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

I built a custom AI knowledge-transfer GPT designed to prevent institutional knowledge from walking out the door when an experienced employee leaves. The trigger was an experienced operations manager preparing to leave the organization. I realized that while we had procedures, files, emails and account documentation, a huge amount of operational knowledge existed only in that manager’s head: customer preferences, recurring staffing problems, site-specific quirks, key relationships, historical issues, workarounds, lessons learned and the small details that can take a replacement months to discover. My goal was to capture that knowledge and turn it into an interactive resource for the incoming operations manager. First, I conducted and recorded an in-depth interview with the departing manager. Instead of only asking standard turnover questions, I had them walk through the operation as if they were personally training their replacement. We discussed customers, employees, locations, scheduling, recurring problems, escalation procedures, communication preferences, historical decisions and things they believed a new manager might not realize immediately. I then transcribed the conversation and used AI to analyze the interview for knowledge gaps. I asked the AI to approach the transcript from the perspective of someone taking over the job and identify important questions that had not yet been answered. Using those gaps, I had AI create customized knowledge-transfer questionnaires specifically for the departing manager. These asked more targeted questions such as: What problems happen repeatedly? What customer preferences are not documented? What exceptions exist to normal procedures? What mistakes is a new manager likely to make? What information exists only in your memory? What would you make sure your replacement understood during their first 30 days? The departing manager completed those documents, giving me another layer of institutional knowledge that would normally be lost. Next, I organized the interview transcript, completed questionnaires, operational procedures, account information, contacts, historical notes and other relevant documents into a knowledge base. I uploaded that information into a custom GPT and instructed it to function as an operational knowledge-transfer assistant. The GPT was told to base answers on the captured information, not invent answers when information was missing, and clearly tell the user when something needed to be verified. The incoming operations manager can now interact with that knowledge conversationally. Instead of searching through folders or wondering who to ask, they can say things like, “I’m meeting with this customer tomorrow. What should I know?”, “Has this location had staffing problems before?”, “Why do we handle this account differently?”, or “What should I watch for during my first month?” The GPT is now being used by the incoming manager as an ongoing reference tool. The result is essentially a searchable, interactive version of the institutional knowledge that previously would have disappeared with the departing employee. It reduces the “I don’t know what I don’t know” period of starting a new position, shortens the learning curve, improves operational continuity and helps prevent the next person from having to relearn years of lessons through trial and error. The same workflow could be recreated for retiring executives, salespeople, plant managers, administrators, project managers, maintenance supervisors or anyone whose experience contains valuable institutional knowledge. The employee can leave. Their knowledge doesn’t have to.

Instead of relying on a single AI chat, I structure the work as an executive team of specialist perspectives. I define the problem, assign roles such as CTO, product leader, economist, marketer, and skeptic, and have each expert analyze it independently. Then I run several rounds of critique so they can challenge one another’s assumptions before synthesizing their areas of agreement and disagreement. The process ends with a recommendation that includes the rationale and any remaining uncertainties. Step-by-step: 1. Define the problem clearly. 2. Assign specialist roles, such as CTO, product leader, economist, marketer, and skeptic. 3. Have each expert analyze the problem independently. 4. Run several rounds of critique in which the experts challenge one another’s assumptions. 5. Synthesize the areas of agreement and disagreement. 6. Produce a final recommendation with its rationale and remaining uncertainties.

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 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.

