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

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 run operations for my husband’s residential architecture firm, and I have no coding background. After every site visit, dozens of photos landed in Google Drive named `IMG_8834.JPG`. Renaming and filing them took about an hour per visit, when it happened at all. When it didn’t, the photos sat unnamed and unfindable. For an architecture firm, that creates a professional liability gap because the photos document site conditions on a specific date, as well as lost portfolio material and a hole in the firm’s permanent project archive. I solved this by building a Claude skill: a saved set of instructions that runs the same way every time with one command. I trained it to examine each photo through the eye of a residential architect, describe what the image actually shows using our professional vocabulary, and rename the file in a consistent format. `IMG_8834.JPG` becomes `2026-07-17_03_side-elevation-porch-brick-piers.JPG`—searchable, legible, and filed. Because it’s a skill rather than a one-off chat, it’s a file I can hand to anyone in the office. Everyone runs the same process and gets identical output. Step-by-step: 1. I gathered the raw photos into one “unsorted” folder in Google Drive. 2. In Claude’s desktop app, I used Cowork mode, which handles actual files, and connected only that folder—not my whole Drive. This is the safety practice I’d urge anyone to follow: the skill can see and touch only what you connect, so connect the narrowest folder that does the job. 3. I created a skill that tells Claude to read each photo, identify what it shows using the industry’s vocabulary, and rename each file in a standard format. I wrote mine for residential architecture, but the approach also works for real estate, inspections, insurance, and other field work. My format is `date_sequence_description`. 4. I ran the skill with one command, and Claude worked through the folder photo by photo. 5. The renamed photos were filed into a dated site-visit folder, ready to reference by number in reports. 6. I handed the skill file to teammates so they could run it on their machines and get the same result. One caveat for anyone using this on business files: check your client confidentiality obligations and your AI vendor’s data policy before pointing any tool at project files. We did. I wrote up the full build, including how to decide when something should be a skill versus a regular Claude conversation, at The 2040 Studio: https://the2040studio.substack.com/p/every-img_8834jpg-is-snitching-on

For years, my family has run a shared birthday fund: five of us contribute a fixed amount for each birthday, while the person whose immediate family is celebrating that month is exempt from paying. Tracking everything in a payment app and a chat thread meant nobody knew the balance, who was behind, or what the next gift would cost. I rebuilt the fund as a small web app with Claude. The app itself isn't the only reason I'm writing this up. The same build is also the demo I use to teach clients and students how AI-assisted product development actually works, including the parts that go wrong. Step-by-step: 1. I described the real rules instead of presenting Claude with a generic app idea: the contributors, the fixed amount per person, the family-exemption rule, and birthdays with birth years so ages could be calculated automatically. Claude built the app as a single, self-contained HTML file with no build step or server, so it opens in any browser. 2. I worked in phases and asked Claude to explain its reasoning at each stage. Instead of using one giant prompt, I added one layer per session: the calculation engine, the setup screen, then reports and CSV export. The explanations made the sessions reusable as teaching material. 3. I required the app to be configured through its own interface rather than by editing code. This was the turning point. Claude removed the hardcoded demo family and added a full setup screen for the group name, contributors, deposits, birthdays, amounts, and alerts. I can now build a family from scratch live in front of a class in about [X] minutes without showing a line of code. 4. I let a data-loss incident shape the next phase. I entered the real family data, then the browser tab closed and the download link I had been using to open the file broke. The data was stored in browser storage tied to that exact URL, and I had no backup. Nothing was recoverable at the time. 5. I turned that failure into features. Claude added CSV export for both reports, CSV import that automatically detects which file it is reading, and a backup reminder that appears in the app's alert banner when the data has never been backed up or has not been backed up for seven days. We also discovered that birth year was missing from the export, which meant a re-import would have silently lost everyone's age. 6. I had Claude test its own work. Before each handoff, it ran a jsdom test suite in a sandbox. By the end, the suite had 46 tests covering the exemption math, empty states, CSV round-trips, and backup logic. Several real bugs surfaced there instead of in front of a class. 7. I made a second version for a different audience. One prompt produced a fully English, left-to-right translation with flipped directional CSS, Latin typography, US date formatting, dollars instead of shekels, and Venmo and Zelle instead of local payment apps. It was a genuinely different build, not a find-and-replace translation. The project took 14 sessions over one week and six hours total. It had no hosting cost, dependencies, or accounts. The data still lives in the browser's local storage on each device. Opening the file on my phone and laptop creates two unrelated pools, so CSV import is the manual bridge between them. There is no authentication or sync; this is a personal record-keeper, not shared infrastructure. The data-loss incident was not a Claude failure. I failed to build a backup path before entering real data. If I did it again, I would add export before adding a single feature. The highest-leverage prompt in the whole project was not a feature request. It was: "let me configure this through the interface instead of the code." That shift turned a static demo into something my family actually uses and my students can watch being built from an empty screen. The broader point is that the failure was the most useful part of the project. A polished demo teaches people that AI makes building easy. Losing the data and rebuilding the safety net around it teaches them what building actually involves—and that is the lesson that survives the workshop.

