI interview you, draft the documents, and file them in the appropriate locations. 5. Connect the AI to your communication tools, such as Zoom and community forums, so it can stay informed and participate when asked. 6. Connect the AI to the systems where you want it to execute tasks. Use a direct API or MCP connection when available, or give it browser access when it is not. 7. After each working session and meeting, have the AI update decisions, task lists, and project documents. 8. Add new learnings to the relevant SOP so each future run improves on the last.

I built Show Hole to solve my family’s classic streaming problem: we spend too much time deciding what to watch, and the answer changes depending on who is actually on the couch. We each have different tastes, but the more interesting problem is that our tastes overlap differently in different combinations. I watch one kind of thing with my spouse, my spouse watches something different with our kid, and my kid and I have our own lane too. Most recommendation tools flatten that into one account profile, one watch history, or broad genre buckets, so they miss the real context of a household. Show Hole treats people and viewing contexts as first-class citizens. It recommends titles “in the vein of” something we liked, filters recommendations to the streaming services we actually subscribe to, avoids titles that the people present have already seen or vetoed, and explains why a recommendation fits tonight. Instead of relying mainly on genres such as comedy, drama, or sci-fi, Show Hole looks at more human taste signals: pacing, world building, humor, emotional weight, complexity, tone, and similar dimensions. It also learns from what we actually do after a recommendation: what we watch, skip, save for later, love, and drop. The result is a personal household recommender that understands “who is watching tonight?” as part of the question, instead of pretending one streaming profile can represent everyone. I designed the app using Claude design, then used those designs with Claude Code to build it. Step-by-step: 1. I identified the household viewing problem and accounted for the different combinations of people who might be watching together. 2. I designed Show Hole around people and viewing contexts instead of treating the household as one account profile, watch history, or set of broad genre preferences. 3. I had it recommend titles “in the vein of” something we liked, filter them to the streaming services we subscribe to, exclude titles already seen or vetoed by the people present, and explain why each recommendation fits that night. 4. I used taste signals such as pacing, world building, humor, emotional weight, complexity, tone, and similar dimensions instead of relying mainly on genres. 5. I made the recommender learn from what we watch, skip, save for later, love, and drop after receiving a recommendation. 6. I designed the app using Claude design and used those designs with Claude Code to build it.

Most AI agents are effectively static. You write their instructions, use them repeatedly, notice where they struggle, and manually tweak the prompt when something goes wrong. Valuable feedback from real work is often lost, so the same mistakes can keep happening. I created a self-improvement flywheel that uses actual agent performance data to improve agents over time. The system collects two kinds of evidence: - Task scores showing how well each agent performs across different quality dimensions - Run telemetry and review outcomes revealing recurring failures, coordination problems, and cases where actual behavior differs from expectations A scheduled weekly cycle analyzes that evidence, identifies patterns, creates improvement proposals, evaluates whether those proposals are safe and broadly applicable, updates agent instructions when appropriate, and measures whether those changes actually improve performance. The goal is not to let agents rewrite themselves freely. It is to create a controlled learning loop. Step-by-step: 1. Collect performance data while agents work. Score important outputs across consistent quality dimensions, and record useful execution telemetry such as failures, decisions, reviewer outcomes, and unexpected behavior. 2. Analyze performance trends on a recurring schedule. Calculate per-agent averages, identify weak dimensions, compare agents, and look for improvement or decline over time. 3. Mine run history for recurring patterns across multiple sessions, including agents that repeatedly struggle, low-quality runs, and cases where expected behavior differs from what actually happened. 4. Turn repeated problems into improvement proposals. Before proposing a change, inspect the agent’s current instructions so you do not add a rule that already exists. 5. Evaluate each proposal before applying it. Check whether the lesson is broadly useful, redundant with existing instructions, or in conflict with established behavior. 6. Separate low-risk and high-risk changes. Automatically apply additive or clarifying improvements. Escalate conflicting changes for human review instead of allowing the system to fundamentally change an agent’s behavior on its own. 7. Look for system-level problems. Analyze patterns across agents to identify quality gaps, missing capabilities, or coordination failures that cannot be fixed by changing one agent alone. 8. Apply approved improvements and preserve the history. Update the relevant agent instructions, archive the processed proposals, and version the changes so they remain inspectable and reversible. 9. Measure whether each change actually helped by comparing agent performance before and after the refinement. If quality does not improve, do not automatically assume the change was useful. 10. Repeat the cycle. As agents complete more real work, the system gathers more evidence and gets another opportunity to improve. Instead of treating agent instructions as static prompts, I turned them into a continuously improving system: Work → Evaluate → Find Patterns → Propose Changes → Refine → Measure → Repeat The important part is that the loop is evidence-driven and controlled. Agents improve from real usage, but low-confidence or behavior-changing updates still require judgment rather than being applied automatically.