Turn a collection of documents, reports, spreadsheets, and notes into an evidence-backed decision brief with ChatGPT. Instead of asking AI to simply summarize the information, this workflow makes it identify what matters, connect the evidence, compare it with historical context, explore scenarios, and highlight what should be considered before making a decision. Step-by-step: 1. I gather the information relevant to one decision, including reports, PDFs, spreadsheets, research, historical data, meeting notes, and existing analysis. I upload everything into ChatGPT. 2. I ask ChatGPT to understand the situation using this prompt: > “Analyze the information I provided and build a structured understanding of the situation. Identify the key entities, important facts, relationships, metrics, trends, assumptions, and constraints. Do not make recommendations yet.” This creates the context before jumping to conclusions. 3. I build an evidence brief by asking: > “Create an evidence brief. Separate verified facts, derived insights, assumptions, conflicting information, and missing information. For every important conclusion, identify the supporting source or evidence.” This gives me a clearer picture of what is known versus what is inferred. 4. I add historical context when it is available by asking: > “Compare the current situation with the historical information provided. Identify meaningful patterns, similarities, differences, and changes. Highlight which historical observations could be relevant to the current decision.” This turns historical data into context rather than simply another report. 5. I explore three scenarios by asking ChatGPT: > “Based on the evidence and historical context, evaluate three scenarios: upside, base case, and downside. For each scenario, identify the assumptions, key drivers, risks, likely impact, and evidence supporting the assessment.” The objective isn't to pretend the future can be predicted perfectly. It is to understand how the decision changes when assumptions change. 6. I generate the decision brief by asking: > “Create a concise decision brief containing: > > 1. Current situation > 2. Most important evidence > 3. Key insights > 4. Historical context > 5. Critical assumptions > 6. Key risks > 7. Scenario analysis > 8. Evidence gaps and uncertainties > 9. Questions that should be investigated > 10. Possible actions and their implications. > Do not make the final decision on my behalf.” This produces a structured decision brief instead of another AI-generated summary. 7. I review the brief and challenge its conclusions before making the decision. I ask follow-up questions such as: > “Which assumption has the greatest impact on this decision?” > “Show me the strongest evidence against the current conclusion.” > “What information would most likely change the recommendation?” The AI helps structure the decision, but I make the decision. The important shift is: Summarize the information → Understand the situation → Establish the evidence → Add historical context → Explore scenarios → Evaluate the decision This approach can be applied to almost any domain where decisions depend on complex and interconnected information. A property investment is one example. A business strategy, product decision, operational problem, financial analysis, research question, or engineering decision can follow the same pattern.

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.

Most days, I want one capable general AI agent. The failure mode appears with higher-stakes questions in security, finance, law, or medicine: my main chat is already full of project context, the agent may answer confidently outside its depth, and a “specialist” prompt in the same thread still inherits the assumptions and tools that session has already loaded. I set up Hermes Agent with a consultation workflow that cold-starts an isolated specialist profile for a one-shot answer. I keep four advisors ready: security, financial, legal, and medical. Each call starts a separate process with its own model, tools, and skills. The specialist has no access to my parent conversation, so I have to write a self-contained prompt. It takes anywhere from a few seconds to a couple of minutes—not instantly—which is fine because I only use it when the stakes justify the wait. The gate is the part I care about most. Nothing runs until I explicitly name the profile, approve the exact prompt, and confirm. There is no silent auto-routing. When I want a second opinion, I draft my own take first, send the same question to the specialist, and compare where we agree and differ. This keeps the general agent honest and prevents specialty advice from becoming the default for routine work. I also keep the scope tight. I limit the medical profile to personal or educational questions, or fully de-identified material—not identifiable patient care. Routine work that my main agent already handles well never goes through consultation. I reserve the specialist profiles for deliberate second opinions or questions I do not want the default session answering alone. Step-by-step: 1. I work through the problem in my main Hermes session and write my own answer first when I want a second opinion. 2. If the question is high-stakes in security, finance, law, or medicine—or I simply want a deliberate second look—I choose the specialist profile to use. 3. I write a self-contained prompt with every fact and constraint the specialist needs because it cannot see the parent chat. 4. I name the profile, approve the prompt, and confirm before anything runs. 5. I let Hermes cold-start that profile as a separate process and return a one-shot answer. 6. I compare my draft with the specialist’s response: where we agree, where we differ, and what still needs a human professional. 7. I skip consultation for routine work and keep medical use limited to personal, educational, or de-identified material.