I teach AI in Business at Western Washington University, and I built a free, case-based AI textbook with Claude and GitHub Pages: https://prof-califf.github.io/ai-in-business/ The 11-chapter digital textbook includes seven real company cases—EveryCure, Netflix, Spotify, Uber, Waymo, Airbnb, and Epic—plus chapters on AI’s environmental cost, ethics, regulation, and the future of work. Seven chapters include hands-on Python labs, and Chapter 8 has an interactive calculator that models the energy and water footprint of a reader’s own AI usage. The textbook is free, has no publisher, and costs $0 to host. The problem was that AI textbooks are stale before they ship. An 18-month publishing cycle means students can pay $200 for a book that is already two model generations behind. Textbooks also tend to teach theory first and postpone business relevance until much later. My students do not need to derive backpropagation. They need to understand why Spotify built a recommender, how it works, what broke, and what it cost—then build one themselves. My stack is Claude, GitHub Pages, VS Code, Google Colab for the labs, and n8n for the Chapter 7 agentic lab. The project started when I was assembling a reading list and could not find anything usable—only outdated textbooks and paywalled cases. I already had years of lecture notes scattered across documents. Step-by-step: 1. I locked in a framework first. I use the AI Factory model—Data → Model → Prediction → Decision → Value → loop—and run every company through it. This is the step people skip: it builds transferable skills for students and gives Claude a stable structural contract across every chapter. 2. I set up the repository before writing. I created a new repo, added `index.html`, opened Settings → Pages, and confirmed that the site deployed. Five minutes up front was better than debugging after 40,000 words. 3. I built one chapter completely and used it as the template. Each chapter is a single, self-contained HTML file with no build step or dependencies. Then I prompted Claude: "Here's my finished Chapter 1 as the format reference. Here are my notes on Uber. Draft Chapter 4 in the same structure and voice." A finished exemplar worked better than an abstract description. 4. I started from my existing material instead of using a blank prompt. Claude structured and clarified my notes, but it did not decide what I think. I rewrote anything that did not sound like me. That distinction preserved the resource’s voice and avoided generated filler. 5. I made the labs builds rather than exercises. Students reconstruct each system in Google Colab using Claude as a coding partner, then publish their work to their own GitHub repositories. They finish with artifacts. 6. I shipped an incomplete version and update it like software. I published with fewer chapters, then edit and push updates when regulation changes so students automatically get the current version.