Most AI agents start with someone writing a prompt from scratch. I wanted a better way. So I built an Agent Creator. I describe the kind of agent I need, and it determines whether I actually need a new one, figures out how that agent should work, creates it, and adds it to the rest of my agent team. Step-by-step: 1. I describe what I need by telling the Agent Creator what I want the new agent to do. 2. It checks what already exists by reviewing my existing agents and skills. If something already does most of the job, it recommends improving or reusing that instead of creating another overlapping agent. 3. If a new skill is needed, it researches the role, including current best practices, common mistakes, useful tools, and what good work looks like in that area. 4. It creates the agent by defining its job, required information, outputs, available tools, and the steps it should follow. 5. It gives the agent the right skills by creating or reusing supporting skills, including examples, reference material, and checks that help it work consistently. 6. It sets clear boundaries so the agent knows what it should handle, what it should not handle, and when another agent should take over. 7. If the new agent belongs in an existing workflow, it adds the agent to the team by updating the handoffs so the other agents know when to use it. 8. Before finishing, it checks the agent’s work by running validation checks to confirm that the new agent follows the standards I’ve set for the whole team. The result is that I don’t have to manually design every new agent from scratch. I can describe the kind of help I need, and one agent can research the role, create the new specialist, connect it to the rest of the system, and make sure it’s ready to use. In other words, I built an AI agent that can help grow its own team.

Take the AI out of AI-written text. We all know its characteristics: it is sometimes overwritten and repeats itself. /humanise

At some point, my newsletters stopped feeling like reading and started feeling like debt. The information was good; I just couldn’t keep up. I wanted a way to turn that backlog back into something useful. So I built The Daily Nexus, a private tool that reads newsletters from a Gmail label and creates two editions: a podcast I can listen to and a separately written, two-page newspaper I can scan. It runs on demand or on a schedule, and it can publish the audio to a private RSS feed for Apple Podcasts. The project also became a hands-on experiment in building with coding agents. Claude Code and Codex helped me implement features, troubleshoot failures, review the design, and tighten security. The stack includes Python, the Gmail API, Antigravity, Kokoro, FFmpeg, Firebase, Cloudflare Workers, and GitHub Actions. The carousel shows the rest of the flow. It started as a personal tool, but I’m sharing the template for anyone who wants to adapt the idea. Each deployment uses its own accounts and credentials, and the design aims to avoid additional API costs by using an existing AI subscription and available free tiers. GitHub Repo Template: https://lnkd.in/eYceS4KR Step-by-step: 1. I label the newsletters I want to process in Gmail. 2. I run The Daily Nexus on demand or on a schedule so it can read the newsletters from that Gmail label. 3. The tool creates a podcast edition and a separately written, two-page newspaper edition. 4. I listen to the podcast or scan the newspaper, depending on how I want to catch up. 5. When needed, the audio is published to a private RSS feed for Apple Podcasts. 6. I use Claude Code and Codex to implement features, troubleshoot failures, review the design, and tighten security. 7. Each deployment uses its own accounts and credentials, with Python, the Gmail API, Antigravity, Kokoro, FFmpeg, Firebase, Cloudflare Workers, and GitHub Actions supporting the workflow.

