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

I’m building a mobile game called ExoLab Blast with Astra. I developed it through conversation, starting with the basic concept and continuing through testing the game mechanics. Astra also created and repeatedly updated the game’s graphics and UI based on my feedback. Step-by-step: 1. I discussed the basic concept for ExoLab Blast with Astra. 2. I used Astra to build out the mobile game. 3. I tested the game mechanics. 4. I gave feedback on the graphics and UI. 5. Astra created and updated the graphics and UI multiple times based on that feedback.

I’m on a GLP-1 medication that heavily suppresses my appetite, and I’m also managing a bilateral vestibular condition that causes balance and gaze issues. I needed a way to hit my protein and calorie targets despite having a low appetite, track body composition accurately, log vestibular symptoms, connect my actual training data, and get coaching guidance that reflects my situation instead of generic fitness-app advice. I built FuelStrong: three connected apps created with Claude over many sessions. They include a daily tracker for meals, water, energy, and training check-ins; a Progress and analytics module; and a standalone Vestibular symptom tracker. They share a Cloudflare Worker and D1 database backend, with KV for cross-device sync. I describe a feature or problem to Claude in plain language. Claude proposes structural options, I push back or choose a direction, and Claude writes the HTML, CSS, and JavaScript. I program my lifts in Fitbod using an Upper/Lower/Upper split, with an arms-and-back priority and the Build Muscle goal. I export those workouts as CSV and drop them into FuelStrong’s import zone, which parses exercises, sets, reps, and volume into my training history. Custom foods receive macro estimates through a Claude API call routed through my own Worker endpoint. Evolt body-scan data feeds dynamic calorie and protein targets based on BMR × activity factor, minus a deficit, with hard floors instead of static numbers. The Vestibular module intentionally uses open text fields for now, so Claude and I can identify which data matters before formalizing the inputs. Everything syncs across devices through Cloudflare KV. The coaching layer uses a three-tier framework—evidence floor, confirmed operating range, and aspirational target—to drive every recommendation. Two calorie floors, a daily target of approximately 1,000–1,100 kcal and a weekly average of approximately 1,300–1,400 kcal, reflect that chronic under-eating—not missed protein—is the real GLP-1 risk. Muscle mass has remained stable since my February 2026 baseline, so the coaching treats that as a genuine win rather than a plateau. Vestibular-training coaching connects dry-needling focus areas—SCM, suboccipitals, and splenius capitis/cervicis—to gaze-stabilization symptoms, since cervical proprioception substitutes for non-functional vestibular canals. The result is one dashboard that brings together training, nutrition, body composition, vestibular symptoms, and coaching logic. My muscle mass has held stable through it all. Step-by-step: 1. I describe a feature or problem to Claude in plain language, review its structural options, choose a direction, and have Claude write the HTML, CSS, and JavaScript. 2. I use FuelStrong’s daily tracker to record meals, water, energy, and training check-ins, while the Progress and analytics module tracks body composition and related trends. 3. I program my Upper/Lower/Upper workouts in Fitbod with an arms-and-back priority and the Build Muscle goal. 4. I export Fitbod workouts as CSV and import them into FuelStrong so it can parse exercises, sets, reps, and volume into my training history. 5. I route Claude API requests for custom-food macro estimates through my own Cloudflare Worker endpoint. 6. I use Evolt body-scan data to calculate dynamic calorie and protein targets from BMR × activity factor, minus a deficit, while maintaining hard floors. 7. I log vestibular symptoms in the standalone Vestibular tracker using open text fields while Claude and I determine which inputs should eventually be formalized. 8. I sync the three apps across devices through the shared Cloudflare Worker, D1 database, and KV backend. 9. I use the evidence floor, confirmed operating range, and aspirational target framework to guide recommendations, including the daily and weekly calorie floors. 10. I connect vestibular-training coaching to dry-needling focus areas and gaze-stabilization symptoms, then use stable muscle mass since the February 2026 baseline as a positive outcome rather than treating it as a plateau.

I built a small GPT automation called PatternSpeak that periodically looks back across my conversations for ideas, themes, or approaches that keep resurfacing over time. It is not meant to analyze me or turn recurring thoughts into tasks. Its job is much simpler: occasionally say, in effect, “Hey, this idea keeps coming back. Maybe there is something here.” I like it because repetition can be meaningful without being urgent. Sometimes an idea disappears for weeks and then returns in a completely different context. PatternSpeak helps me notice those echoes without forcing them into a productivity system. It feels less like tracking and more like having a friendly observer tap me on the shoulder when a thread has quietly become a pattern. It works very well with the scan and analysis workflow I also shared here. Step-by-step: 1. I use PatternSpeak to periodically look back across my conversations. 2. It identifies ideas, themes, or approaches that keep resurfacing over time. 3. When it notices a recurring thread, it surfaces it as a gentle prompt rather than turning it into a task. 4. I review the recurring ideas and notice whether they have become meaningful patterns, even when they return in different contexts. 5. I use the scan and analysis workflow I also shared here alongside PatternSpeak.