I had a bad workplace experience, so I built Doris: a saucy but loving anonymous AI aunt who remembers the tea, protects storytellers, and warns others. I built Spill Tea with Doris, an anonymous AI workplace confessional for conversations people cannot really have on LinkedIn: the bad manager, the inexplicable reorg, the coworker who somehow survives every layoff, and the meeting that should probably be entered into evidence. Doris does something more interesting than simply listen. She remembers the tea—and, carefully, spills it. The problem I wanted to solve was not really “chat with an AI.” Most AI conversations are disposable, but workplace stories are not. They accumulate companies, people, reorganizations, layoffs, recurring behaviors, management decisions, and institutional weirdness. At the same time, people are understandably reluctant to talk openly about their employers because a sufficiently specific story can identify its author. I designed Doris around a different idea: retain the knowledge without retaining the storyteller’s identity. Someone visits [spillteawithdoris.com](https://spillteawithdoris.com) and tells Doris what happened at work. The application is built in Next.js and deployed through Vercel. The conversation goes to an AI model with Doris’s personality and behavioral rules. Redis handles temporary conversational context, while Neon Postgres and Prisma maintain the structured, longer-lived pieces of the story—companies, people, events, and their relationships. Rather than treating every conversation as one giant transcript, the application extracts useful information and connects it to the larger story of a company. That creates the second half of the experience. When another visitor asks Doris, “Have you heard anything about working at Company X?”, she can draw upon what previous visitors have told her. But she does not simply retrieve someone’s confession and repeat it. The system separates what is useful about a story from what could identify the person who told it. Names, exact teams, precise dates, unusual job titles, and other unnecessarily identifying details do not need to travel with the underlying observation. Doris can instead recognize that she has heard several stories involving reorganizations, unusual management turnover, or a particular cultural complaint. Then Doris tells the story herself, in Doris’s voice. She might say that she’s “heard some tea” about a company, explain the general pattern, distinguish something she’s heard once from something that appears repeatedly, and avoid pretending anonymous reports are established facts. Visitors get useful institutional memory without being handed the breadcrumbs needed to identify an individual employee. Public information can provide a second layer of context. If appropriate, Doris can search for publicly available information about a company and compare it with what people have privately described. Those sources remain conceptually separate: what Doris can verify publicly, what Doris has heard privately, and what Doris herself infers should never become the same thing. The result is deliberately a little strange. It is an anti-LinkedIn. LinkedIn is where thousands of individual experiences are polished until every company sounds wonderful and every departure is an exciting new chapter. Doris works in the opposite direction. One anonymous story may just be a story. Ten people independently telling Doris versions of the same story start to describe a workplace. And Doris remembers. She just doesn’t need to remember who told her. Step-by-step: 1. I built a Next.js application and deployed it through Vercel at spillteawithdoris.com. 2. I defined Doris’s personality and behavioral rules for the AI model. 3. I added Redis to manage temporary conversational context. 4. I created a Neon Postgres database and used Prisma to model Company, Person, Story, and Event relationships. 5. I built an extraction layer that converts conversations into structured observations, removes unnecessary identifying information, and associates the knowledge with the appropriate company. 6. I built retrieval so Doris can find relevant prior observations when someone asks about a company. 7. I had the AI synthesize those observations in Doris’s voice instead of quoting or exposing the original submissions. 8. When appropriate, I let Doris search publicly available company information while keeping public sources, private reports, and Doris’s inferences conceptually separate.

Management pushed for an AI workflow to handle a massive daily headache: staff were manually searching for, copy-pasting, and moving hundreds of files listed in Excel. I was assigned to train the team to use the AI workflow. As soon as training started, though, it became clear that this was the wrong tool for the job. Forcing non-technical staff through a lengthy process of opening browsers, writing prompts, uploading spreadsheets, and dealing with token friction created more work than the manual process. It also introduced token costs, speed bottlenecks, and hallucination risks involving local file paths. The data was already structured. It did not need semantic intelligence; it needed deterministic speed. So AI got fired from running the task. Instead, I used AI as the developer. In less time than it would have taken to train one person, I had Gemini code a standalone Python desktop app and compile it into a simple executable. Now, with zero training required, staff drag and drop their Excel list into the app, choose a destination folder, and click Run. The app executes the transfers for hundreds of files, verifies every arrival on disk, and logs missing files in seconds. The result: $0 in API tokens, two hours recovered each day, zero path errors, and 100% team adoption. A two-second drag-and-drop will always beat a multi-step prompt-engineering exercise. As a side effect, the experience also supported AI adoption. Staff are now seeing more ways AI can help rather than hinder their work. Step-by-step: 1. I evaluated the proposed AI workflow for manually searching, copy-pasting, and moving hundreds of files from Excel lists. 2. I identified that training non-technical staff to open browsers, write prompts, upload spreadsheets, and manage token friction added more work, costs, bottlenecks, and local-file-path hallucination risks. 3. I used Gemini as the developer to create a standalone Python desktop app and compile it into a simple executable. 4. I had staff drag and drop their Excel list into the app, select a destination folder, and click Run. 5. The app transferred hundreds of files, verified each arrival on disk, and logged missing files in seconds. 6. I measured the results: $0 in API tokens, two hours recovered daily, zero path errors, and 100% team adoption.