I used Claude and Nano Banana 2 to create a detailed landscaping plan for my property. The plan included precise recommendations for plant types and locations, soil testing, purchase lists, local suppliers, expected wholesale pricing, and photorealistic images of the mature planting beds. I refined the plan through 20–30 iterations, incorporating all of my requirements. Because I have previous experience working with landscape architects, I was able to use the AI-generated plan effectively and legitimately saved $5,000 in fees. Step-by-step: 1. I used Claude and Nano Banana 2 to develop a landscaping plan for my property. 2. I included requirements for plant types and locations, soil testing, purchase lists, local suppliers, expected wholesale pricing, and photorealistic images of the mature planting beds. 3. I refined the plan through 20–30 iterations until all of my requirements were incorporated. 4. I used my previous experience working with landscape architects to evaluate and apply the plan. 5. I saved $5,000 in landscape architecture fees.

I built a system that reads my AI newsletters every morning and turns them into a searchable catalog of AI tools, plus a chat website where I can ask questions about the catalog in plain English. The system has two parts: a workflow that collects the information and a website that answers questions about it. I subscribe to several AI newsletters, and each issue mentions five or ten interesting tools. I would read about one and think, “I should remember that.” Months later, I would vaguely remember it but have no quick way to find it. I wanted a repository of these AI tools that I could search easily. The collector is a scheduled Claude Code Routine that runs once a day. It searches Gmail for newsletters from the last 24 hours and reads each email in full. It extracts every AI tool’s name, description, category, official link if present, and source newsletter. It skips non-AI items and pure ads but keeps sponsors that are genuine tools. Before adding anything, it checks for duplicates. New tools are added under the appropriate category in alphabetical order. If an existing tool has fresh details, its description and “last updated” date are refreshed. Tools mentioned by three or more sources receive a “Highly Mentioned” tag, which is a useful signal for what is catching on. The workflow also creates categories when new tools do not fit into an existing one. The workflow commits and pushes the catalog to a private GitHub repository, then posts a summary to Slack. The catalog is a single Markdown file—plain text, human-readable, and versioned in Git, with no database. The chat website displays the tool count, category count, and last-updated date, along with clickable example questions. If I ask, “Is there anything for voice AI?” it returns a written answer listing every match with descriptions and working links. The site is a React single-page app on Netlify with two small backend functions: one returns the statistics, and the other handles chat. When I ask a question, the backend fetches the Markdown file from the private repository, sends it to Claude along with my question, and returns the answer. To recreate it, you’ll need a GitHub account, Netlify (the free tier is fine), an Anthropic API key, and Claude Code. The routine prompt is the most important part. It names the exact newsletters, lists the fields to extract, and explicitly says: never invent a URL, never delete an entry, and only add or update. Vague instructions produce files that degrade over time. I learned a few things the hard way. Newsletters deleted before the workflow runs may cause it to report “nothing new,” so the logic should also check Trash or Deleted items. Tokens expire, and mine quietly expired, which caused the search site to stop working. Choose a long expiration period and record the date. Also, explicitly say “never invent a URL,” or the workflow may produce plausible links that go nowhere. It now runs every morning without me. When I need something, I ask a question and get an answer in seconds instead of trying to remember which newsletter, and which month, mentioned the tool I’m thinking of. Step-by-step: 1. I created a private GitHub repository with a starter Markdown file containing “Last updated” and “Total tools” fields, category headings, and consistent fields for each tool. 2. I wrote a Claude Code Routine prompt that names the newsletters, specifies the fields to extract, and instructs the workflow never to invent a URL, never to delete an entry, and only to add or update tools. 3. I scheduled the routine to run daily with Gmail access. 4. Each day, the routine searches Gmail for newsletters from the previous 24 hours, reads them, extracts AI tools, skips non-AI items and pure ads, preserves genuine tool sponsors, and checks Trash or Deleted items when necessary. 5. The routine checks for duplicates, adds new tools alphabetically under the right category, updates existing tools with fresh details, creates categories when needed, and applies the “Highly Mentioned” tag to tools found in at least three sources. 6. The routine commits and pushes the Markdown catalog to the private GitHub repository and posts a summary to Slack. 7. I built the frontend with Vite and React, including a statistics header, a scrollable message list, an input box, and example questions. 8. I added two backend functions: one for statistics and one for chat, with the GitHub fetch handled by a shared helper with a short cache. 9. I created a fine-grained, read-only GitHub token limited to the single repository. 10. I deployed the site to Netlify with the required keys stored as environment variables rather than in the code. 11. When I ask a question, the backend fetches the Markdown catalog, sends it to Claude with my question, and returns the matching tools, descriptions, and links.