My calendar is wall-to-wall meetings, so I built a Scheduled Claude Cowork task that automatically preps me for all of them (sort of like an AI Chief of Staff). Every morning, it scans my calendar, then pulls past emails, Slack, and my Granola notes for each call to build a context brief that takes 30 seconds to read before each meeting. It's simple and keeps me sharp for every meeting. Step-by-step: 1. I created a Scheduled Claude Cowork task that runs before my meeting day begins. 2. I had it scan my calendar and identify every meeting that needed preparation. 3. For each call, it pulled relevant past emails, Slack messages, and Granola notes. 4. I asked it to synthesize those sources into a short context brief with the information I would need in the room. 5. I read each brief in about 30 seconds immediately before the meeting.

I’ve been using a simple AI workflow to capture and act on my best ideas before they get lost between meetings. It’s been so useful that I wanted to share it for others to borrow. Here’s what I do: Step-by-step: 1. While walking between meetings, I open Wispr Flow on my phone and dictate every idea and takeaway into an Apple Note, completely unstructured. The goal is to get everything out of my head before the next meeting overwrites it. 2. The notes sync automatically to my Mac, where a scheduled Claude task runs at the end of the day through the Claude Desktop app and simple connectors. It reads all the voice notes I’ve added. 3. Claude structures the notes in Notion, where I do most of my work, turning them into to-do tasks with key ideas, action items, and suggested deep-work blocks in my calendar for the bigger items. I no longer stress about forgetting important meeting takeaways because, by morning, I have actionable next steps waiting for me. I never have to touch my keyboard.

Microsoft is retiring Publisher on October 1, 2026. I have many `.PUB` files that I need to convert to PDFs before then, but I did not want to use online converters. I wanted a solution that would run locally on my computer. I worked with Claude to create a lightweight program that searches for `.PUB` files on a drive of my choice and converts them into high-quality PDF files, placing each new PDF in the same folder as its source file. Opening PowerShell manually and managing permissions was too cumbersome, so Claude also created a batch file to make the process easier. For anyone who wants to create their own mini-program, I asked Claude to create a reusable prompt. I posted that prompt at https://mediumseagreen-seal-177480.hostingersite.com/ along with my two files: the batch file and the PowerShell commands. Step-by-step: 1. I identified the `.PUB` files I needed to convert before Microsoft retires Publisher on October 1, 2026. 2. I decided to use a local solution instead of an online converter. 3. I worked with Claude to create a lightweight program that searches a selected drive for `.PUB` files. 4. I set up the program to convert the files into high-quality PDFs and place each PDF in the same folder as its source `.PUB` file. 5. I used a batch file created by Claude so I would not need to open PowerShell manually or manage permissions each time. 6. I asked Claude to create a reusable prompt for others who want to build their own version and posted it with the batch file and PowerShell commands at https://mediumseagreen-seal-177480.hostingersite.com/.

AI is good at generating polished answers, but polished answers are not always your answers. When people ask AI for help with writing, strategy, or difficult decisions, it can jump too quickly to a conclusion and fill in beliefs the user has not fully examined. I created a thought-partner agent that interviews me before producing recommendations or drafts. Its job is to ask probing questions, challenge weak assumptions, surface contradictions, and separate my actual views from ideas suggested by the AI. Instead of writing for me immediately, it helps me clarify my position first. Step-by-step: 1. I give the agent the topic, decision, or idea I want to explore. 2. I tell it not to draft the final output yet. Its first job is to interview me. 3. I have it ask one focused question at a time about my reasoning, evidence, assumptions, audience, and uncertainty. 4. I require it to challenge vague claims and point out contradictions or overlap with my previous thinking. 5. I ask it to clearly separate: - conclusions I stated - ideas the AI proposed - issues that remain unresolved 6. I continue until the central belief, argument, or decision becomes clear. 7. I have the agent create a structured synthesis containing the core thesis, supporting reasoning, counterarguments, open questions, and useful language from the discussion. 8. I pass that synthesis to a writing, planning, or execution agent. I end up with a position that reflects my actual thinking rather than a plausible answer generated by AI. The final writing or strategy is more original, more consistent, and easier for downstream agents to execute.