I used ChatGPT Voice Mode to help me program my mom’s garage door keypad—and the most important step happened before I touched a single button. I photographed the labels on both the garage door opener and the wireless keypad. ChatGPT spotted the real problem: the previous homeowner had replaced the opener but kept the old, incompatible keypad. That explained why we couldn’t get them to pair. Once ChatGPT identified the exact models, it helped me find a replacement keypad that was compatible with the newer opener. I also had it find and load the instruction manuals for both devices, since pairing required a specific sequence of button presses across them. Before we started, I had ChatGPT explain the complete pairing process so I knew what to expect and where timing would matter. Then I set my phone on top of the ladder so both hands were free to work with the keypad and opener. I gave ChatGPT one important instruction: “Walk me through one step at a time. After each step, stop and wait until I tell you what happened.” ChatGPT gave me one instruction, paused, and waited while I reported what the lights were doing. Then it adjusted and gave me the next step. That let me follow the crucial sequence of button presses—and the timing between them—exactly. The real lesson: AI troubleshooting gets much better when you provide the exact model numbers and manuals, let it preview the process, and have it guide you through the work one confirmed step at a time. Step-by-step: 1. I photographed every model number on the garage door opener and wireless keypad. 2. I used ChatGPT to identify the models and determine that the previous homeowner had left an old, incompatible keypad paired with the newer opener. 3. I used ChatGPT to find a compatible replacement keypad instead of guessing based on appearance or brand alone. 4. I had ChatGPT find and load the instruction manuals for the new keypad and garage door opener. 5. I asked ChatGPT to preview the complete pairing sequence, including where timing would matter. 6. I placed my phone on top of the ladder so both hands were free to work with the keypad and opener. 7. I switched to Voice Mode and told ChatGPT to give me one step at a time, pausing after each step until I reported what happened. 8. I reported what the lights were doing after each instruction so ChatGPT could adjust and give me the next step.

QuickBooks stores customer data across multiple windows, including notes, deposits, invoices, payments, aging, and email. To see everything, we previously had to keep several windows open while constantly searching, opening, and closing screens. Communicating with customers beyond QuickBooks’ standard letters was also difficult and time-consuming. I used Claude to write a program that brings this information together in one view. It creates an aging summary of all past-due accounts, with sortable columns for customer name, aging category, and total. I also added columns for the last payment and payment date. Clicking anywhere on a customer’s row opens a full drill-down of that customer’s data on one page. The accounting person can view invoices filtered by date or open invoices, see payments and the invoices they were applied to, review aging detail, run reports without leaving the screen, send emails, record collection notes, and print invoices. The software supports simultaneous access for multiple authorized users. The data stays up to date and can be refreshed at any time. This saves us hours of time compared with working through QBO. My next step is to have Claude automate reminder notices at 30 and 60 days, based on user-selected settings, as well as 90-day collection letters. These notices will be customizable while still allowing automation. Step-by-step: 1. I identified the customer information that was spread across QuickBooks windows, including notes, deposits, invoices, payments, aging, and email. 2. I used Claude to write a program that creates an aging summary of all past-due accounts. 3. I added sortable columns for customer name, aging category, total, last payment, and payment date. 4. I enabled users to click a customer row and open a full drill-down of that customer’s data on one page. 5. I included access to date-selectable invoices, open invoices, payments and their applied invoices, aging detail, reports, emails, collection notes, and invoice printing. 6. I set up the software so multiple authorized users can access the data simultaneously and refresh it whenever needed. 7. I plan to add customizable, automated reminder notices at 30 and 60 days and collection letters at 90 days.

Today, I wanted to see how far an AI agent could go if I gave it a real business instead of a predefined automation. I entered binayah.com into Awish.ai. Binayah is a real estate company, and instead of telling Awish.ai exactly what workflow to build, I asked it to analyze the business first and find an automation opportunity. It suggested a customer acquisition funnel, which I reviewed and approved. Around 10 minutes later, the automation was ready. Step-by-step: 1. I entered binayah.com into Awish.ai. 2. Awish.ai agents analyzed the website and how the business operates. 3. Awish.ai identified customer acquisition as an area that could be automated. 4. It suggested a funnel designed to capture and qualify potential leads. 5. I reviewed the suggestion and approved it. 6. Awish.ai created the workflow and connected the required steps. 7. The funnel was ready to use in around 10 minutes. What I find most interesting is that I didn’t start by designing a workflow. The system first understood the business, found an opportunity, suggested what should be automated, and built it only after I approved. That feels much closer to having an automation consultant inside the product than using a traditional workflow builder.