I used Claude Code to build a 13-agent workforce for generating micro-courses. Each agent has its own job description and a defined role in the workflow, which begins with document analysis and ends with a course package agent delivering a complete, interactive HTML prototype as a local file. The agentic workforce creates knowledge-check quizzes with corrective feedback. Each micro-course also includes a downloadable handout highlighting the main points. In my case, a human course builder receives the final interactive HTML prototype and uses it to update our organization’s course catalogue. The HTML file is available for everyone to use as well. This reduced the production time from three months to two hours at most. I also included a security gate that redacts information from transcripts used to create course content. I’m happy to share more—we’re talking about folders and files here. Step-by-step: 1. I used Claude Code to build a 13-agent workforce for generating micro-courses. 2. I gave each agent its own job description and defined workflow. 3. I started the workflow with document analysis before the work begins. 4. I used a course package agent to deliver a complete, interactive HTML prototype as a local file. 5. I had the workforce create knowledge-check quizzes with corrective feedback. 6. I included a downloadable handout with highlights at the end of each micro-course. 7. I sent the final interactive HTML prototype to a human course builder, who updates our organization’s course catalogue from it. 8. I added a security gate to redact information from transcripts used for course content. 9. I made the HTML file available for everyone to use.

I built a meal tracker where my only job is to photograph a plate and send it to an agent. Identification, portion estimates, macros, storage, corrections, and the weekly review happen without me. The part worth stealing isn't the food. The agent has its own email address and iMessage thread, so anything I can send from my phone becomes an input. I send a photo through whichever channel takes fewer taps. I send corrections as plain English with `CORRECTION` in the subject, and answer questions in the same thread. There’s no app and no form. Adding a channel took an afternoon and changed what the agent could be pointed at—the tracker is just one use of an agent you can talk to. It polls on a schedule instead of using a webhook because my laptop sleeps and a local gateway would be unavailable half the time. Storage is append-only JSONL. Corrections append a new record with the same ID using last-write-wins, so the stats layer sees one meal while the original estimate stays on disk. Every number can be traced back to the model’s first guess and my override. The accuracy mechanism is a challenge step. Every photo is estimated twice: first by the main model, then by a blind subagent that receives only the photo and the rubric—not the first answer. If it identifies different food, the entry is downgraded to low confidence and becomes a question for me. Testing before making the system autonomous caught bugs that otherwise would have failed silently. The API returns attachments under a different field than I had assumed, and only on the detail endpoint. As a result, a photo email was read as having no attachments, and every meal photo would have been dropped while the daily task logged a tidy “no new meals” and appeared healthy. The send path was separately broken, which would have killed the weekly review on a Sunday even with everything upstream working. A silent no-op that produces a plausible clean run is what this category of build is prone to. The bug that actually cost me was token usage: each blind challenge read used about 44,000 tokens, so a five-photo dinner cost roughly 220,000 tokens for one meal and capped my usage. The fixes, in order of effect, were to run the challenger on a cheap model, skip it once a named product or my confirmation has settled the entry, downscale photos for viewing, and republish the dashboard only when the data changes. Measuring first mattered—I would have blamed photo size, but that was the smaller half. The honest limits are important: calorie estimates from a photo are 20–25% off at best, identification error is a bigger risk than arithmetic error, and alcohol, water, and caffeine are never estimated from photos. The sequence in which I asked for things mattered more than any single instruction: Step-by-step: 1. I gave the goal and the one ingestion mechanic I was sure about, then insisted on an agreed plan before any code. Arguing about storage and failure modes is cheap before code is attached. 2. Before scheduling anything, I processed one real input end to end in front of me, including every outbound path. Inbound gets tested because I use it; the reply and the weekly digest do not. 3. When the agent reported something about my own input that I knew was wrong, I said so and made it re-check. Confidently wrong answers about things I witnessed were the cheapest bugs to find. 4. I asked for an independent second assessment of anything estimated rather than read, and decided up front what level of agreement was enough to accept the result. 5. I asked for a visible audit surface showing every field the agent claims to track, with a correction control on it. 6. I asked the agent to look up anything knowable rather than estimate it. A named product is a lookup; only the unnameable needs a guess. 7. I treated approval friction and token cost as requirements rather than complaints, and measured before changing anything. Almost every rule exists because something went wrong in ordinary use, not because it was designed up front. An agent I can email or text, which keeps records and answers back, is general-purpose; I’ve pointed it at one narrow job. What else would you point it at?