I am a Mohs surgeon who built and shipped an iOS app without formal software engineering training. The surprising part was not only getting AI to write the code; it was getting AI to remember what it had already done. I built ErgoSherpa because up to 90% of surgeons in my field report musculoskeletal symptoms, while our training fails to address them. I wanted to help surgeons improve their health easily between cases. It is free on the Apple App Store and at ergosherpa.com. The bottleneck was maintaining coherence over time. Many sessions seemed to start from zero: I would re-explain the architecture, then watch a fix quietly undo something I had solved earlier. Three habits fixed that. First, I created persistent project documentation: a `MEMORY.md` index file plus separate topic files for architecture and business decisions. I update them at the end of every session so a new session can read the files first and pick up where the last one stopped. Second, I stopped handing one model the whole job. I use three models and match them to the task. Claude Fable audits only. I open a separate session, point it at the codebase, and require a prioritized checklist with the file path, the problem, and the fix in one sentence—without writing code. A model that did not write the code and has no memory of the project reviews it more honestly than the session that built it. I paste that checklist into a Claude Opus session, which handles the codebase repairs. Claude Sonnet handles routine work such as content updates, image processing, and scheduled maintenance, often from handoffs written by Opus or Fable. Nothing gets implemented on the auditor’s word alone: I have Opus flag any decision that needs human input. This workflow caught a deep-link handler that accepted authentication tokens from any URL and a database policy missing its write-side check. Third, I verify against production, not just the code. Some of the most frustrating parts of the project involved fixes that were correct in the file but wrong on the user’s screen because of a cached asset, a stale database row, or an iOS process that needed a force-quit. I no longer consider anything fixed until I have checked the live app. Step-by-step: 1. I keep a project memory directory with a `MEMORY.md` index and separate topic files for architecture and business decisions, updating them at the end of every session. 2. I open a separate Claude Code session running Claude Fable and prompt it to audit the codebase and return only a prioritized checklist: file path, line number, the problem in one sentence, the fix in one sentence, with no code or commentary. 3. I keep the auditor in its own session with no project history so it reviews the code independently instead of defending work it wrote. 4. I paste the checklist verbatim into a Claude Opus session and have it work from the top down, reading each file and making each change. 5. I tell Opus to flag anything it believes is a false positive instead of implementing it, keeping a human in the loop on key findings. 6. I use Claude Sonnet for routine work such as content updates, image processing, and scheduled maintenance, often from handoffs written by Opus or Fable. 7. I verify every change against the live production site rather than the local files because cached assets and stale database rows can make correct code behave incorrectly for users. 8. I append confirmed lessons and architectural decisions to the project memory so the next session starts from the project’s current state.

I keep a long wishlist on Audible, but whenever I want a new audiobook, I face the same question: does my library already offer it for free through Libby? Checking hundreds of titles manually feels like too much work, so I often spend a credit instead. I had Claude build a workflow that checks for me. It reads my Audible wishlist and cross-references every title against my library’s Libby catalog, sorting each one into three categories: borrow now, join the waitlist, or not available. The important part was learning to interpret Libby accurately. Badges and time estimates can make an audiobook look ready when it isn’t, and a pending hold can look like an active one. The reliable signal is the exact text on the button: “Borrow” means I can borrow it; anything else means I should wait or move on. Step-by-step: 1. I gave Claude a workflow to read my Audible wishlist. 2. I had it cross-reference every title against my library’s Libby catalog. 3. I had it sort each title into “borrow now,” “join the waitlist,” or “not available.” 4. I configured the workflow to interpret availability using the exact button text rather than relying on badges or time estimates. 5. Before spending an Audible credit, I check whether Libby already has the audiobook ready.

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.