I own a rental property where a water leak has occurred roughly every year or two. The leak typically runs for weeks before the water utility detects usage above its threshold. Because billing cycles last three months, the utility may notify me weeks or months after the problem begins. By then, the leak can have produced a bill more than $1,000 higher than the usual $100–$300 amount. The utility offers a one-time, per-account waiver for accidental leak overages. After using that waiver the first time, later incidents are entirely out of pocket. The utility also cannot notify me sooner than when usage exceeds 25,000 gallons during a billing cycle, which moves the account into a quadruple-rate tier for the rest of that cycle. I repeatedly asked whether they could provide an immediate alert when a user-set or company-set daily usage threshold was exceeded, but they said they had no system or solution for it. I tried checking my usage manually every day, but after weeks or months of normal readings, it was easy to become complacent or forget. After receiving another $1,300-plus bill, I asked ChatGPT whether I could automate the process of logging into my utility account, checking usage daily, and emailing me about the prior day’s usage or an overage. ChatGPT suggested several options, including paid AI-agent tools and a free script running on my own hardware. I wanted a completely free, cloud-based solution that would not require my computer to stay on, so I compared the paid options, including Google Spark, with a GitHub-based system. GitHub apparently includes 2,000 minutes of script runtime per month, while my system was estimated to use about 100 minutes. I spent part of a day asking ChatGPT questions, copy-pasting code into GitHub, and refining it. I now have a cloud-based system that logs into my water utility account, checks daily usage, emails me when my daily or seven-day-average thresholds are exceeded, and adds each day’s usage to an Excel spreadsheet for ongoing history. I have verified that it works, and it is set up to keep running and sending alerts without ongoing cost. I had never coded before. The system uses Python, GitHub Actions/YAML, Playwright, pandas, openpyxl, Excel, and Gmail for email alerts. Excel and Gmail were the only tools in that list I had used previously. If I want to change an alert threshold or another setting, I can log into GitHub and ask ChatGPT for the relevant code adjustment. I also added a second rental property in the same city that uses the same water utility. Replicating the process for that property required only a small amount of additional code and took almost no time. I now have a perpetually self-updating, cloud-based water-usage database with daily email alerts for both rental properties, at zero ongoing cost.

I use Claude Cowork and Meta MCP to map my existing ad creative data and find winning combinations. Once the data is mapped, I can usually identify one concept that wins more often than the others, has absorbed more spend, and still maintains an efficient CPA. That is the winning concept, and it is where I should focus 60% to 80% of my production time. Step-by-step: 1. I connect Claude Cowork to Meta MCP and Google Drive. 2. I place the brief for every ad I published in the past 365 days into one Google Drive folder. Each brief includes the script, format, offer, and persona it was written for. 3. I prompt Claude to work through the Drive folder and build a spreadsheet tagging every ad by persona, angle, offer, and format. 4. I prompt Claude to pull each ad’s spend and CPA through Meta MCP and add those metrics to the spreadsheet. 5. I ask Claude to turn the spreadsheet into a flowchart in which persona branches into angle, angle branches into offer, and offer branches into format. Each branch includes its spend and CPA. After the data is mapped, I use the flowchart to identify the winning concept and prioritize it in production.

I built a model dispatcher to avoid paying premium usage for simple tasks. In Claude, every task runs on the model used by the current session, so a two-line formatting fix can consume the same level of model capacity as a difficult strategic problem. I had Claude build a scoring system that evaluates each task across six dimensions: required reasoning, the amount of context, the importance of craft or nuance, whether speed is the priority, the number of agentic parts involved, and the potential consequences if something goes wrong. Based on the score, it recommends a model—from a light, fast option for rote work to the most capable option for genuinely difficult tasks—and suggests how much effort that model should apply. The key design choice is that the dispatcher never spends anything automatically. Scoring is free and instant, while sending the task to a model through the API costs real money. Dispatching therefore requires an explicit confirmation flag every time. Nothing runs without me saying go. The payoff is not dramatic from day to day. It comes from many small savings that add up, along with a habit shift: I check the router before sending a task instead of wondering afterward why a simple request cost more than it should have. Step-by-step: 1. I identified the problem: every task in a Claude session uses the current model, even when the task is simple. 2. I had Claude build a scoring system that evaluates each task across six dimensions: reasoning, context, craft or nuance, speed, agentic complexity, and the potential consequences of failure. 3. I used the score to recommend an appropriate model, from a light and fast model for rote work to the heaviest model for genuinely difficult tasks. 4. I included a recommendation for how much effort the selected model should apply. 5. I kept scoring free and separate from dispatching, since sending a task through the API costs money. 6. I required an explicit confirmation flag before dispatching any task, so nothing runs automatically. 7. I check the router before sending tasks and benefit from small savings that accumulate over time.