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.

My doctor asked me to track my blood pressure for a month because it was on the high side before prescribing any medication. I initially recorded each reading manually in an Excel sheet, but after a few days, I wanted a simpler way to enter and manage the data. I uploaded the sheet to Claude Code and asked it to build a blood pressure tracking app. After the app was built, I hosted it on Netlify, used Supabase as the backend to save data for both my wife and me, and added it to my iPhone Home Screen. Step-by-step: 1. I started tracking my blood pressure in an Excel sheet as my doctor requested. 2. After several days of entering the readings manually, I uploaded the sheet to Claude Code. 3. I asked Claude Code to build an app for tracking blood pressure. 4. I hosted the app on Netlify. 5. I used Supabase as the backend to save blood pressure data for both my wife and me. 6. I saved the app to my iPhone Home Screen for easier access.

I’m 71 years old, retired from owning a large cattle-feeding operation, and fairly new to AI and software development. I’ve discovered that I really enjoy using AI to build practical tools in Replit. My latest project is an app for our church to help us oversee a $13.5 million renovation of a 65,000-square-foot former movie theater into our new church facility. I’m not a programmer or a construction expert, so I’m using AI to help bridge both gaps. I built the app almost entirely by describing in plain English what I wanted it to do, testing what it built, and working back and forth with AI to improve it. The app uses AI to read meeting notes, emails, texts, and general project updates and identify decisions, action items, important dates, budget changes, and project events. Nothing is accepted automatically. I review, edit, approve, or reject what AI finds before it becomes part of the project record. The app also keeps our budgets, documents, meetings, and project history together. My goal isn’t to replace our project manager or construction software. I want to see whether someone my age, with no programming or construction background, can use AI to build a useful tool for helping an owner understand and manage a complicated real-world project. Step-by-step: 1. I described in plain English what I wanted the app to do. 2. I used AI in Replit to build the app based on those descriptions. 3. I tested what AI built and worked back and forth with it to improve the app. 4. I designed the app to read meeting notes, emails, texts, and general project updates. 5. I use it to identify decisions, action items, important dates, budget changes, and project events. 6. I review, edit, approve, or reject every item before it becomes part of the project record. 7. I use the app to keep our budgets, documents, meetings, and project history together.