I come across a public social video—a Reel, TikTok, or short clip—with an idea, process, or tool worth keeping. Rather than saving it and forgetting it, I drop the link into my capture workflow. I also use the workflow for clips I have permission to upload or process. The workflow extracts useful information from the video. It creates a transcript of the spoken content and captures key frames when useful information appears on screen. AI then turns that raw material into a structured research note covering the main idea, any reusable framework or step-by-step process, tools or prompts mentioned, constraints, and whether the item should become a project, opportunity, reference, watchlist item, or be ignored. I save the finished note in Obsidian with the original source link so I can search for it later and trace where the idea came from. Each note ends with one recommended next action, turning the video into something I can act on rather than another forgotten save. I only process public content or content I have permission to use, and I label rough transcripts as rough rather than treating them as perfect. Step-by-step: 1. I find a public Reel, TikTok, or short video containing an idea, process, or tool worth keeping. 2. I add the video link to my capture workflow, or upload a clip I have permission to process. 3. I create a transcript of the spoken content and capture key frames that contain useful information. 4. I use AI to turn the transcript and frames into a structured research note covering the main idea, reusable frameworks or processes, tools or prompts, constraints, and the appropriate category. 5. I save the note in Obsidian with the original source link and label any rough transcript accordingly. 6. I end the note with one recommended next action so I can act on the idea.

Granola transcribes my one-on-ones with my boss. I use its API and an HTML dashboard to automatically ingest and categorize the conversations. A scheduled task and skill then process them into a “wiki.” In a custom project, I can ask how my boss would respond to a question. The results are scary good. Step-by-step: 1. I use Granola to transcribe my one-on-ones with my boss. 2. I use the API and an HTML dashboard to ingest and categorize the conversations automatically. 3. A scheduled task and skill process the one-on-ones into a “wiki.” 4. I ask a custom project how my boss would respond to a question.

I started with a problem: Most people use AI transactionally. They ask a question, get an answer, and leave. That makes AI useful, but it leaves much of its potential untapped. I wanted to find out what would happen if a human and an AI developed an ongoing working relationship—one where context, previous discoveries, disagreements, successes, failures, and the human’s way of thinking accumulated over time. I use ChatGPT, but the goal isn’t to have AI think for me. I remain the decision-maker. The AI’s job is to expand my ability to think: challenge assumptions, identify blind spots, connect seemingly unrelated information, preserve useful context, and sometimes disagree with me. Step-by-step: 1. I established the relationship by telling the AI that I didn’t simply want agreement or answers. I wanted an ongoing thinking partner that could challenge my reasoning while leaving decisions and agency with me. 2. I established operating roles. Over time, ours developed into six modes: Mirror, Builder, Sentinel, Teacher, Witness, and Operator. The AI can reflect my reasoning, help construct something, identify risks or contradictions, teach unfamiliar material, observe patterns across conversations, or help execute a defined task. 3. I separated knowledge from judgment. When we solve difficult problems, we distinguish between facts, reasonable inferences, unknowns, and opinions. This helps prevent a confident AI response from being mistaken for established truth. 4. I let disagreement remain in the system. I correct the AI when it’s wrong, and it challenges me when my assumptions don’t fit the evidence. Instead of treating those moments as failures, I treat them as part of the accumulated context of the relationship. 5. I preserved useful context across different domains. I use the same AI relationship for automotive diagnostics and engineering, business decisions, financial reasoning, writing, research, project planning, and philosophical questions. Something learned in one area can unexpectedly become useful in another. 6. I evaluated the human, not just the AI. The final test isn’t, “Did the AI produce a good answer?” It’s: Did this interaction leave the human better able to understand the problem, make the decision, or solve the next one? After hundreds of conversations, something unexpected happened. The value stopped being any individual prompt or answer. It became the accumulated interaction itself. The AI gained context about how I reason, while I became better at questioning the AI. Previous discoveries started informing new problems, including problems that appeared completely unrelated. Someone can recreate this without special software, coding, or an API. Start with an AI that supports ongoing context or memory, establish the operating principles above, use it consistently across real problems, correct it when it’s wrong, invite disagreement, and allow useful context to accumulate. My original experiment was essentially this: Can an ongoing human-AI relationship make the human more capable rather than more dependent on the AI? Somewhere along the way, I realized we had built a framework for doing exactly that. We gave it a name: Confluxus. The measure of its success isn’t how much the AI can do for me. It’s how much more capable I become because of the relationship.