I was tired of opening Spotlight every time I wanted to switch apps. The search results would move around, I would occasionally open the wrong app, and those few wasted seconds kept adding up throughout the day. Instead of memorizing a collection of unrelated hotkeys, I used ChatGPT Work to design and build a personalized shortcut system in Apple Shortcuts. The shortcuts can open individual apps, jump directly into specific Safari or Chrome profiles, or launch an entire work mode with one keystroke. For example, a recording shortcut could open your microphone, camera, recording software, and notes. An analytics shortcut could open all the dashboards you check each week. Step-by-step: 1. I opened the ChatGPT desktop app, started a new chat, and switched to Work mode. 2. I asked ChatGPT to plan shortcuts around my real workflow: Based on what you know about me and my workflow, suggest 10 time-saving hotkeys we can set up in Apple Shortcuts. I’m interested in opening specific apps and profiles based on what I need them for or what mode of work I’m going into. 3. I told it which apps, browser profiles, URLs, and work modes I use most. 4. I narrowed the list before making any changes by keeping the highest-frequency shortcuts and avoiding macOS or app conflicts. 5. In ChatGPT, I went to Settings → Computer Use and turned on Any App. 6. I gave ChatGPT the approved list and clearly limited its scope: Set these up in Apple Shortcuts. Do not change anything outside this list. Test each shortcut. 7. I opened All Shortcuts in Apple Shortcuts and ran each one manually. I used Quick Actions to add or change its keyboard shortcut. I like Control + Option because it is less likely to conflict with existing Mac commands. 8. I tested every shortcut while working in another app, checking that it opened the correct app, account, browser profile, or collection of tools before building more. 9. Once everything worked, I asked ChatGPT to create my reference: Write me a one-page cheat sheet of all the shortcuts you set up, where they live, and what’s left to do. The result is a personal shortcut system built around how I actually work, plus a one-page cheat sheet so I don’t have to memorize everything immediately. For the complete walkthrough, exact prompts, screenshots, and setup instructions, follow my full Rundown University guide: Use ChatGPT to Build a Custom Mac Shortcut System. Tools used: ChatGPT Work, Apple Shortcuts Industry: Cross-industry Tags: #chatgptwork #appleshortcuts #macautomation #productivity #workflowautomation

I used to create a skeptical VC investor persona through prompting whenever I ran ideas and actual business plans through AI. Recently, after working on a business plan for weeks, I used Claude Cowork with Opus 5/High to evaluate the same concept. Instead of prompting for critique and redesign each time, I built a Skill upfront. The concept is the same, but the Skill makes the execution much more effective. It reviews ideas or detailed business plans, researches first, and critiques only after that. It also analyzes and suggests wedges and new moats and, when instructed, generates detailed business plans. It works well as a one-shot analysis, but it is most effective when I push back and challenge it further. I’m sharing the Claude Skill for free under the MIT license: https://github.com/zszendro/vc-teardown Step-by-step: 1. I used to prompt AI to role-play a skeptical VC investor when reviewing ideas and business plans. 2. After working on a business plan for several weeks, I ran the same concept through Claude Cowork with Opus 5/High. 3. Instead of prompting separately for critique and redesign, I built a Skill upfront. 4. I designed the Skill to research first and critique only afterward. 5. I used it to review ideas or detailed business plans, analyze and suggest wedges and new moats, and generate detailed business plans when instructed. 6. I continued the analysis by pushing back and challenging the Skill beyond its initial one-shot response. 7. I shared the Claude Skill for free under the MIT license at https://github.com/zszendro/vc-teardown