Most AI agents are built around general best practices. That’s useful, but it doesn’t mean they work the way I want them to. I’ve started using a simple calibration process to tailor my agents to my preferences. Instead of telling an agent what to do on each task, I have it interview me about how I like work done in its specific domain. A writing agent asks different questions than a research agent, and a strategy agent asks different questions than a coding agent. The goal is to make my working preferences part of how the agent operates. Step-by-step: 1. I pick an agent I use regularly, such as one for writing, research, strategy, coding, analysis, or career advice—especially where my personal preferences matter. 2. I ask the agent to interview me about how I prefer work to be done in its domain. A writing agent might ask about tone, structure, editing style, and how much pushback I want. A research agent might ask about source quality, depth, recency, citations, and how much synthesis I prefer. 3. I have the agent summarize what it learned and separate durable preferences from temporary or situation-specific ones. 4. I review the proposed changes and ask the agent to show me exactly how it wants to update its instructions or skills. I correct anything it misunderstood and explicitly approve the changes before anything is modified. 5. Once I approve the changes, I have the agent apply them to its instructions or skills so those preferences become part of how it works going forward. 6. I use the agent normally and pay attention to where it feels more aligned and where it still misses the mark. 7. When I notice recurring friction, I add or adjust the relevant preference instead of repeatedly correcting the same behavior task by task. 8. I repeat the interview periodically. My preferences, tools, and workflows change, so the agent should be able to ask which preferences are still valid, which ones I keep overriding, what has been annoying me, and what should be added or removed. The result is an agent that doesn’t just know how to do the job; it knows how I want the job done. Because every change is proposed and approved before it becomes permanent, the personalization stays intentional rather than turning into a collection of guesses about me.

AI chatbots have limitations around memory, numbers and types of attachments, connectors, storage, and other resources. The underlying LLMs also change over time, and data leakage is a concern. Code-based versions such as Claude Code and Grok Build can store essentially unlimited files on your computer, organize them with databases and files, connect to public and private MCPs, and even host interfaces for reviewing results. You can choose between a hosted LLM such as Claude, Grok, or ChatGPT and a local LLM if you prefer. The best part is that these code-based versions have no memory between sessions: everything is stored on your computer, assuming a basic subscription. You start by prompting the system about the domain, what you want to store, how you want to access it, and other requirements. Then it creates the system for you. I started with my own personal health archive. I'm comfortable using the terminal interface for Claude Code and Grok Build, so I use that directly. When I built one for my wife, she couldn't use the terminal, so I had it build a basic website with Q&A interfaces, data access, and upload functionality. I hosted it on my Mac, and I wrote no code. We loaded hundreds of documents in various formats into each of our instances without any trouble. When we have new files, we can simply drop them in. For specific questions or health events we're tracking, the system has perfect memory and no memory limits within the archive. For my archive, I use a Garmin watch and a food tracker. Because public MCPs weren't available for those services, I had the system build local MCP servers by reverse-engineering them. My health tracker now has a continual feed of my food, fitness, sleep, and other data. My wife has some chronic health issues, and we had reached a point where the standard chatbots were hitting their limits. We were struggling and didn't know what to do, so I discussed it with Claude, and we came up with this approach. The best part, besides getting a better handle on our health, is that I can launch any LLM within the project—Claude, Grok, or others—and use it for that session. The project isn't tied to or limited to a single LLM. That lets me manage costs, switch to better LLMs as they improve, and use specialized models for deep research, all while working with one data set. Step-by-step: 1. I prompted a code-based AI about the health domain, the information I wanted to store, and how I wanted to access it. 2. I created a personal health archive and loaded hundreds of documents in various formats into it. 3. I built a second archive for my wife with a basic website, Q&A interfaces, data access, and upload functionality, then hosted it on my Mac. 4. I added new files by dropping them into the appropriate archive. 5. I had the system build local MCP servers for my Garmin watch and food tracker by reverse-engineering those services when public MCPs weren't available. 6. I used the resulting health tracker to maintain a continual feed of food, fitness, sleep, and other health data. 7. I launched different hosted or local LLMs within the same project as needed for each session, including using specialized models for deep research.