Many organizations have critical process knowledge that exists only in employees’ heads. When someone has a question, they have to track down the right expert, ask questions others may have already asked, and hope they remember every detail. This doesn’t scale and creates knowledge silos. I built a workflow that turns conversations with subject matter experts into structured, searchable organizational knowledge. Instead of asking employees to write documentation, an AI interviewer guides them through the process they know best, converts the conversation into well-structured documentation, and publishes it to an AI-powered knowledge base that anyone can query. Step-by-step: 1. Ask an employee to choose a business process they know well. 2. Have an AI interviewer ask follow-up questions to capture the complete workflow, decisions, exceptions, and best practices through a natural conversation. 3. Save the interview transcript. 4. Use an LLM to convert the transcript into structured documentation with clear sections, steps, decision points, and FAQs. 5. Store the documentation in a searchable knowledge repository and index it in a vector database. 6. Let employees ask questions through an AI assistant that retrieves the most relevant documentation and answers in natural language. 7. Repeat the process over time as processes evolve or additional experts contribute new knowledge. Instead of repeatedly interrupting the same subject matter experts, employees can get consistent answers from an AI assistant backed by documented organizational knowledge. The organization captures valuable expertise before it’s lost, reduces knowledge silos, improves onboarding, and creates documentation simply by having conversations.

I built an AI meeting-intelligence workflow that turns my meetings, emails, chats, and handwritten notes into one living action tracker. Every action stays linked to its original source, and the workflow automatically generates a prep sheet for each meeting. Two problems drove me to build it. First, provenance: action lists are often disconnected from their sources. A line such as “follow up with vendor on pricing” is much less useful when I can’t open the Teams message or email it came from to review the details or reply. The context disappears as soon as the action is recorded. Second, I take most of my notes by hand because I think better on paper. Those notes used to be a dead end: they never entered any system, so the follow-ups disappeared. The workflow runs on a morning schedule or on demand before a meeting. I use Claude in Cowork with MCP connectors for email, chat, and calendar. It pulls recent messages and upcoming meetings while capturing the deep link or ID for each source item, so every action can be traced back to the exact email or Teams thread. For handwritten notes, I photograph the pages into a OneDrive folder and tag them. The workflow uses OCR and vision to extract the text and action items. Quick shorthand tags—`action`, `prep`, and `done`—on messages and photos tell it what to track or close. A Python layer then deduplicates the actions, assigns each one a stable ID, applies the tags, and updates the master tracker while preserving the source links. The result is one self-maintaining action list. I can click any item to return to its original artifact to reference the details or reply, and my paper notes finally flow into the same system. To recreate it, connect an AI assistant to your mail, chat, and calendar through MCP and store each source link with its action. Add a OneDrive photo drop with OCR for handwritten notes, use a simple tag vocabulary, and separate the responsibilities: let the AI handle capture and OCR, while plain code handles deduplication, IDs, and status updates. Step-by-step: 1. I scheduled the workflow to run each morning and added an option to run it on demand before a meeting. 2. I connected Claude in Cowork to my email, chat, and calendar through MCP so it could gather recent messages and upcoming meetings. 3. I captured the deep link or ID for every source item, allowing each action to trace back to the exact email or Teams thread. 4. I photographed handwritten notes into a tagged OneDrive folder and used OCR and vision to extract their text and action items. 5. I used the shorthand tags `action`, `prep`, and `done` on messages and photos to indicate what to track or close. 6. I used a Python layer to deduplicate actions, assign stable IDs, apply tags, and update the master tracker without removing source links. 7. I used the resulting tracker to return to the original artifact for each action and to bring paper-note follow-ups into the same system.