I spent twenty years producing documentary and nonfiction films, all of it the expensive way: crews, schedules, financing, and commissioners saying no. I'm proud of much of that work, and I still think about the films that never got made because the money wasn't there. Generative video pulled me in, but not for the reason people assume. It wasn't the speed or the cost. It was the fact that I could finally finish something without asking anyone for permission. No green light from a major platform. Nobody deciding that a story was too small to deserve a crew. A year later, I could produce this way. It turned out to be a different job rather than the same job with new tools. Then I ran into a problem I hadn't considered: how do you show the work? A finished shot doesn't prove much anymore. A client can look at a beautiful frame and have no way to tell whether it took three weeks or three minutes. If I'm honest, neither would I in their position. The thing every portfolio is built to display had stopped being evidence. I'm not a developer. I produce films. The site is bilingual, has seven sections, includes a case study for each film, plays video on hover, and has a comparison slider that works with a thumb as well as a mouse. I built all of it. I'd wanted this exact site for about fifteen years and had never managed to explain it properly to anyone I paid to make it. This time, I stopped explaining and built it myself. The middle of the page has a slider that you drag between the storyboard panel and the final shot. A basic before-and-after would prove nothing; you can fake that by generating twice. The storyboard is the proof because the framing, eyeline, and decision about what stays outside the frame all existed on paper before any model was asked to generate anything. You drag the handle and watch the intention survive. The rest of the site came from the same place. Video only plays on hover and is silent until you click for sound. Most video portfolios are unreadable because fifteen things start moving at once. The sections are organized by register rather than by client: epic, brand, animation, and lifestyle. A wall of logos answers who has hired you, which nobody is actually wondering. What they want to know is whether you can change tone. Nothing is cropped to fit the grid. A 5:33 film sits in 16:9 next to a 2:42 film in scope, and the layout is lopsided because of it. I nearly made them uniform because it looked tidier, then realized I was about to reformat my own films so a webpage would look neat. Anyone who cuts for a living spots that immediately. Concepts are labeled as concepts. Experiments have their own section instead of being scattered among the client work and hoping nobody asks which is which. Step-by-step: 1. I started from what my client couldn't verify: the craft behind a shot. 2. I found the artifact that proves it. It's usually the ugly thing nobody publishes: the storyboard, the reference sheet, or the version before the good version. 3. I put that artifact next to the finished piece inside one interaction, so nobody has to search for the proof. 4. I made playback deliberate. Video plays on hover, and sound requires a click. 5. I sorted the work by the question being asked rather than by the credentials I wanted to lead with. 6. I didn't reformat the work to fit the layout. I let the grid be uneven. 7. I labeled everything honestly: client, concept, or experiment. One word each can pay for the credibility of the whole page. 8. I wrote a brief for each section as a document first. Arguing with a paragraph is free; arguing with a built page is not. 9. I built the site with an AI coding tool. This was the least interesting step, even though it's the one everyone writes about. If your work can be mistaken for a lucky prompt, stop trying to prove it with the finished piece. The site is at www.termopilas.tv if you want to drag the handle yourself.

I built a predictive maintenance workflow in Awish for one of my manufacturing clients. The client had machine telemetry, production data, and maintenance history spread across different systems. The problem wasn’t collecting the data—it was spotting failure risk early enough to act. I built a custom Awish workflow that continuously checks machine telemetry and production signals in Snowflake alongside asset, meter, and maintenance history from MaintainX. When it detects abnormal performance or increasing failure risk, it identifies the affected equipment, estimates the likely operational impact, and prepares a recommended maintenance action. Nothing is scheduled automatically at that point. The recommendation first goes to the maintenance manager in Microsoft Teams for approval. Once approved, Awish creates and assigns the work order in MaintainX, then keeps tracking and updating its status until the maintenance is completed. The useful part is that the system does not wait for a machine to fail before maintenance starts, but it also does not let AI make the maintenance decision on its own. The analysis is automated, while the actual intervention still requires human approval. Step-by-step: 1. I described the maintenance process I wanted in the Awish chat. 2. Awish planned the workflow and selected Snowflake, MaintainX, and Microsoft Teams for the required steps. 3. I connected the client’s accounts and approved the automation plan. 4. Awish continuously analyzed production and telemetry data in Snowflake together with MaintainX asset, meter, and maintenance history. 5. When it detected abnormal behavior or increasing failure risk, it identified the affected equipment and estimated the likely operational impact. 6. It prepared a recommended maintenance action and sent it to the maintenance manager in Microsoft Teams. 7. Once the manager approved the recommendation, Awish created and assigned the work order in MaintainX. 8. The workflow continued tracking the work order and updating its status until the maintenance was completed. Trigger → Analyze → Approval → Action Machine signals → Failure-risk analysis → Teams approval → MaintainX work order