I built a workflow called PeopleSparkles for researching people connected to creative fields, schools, collectives, residencies, local art scenes, and cultural networks. The workflow starts from a defined group of people, for example teachers, alumni, artists, current or former members of an association, residents, or associates connected to a specific academy, organization, or cultural scene. A typical research request can be as simple as: “Look at this art website and identify all current and former residents and associates. Build a list. Then research them in batches of ten, checking their websites and other relevant sources, and write a short description of their work. Deliver the results in a format that can be imported into my local database.” Before each new research run, I provide GPT with a ZIP containing the current state of the PeopleSparkles database. This means the research starts from the existing corpus rather than from scratch. New people can be added, existing entries can be expanded, and previously researched people can be recognized before new material is prepared for import. The actual database lives locally on my computer. Apart from the initial development of the code and the research needed to create new lists of people, the database itself runs locally. Once a new batch has been researched and imported, browsing, organizing, scoring, annotating, and using the material does not require the whole corpus to be sent back for analysis. The database also generates a human-readable HTML version with a designed layout, so the research is not trapped inside raw data or spreadsheets. I can browse the people and their notes visually as a small personal research publication, while the underlying structured data remains available for future additions and processing. The “Sparkles” part is personal. I can add my own notes and scores to each person to capture whether their work sparked something in me, and if so, how. That might be curiosity, recognition, inspiration, aesthetic attraction, a strong question, a surprising association, or simply the desire to look again. This means the database does not only record who someone is and what they make. It also records my evolving relationship to their work. Over time, that creates a second layer on top of the research corpus: not just a map of creative people, but a map of resonance. The database also includes a “Surprise me” function that brings up a person from the collection without me choosing them deliberately. This helps break habitual search patterns and allows older, less obvious, or previously overlooked entries to resurface. Someone I barely noticed months ago can suddenly become relevant in a completely different creative context. The purpose is not to create conventional biographies. I am interested in the sparks around a person: what they make, the media and themes they work with, the organizations or people they connect to, and which traces may lead somewhere unexpected. This is particularly useful for creative ecosystems where information is fragmented across artist websites, academy pages, exhibition archives, old posters, association websites, interviews, catalogues, and small cultural organizations. The workflow gathers those fragments into a cumulative research corpus. It also allows the research to grow organically. One artist may lead to a collective, a teacher to a former student, an exhibition to another maker, or an old membership list to someone whose work would never have appeared in a conventional search. In simple terms: existing local database → new source or people list → GPT-assisted discovery and research in batches → import-ready structured data → local database → HTML browsing, notes and scores → surprise rediscovery → new creative connections The result is a living creative research database that combines external research with personal resonance, so I can not only discover people, but also trace which work actually sparks something in me over time.

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

I am 65 and recently retired, and I have been asking AI for advice to keep my plants alive. It tells me whether they need more or less water, more or less light, or soil amendments such as perlite or coconut.

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

I made an orchestration skill to help me build faster while using my expensive Astra and Fable tokens carefully. The skill plugs into Astra or Fable and delegates tasks that can happen in parallel to multiple subagents running cheaper models suited to the work. This is especially useful for researching or finding data on the web or on my computer, analyzing code, collecting context, and indexing. The most expensive, newest models focus on maintaining delegation control, doing the difficult reasoning and strategic planning, and judging whether everything is coming together correctly. The cheaper agents handle the lighter-weight work, especially implementing code from the plans. The core idea is simple: the expensive model plans, briefs, and judges; cheaper agents do the reading and building. When I ask Claude or GPT to build the skill, I specify five things: Step-by-step: 1. I define a triage ladder: work can happen inline, with one agent, through a parallel fan-out, or in a multi-stage workflow. I choose the approach based on the task shape and include examples from my domain. 2. I define parallel versus sequential execution based on data dependencies. Independent pieces run in parallel, while anything that needs another piece’s output runs afterward. I never split one change into separate planner, coder, and tester roles. 3. I define model routing with a mandatory model pin: judgment work goes to the mid-tier model, mechanical bulk work goes to the cheap model, and every agent call names its model so nothing silently uses premium billing. 4. I define a brief template and a return-envelope cap. Every delegation includes the goal, inputs, output file path, definition of done, and constraints. Every agent returns a 250-word summary instead of raw files. 5. I define a cost gate with specific numbers. Below N agents, the workflow proceeds automatically; above N agents, it states the estimate and waits for approval.

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

I built a digital Second Brain after trying several approaches, including OpenBrain and LLM Wiki. OpenBrain and LLM Wiki are useful frameworks for building a digital brain. The theory is solid: flat Markdown files, AI-first conventions, and an ingestion pipeline that turns raw inputs into searchable knowledge. But when applied in practice, the process can be bumpy and may require adjustments—or an entirely different approach. I adapted the ideas to fit how I actually think and work. I kept what worked, discarded what didn’t, and built my own digital brain. The result is documented in a single file containing everything an AI needs to understand, maintain, or rebuild the system from scratch. Step-by-step: 1. I tried several digital-brain frameworks, including OpenBrain and LLM Wiki. 2. I evaluated their approaches, including flat Markdown files, AI-first conventions, and an ingestion pipeline for turning raw inputs into searchable knowledge. 3. I identified where the frameworks were difficult to apply in practice and adjusted my approach. 4. I kept the ideas that worked for me, discarded what didn’t, and built a digital brain suited to how I think and work. 5. I documented the system in a single file so an AI can understand, maintain, or rebuild it from scratch.