The workflow starts when a project grows beyond one conversation and approved decisions, file versions, or next steps become difficult to track. I begin by creating one active authority document. It is not a transcript of every discussion; it contains only the rules, definitions, methods, and structural decisions that currently control the project. Next, I label project files by status: active, working, superseded, or archived. I also state clearly which file is authoritative instead of expecting the AI to infer it from the filenames. As decisions are approved, I record them in the authority document or a change log. I include what was decided, why it was decided, what it affects, and whether it needs later review. This keeps the chat from becoming the only project record. For large deliverables, I divide the work into named stages. A spreadsheet project might move through architecture, data migration, calculations, validation, and publication. Each stage produces a separate file and has a clear completion check. When a conversation gets too long, I create a handoff prompt for the next chat. It includes: - the project goal; - the active authority files; - completed work; - approved decisions; - unresolved issues; - the next specific deliverable; - anything that should not be redesigned. I start the new conversation with that prompt and only the files needed for the next stage. Finally, I validate the output outside the chat. For Excel files, that means opening them in desktop Excel, checking formulas and errors, saving them, closing them, and reopening them. An AI-generated file is not finished until it passes that check. The core pattern is to record the authority, label the versions, log decisions, work in stages, create a clear handoff, and validate the result. Step-by-step: 1. I create one active authority document containing the project’s current rules, definitions, methods, and structural decisions. 2. I label each project file as active, working, superseded, or archived, and identify the authoritative file. 3. I record approved decisions in the authority document or a change log, including the decision, rationale, effects, and any need for later review. 4. I divide large deliverables into named stages, with a separate file and clear completion check for each stage. 5. I create a handoff prompt when a conversation becomes too long, covering the project goal, authority files, completed work, approved decisions, unresolved issues, next deliverable, and anything that should not be redesigned. 6. I begin the next conversation with the handoff prompt and only the files needed for that stage. 7. I validate the final output outside the chat—for Excel files, by opening them in desktop Excel, checking formulas and errors, saving, closing, and reopening them.

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 use reusable AI skills rather than relying on one long prompt or previous chat history. I start by describing the project in plain English and invoking a project-kickoff skill. It creates a live project specification containing the objective, scope, constraints, acceptance criteria, concerns, and next actions. For larger or more ambiguous work, I can opt into a scope-discovery skill. AI guides me through one important decision at a time, explains the trade-offs, recommends a sensible default, and records each accepted decision until the project is ready to implement. When delivery involves several dependent or risky steps, I can use a runbook-design skill. AI converts the agreed scope into a checkpointed implementation plan with validation, rollback, and clear points where my approval or testing is required. AI then executes the runbook, builds the solution, performs automated checks, and records what actually happened. I mainly provide direction, answer business or product questions, and complete the human acceptance checks that AI cannot genuinely perform itself. The skills live inside the project repository alongside the code, decisions, runbooks, and documentation. Codex only links to them at runtime, so the repository remains self-contained and does not depend on my local setup or previous conversations. This also makes the workflow portable. Another capable AI agent or a human engineer can read the repository, understand how the project should be managed, and continue the work without reconstructing everything from chat history. Step-by-step: 1. I describe the project in plain English and invoke the project-kickoff skill. 2. I use the scope-discovery skill for larger or more ambiguous work, working through one decision at a time until the project is ready to implement. 3. I use the runbook-design skill when delivery involves dependent or risky steps, creating a checkpointed plan with validation, rollback, and approval or testing points. 4. AI executes the runbook, builds the solution, performs automated checks, and records what actually happened. 5. I provide direction, answer business or product questions, and complete the human acceptance checks AI cannot genuinely perform. 6. I keep the skills, code, decisions, runbooks, and documentation together in the project repository so the workflow remains self-contained and portable.

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.