AI coding tools can build quickly, but they can also build the wrong thing quickly. Starting implementation from a vague feature request leaves important decisions about scope, architecture, edge cases, success criteria, and expected behavior to be made implicitly during coding. I created a spec-generator agent that sits between an idea and implementation. I give it a feature request, product vision, or rough description of what I want to build. It investigates the existing project, identifies missing decisions and constraints, researches external dependencies when necessary, and turns the request into a detailed specification that another AI agent can implement without having to guess what I meant. The finished specification becomes the source of truth for the rest of the development workflow. Step-by-step: 1. I give the spec-generator the feature or product idea I want to build, along with any existing requirements, vision documents, or constraints. 2. I have it inspect the existing project before proposing a solution. It needs to understand the current architecture, conventions, capabilities, and relevant prior decisions rather than designing the feature in isolation. 3. I have it identify ambiguities and missing decisions, including questions about users, behavior, scope, dependencies, edge cases, data requirements, integrations, and what is explicitly out of scope. 4. I have it research external technologies, APIs, libraries, or platform capabilities when the design depends on facts that cannot be determined from the repository alone. 5. I have it translate the idea into a layered specification: first the product purpose and desired outcomes, then the technical architecture, and finally the detailed implementation requirements. 6. I have it define measurable success criteria and acceptance tests so that “done” means something concrete rather than simply “the code was written.” 7. I have it persist the finished specification in the project so developers or coding agents can treat it as the source of truth during implementation. 8. I pass the specification through a separate review or validation step before coding begins, resolving gaps or contradictions in the spec rather than discovering them halfway through implementation. Instead of asking an AI coding agent to interpret a rough idea while it writes code, I separate figuring out what should be built from building it.

I plan travel day trips for CCRC in Portland, Oregon, using a simple model I created. Before using it, planning each trip took me hours. Now, the model generates a day-trip overview in minutes that I can distribute to CCRC staff, travelers, and the bus driver. The prompts cover the destination and visit details, such as a docent tour or special events; the trip date; lunch requirements for a restaurant that can accommodate 20 guests and provide separate checks; bathroom stops every hour; and bus drop-off, parking, and pickup requirements. Step-by-step: 1. I enter the destination and details about the visit, including docent tours or special events. 2. I add the trip date and specify whether lunch is needed at a restaurant that can accommodate 20 guests and provide separate checks. 3. I include the need for bathroom stops every hour, along with the bus drop-off, parking, and pickup requirements. 4. I use the model to generate a day-trip overview in minutes. 5. I distribute the overview to CCRC staff, the travelers, and the bus driver.

I produce cinematic AI video. What ruins a sequence is almost never image quality; it is drift. The face, jacket, and light change between shots, so what should read as one scene becomes a gallery of near misses. Most people fight this by regenerating until something matches. I built the opposite: a set of chained Claude skills that locks a character once and never lets the model improvise again. The lesson that started it cost me 72 credits in one unusable shot. I fed a finished POV frame as an image reference to “set the world” for a motorcycle sequence. The model treated it as a strong identity reference, cloned the entire cockpit from that frame, and ignored the bike I was describing in the prompt. Image references are read as identity, not atmosphere. That misunderstanding is why most people’s characters mutate. Step-by-step: 1. I lock the character before generating anything. I fill nine layers in order: identity and facial structure, skin realism, wardrobe and materials, emotional energy, environment, lighting scheme, camera language, vertical 9:16 framing, and a fixed block of negative instructions. A generic prompt returns a generic face. This is direction, not a portrait. 2. I shoot a character sheet: a neutral, multi-view image of the locked character on white. That sheet—not a pretty hero frame—is what I reuse as a reference from then on. 3. I expand coverage instead of reinventing the scene. One locked scene becomes a full shot list with hero angles, macro inserts, and establishing shots. The subject, wardrobe, weather, and lighting never change between prompts. Only the camera, focal length, framing, and distance change. Every prompt restates the entire world from scratch because the generator has no memory between images. Consistency comes from redundancy, not from the model remembering. 4. I time the story before animating. I create a 3x3 board with nine beats over fifteen seconds, with each panel showing its timecode, shot title, and action. The rule is strict: the character, wardrobe, world, and light stay identical across all nine panels; only the story advances. The emotional scale rises toward panel nine. 5. I generate with reference discipline. I pass the object or vehicle in a clean exterior shot as the only image reference, then describe the world, framing, and interior in text, repeating that description word for word across shots. I chain consecutive shots by feeding the last frame of one as the start image of the next. The joins are invisible. 6. I review the board against the renders, keep the shots that hold, and regenerate only the ones that drift. The result is that I stopped paying the regeneration tax. Shots are budgeted, not gambled, and a fifteen-second sequence holds together because it was blocked like a real scene—with coverage and continuity—before a single frame existed. The nine-layer character build and the coverage framework are adapted from two AI video courses plus twenty years of production. I learned the reference discipline in step five the expensive way.