Organic social content is one of the best sources of ideas for ads, so I built a workflow that finds short-form videos performing well in my niches, analyzes why they work, and rewrites the strongest hooks for my brand. Apify scrapes Instagram Reels by hashtag and TikTok videos by keyword across three niches: AI, productivity, and career growth. The workflow filters for English-language videos posted within the last 15 days that are 15–90 seconds long and have more than 50,000 plays. It then ranks them by engagement rate rather than views alone. A simple log file tracks every video I’ve already analyzed, so the workflow doesn’t process the same video twice. ElevenLabs transcribes each video’s audio. Claude then extracts the exact opening line, identifies the hook formula and video structure, and writes a version of the hook for my brand. Everything is compiled into one dated document with the top three discoveries, the strongest hook from the run, and any new patterns I haven’t tried yet. With one command—"Run research"—I get about 20 proven hooks and video structures to test in ads for less than $1 per run. Step-by-step: 1. I use Apify to scrape Instagram Reels by hashtag and TikTok videos by keyword across the AI, productivity, and career growth niches. 2. I filter the results for English-language videos posted within the last 15 days, 15–90 seconds long, with more than 50,000 plays. 3. I rank the remaining videos by engagement rate instead of views alone. 4. I check a log file to skip videos I’ve already analyzed. 5. I use ElevenLabs to transcribe each video’s audio. 6. I ask Claude to extract each video’s exact opening line, hook formula, and structure, then rewrite the hook for my brand. 7. I compile the results into one dated document with the top three discoveries, the strongest hook from the run, and new patterns to test. 8. I run the workflow with the command "Run research" to generate about 20 hooks and video structures for ad testing at a cost of less than $1 per run.

I've been thinking about the value of handoff documents and explanatory documents as we continue exploring efficient ways to work alongside AI to build software and improve communication. Even though we use many different tools, Markdown still has an important place. This new version of an HTML handoff document can document what exists, describe what could exist, or serve as a mockup for a brainstorm. It lets us communicate with remarkable fidelity through visuals, hierarchy, and formatting. It's also an efficient format for AI to understand. We shouldn't underestimate the significance of AI communicating with us through a visual medium. A visual flowchart with thoughtful design, layout, animation, and progressive disclosure can help us understand the logic and flow of incredibly complex systems much faster. I tried all kinds of tools, including React Flow and Mermaid. They're fun to experiment with, but Archify is a game changer for this use case. I can point it at any technology, repository, or brainstorm and work with it to build flowcharts with animations and clean, distinctive design. It's also completely free. https://tt-a1i.github.io/archify/# Step-by-step: 1. I identify whether I need to document what exists, explore what could exist, or mock up a brainstorm. 2. I use Markdown and an HTML handoff document to communicate the ideas with visuals, hierarchy, and formatting. 3. I consider tools such as React Flow and Mermaid for creating visual representations. 4. I point Archify at the relevant technology, repository, or brainstorm. 5. I work with Archify to develop a flowchart with animations, clean design, and progressive disclosure so the system's logic and flow are easier to understand.

My father-in-law has had some close calls with phishing attacks, so I built a digital bodyguard with Claude Code to watch over their email around the clock. It’s designed to catch scam and phishing attempts that are specifically crafted to fool people: fake bank alerts, urgent “click here” links, and messages pretending to be from someone they trust. When it spots one, it pulls the message out of the inbox into a separate folder and sends me an alert so I know it happened. I wrote up the full system, including the prompting and context, in GitHub: https://onabetternote.substack.com/p/using-ai-to-guard-against-email-scams?r=6ihgge&utm_campaign=post-expanded-share&utm_medium=web Step-by-step: 1. I built a digital email bodyguard with Claude Code to monitor my father-in-law’s email around the clock. 2. I configured it to look for phishing and scam messages, including fake bank alerts, urgent “click here” links, and messages impersonating trusted people. 3. When it identifies a suspicious message, it moves it from the inbox into a separate folder. 4. It sends me an alert whenever it takes action. 5. I documented the full system, including the prompting and context, in GitHub.