I built a workflow for turning large ChatGPT conversation exports into a usable personal and creative archive instead of simply storing them as backups. The archive is processed incrementally. The inventory is built offline, and conversations that have already been indexed are not needlessly reanalyzed on every run. Each new export is compared with the existing archive, and only newly added conversations or conversations that have been revisited, extended, or otherwise changed are processed again and updated in the inventory. This keeps the workflow lightweight while allowing the archive to evolve over time. A conversation can remain stable for months, then become relevant again and receive new material without forcing the entire archive back through analysis. This matters because many of my conversations are long, layered thinking sessions: creative explorations, project development, research, problem-solving, or extended reflection. Without an inventory, the depth inside those individual conversations and thinking processes becomes difficult to retrieve later. The workflow makes long-form analysis and creative thought processes findable and reusable without flattening them into a few generic summaries. On top of the inventory, I use lightweight “blubscans” (analysis to improve retrieval): small, human-readable summaries that capture what mattered during a day or period without replacing the original conversations. They act as a navigational layer between thousands of raw messages and the things I may want to find, understand, revisit, or continue later. The important principle is that compression never becomes deletion. The raw conversations remain the source of truth, the inventory provides structure, and the scans provide context and tone. The result is more than a backup system. It becomes working creative memory: something I can preserve, search, revisit, connect across time, and reuse for projects, research, writing, pattern-finding, and future creative work. In simple terms, the structure is: raw exports → offline incremental inventory → blubscans/context layer → retrieval and reuse for later projects and creative work That way, the archive stays deep without becoming heavy, and useful without constantly reprocessing everything that was already understood. Step-by-step: 1. I collect large ChatGPT conversation exports as the raw source material for the archive. 2. I build and maintain an offline inventory of the conversations that have been indexed. 3. With each new export, I compare the conversations against the existing archive. 4. I process only newly added conversations and conversations that have been revisited, extended, or otherwise changed. 5. I update the inventory with the results while leaving stable conversations untouched. 6. I create lightweight “blubscans” with small, human-readable summaries of what mattered during a day or period. 7. I use the raw conversations as the source of truth, the inventory for structure, and the scans for context and tone. 8. I retrieve and reuse the archive for projects, research, writing, pattern-finding, and future creative work.

I’ve found it useful to use Claude while reading nonfiction books, such as *Factfulness* by Rosling. I ask Claude for a synopsis of the book and save the result as a PDF on my computer for future reference. I also ask Claude to quiz me about the book, either with multiple-choice questions or in short-answer format, to test whether I’ve fully understood what I’ve read. In an ongoing conversation, Claude can also relate the current book to other books I’ve recently read and provide additional synopses. Step-by-step: 1. I tell Claude which nonfiction book I’m reading, such as *Factfulness* by Rosling. 2. I ask Claude to create a synopsis of the book. 3. I save the synopsis as a PDF on my computer for future reference. 4. I ask Claude to quiz me using either multiple-choice or short-answer questions. 5. I continue the conversation so Claude can relate the book to other books I’ve recently read and provide further synopses.

My company takes cybersecurity seriously, and part of our new-hire onboarding process is a tour of the IT department to meet the team. Our walls have several screens displaying metrics and information from our security tools, firewalls, and other systems. It looks like a scene from a movie. By far, the most popular display is our custom-made Cyber Threat Map, which shows real-time attempts to infiltrate our network, malicious emails, and other security threats we're blocking. The map drives home the reality of what we're facing 24/7 while protecting our employees, vendors, and customers. I built it using Claude Code. It polls a range of devices and systems through APIs, aggregates the data on one screen, and displays attack vectors, location information, and other details from the last 30 days. Step-by-step: 1. I identified the security tools, firewalls, devices, and systems that provide relevant threat data. 2. I used Claude Code to build a custom Cyber Threat Map. 3. I connected the map to the devices and systems through their APIs. 4. I aggregated the data on a single screen, including attack vectors, location information, and other details from the last 30 days. 5. I displayed the map during IT department tours so new hires could see the real-time threats our company is blocking.

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 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.