Verdict

24 days Zero lines of code → a finished app. How it all started It was a Wednesday evening, April 8th, 2026. I was on the couch with my partner. We were staring into the streaming interface, trying to find a movie we'd both actually watch. She wanted horror: jumpscares, blood, fear. Some slasher from the early two-thousands. I wanted a drama. Something quiet, something arthouse, ideally with long takes where not much happens. Netflix looked at our combined watchlist and suggested a generic action thriller. Again. That wasn't what I wanted. It wasn't what she wanted either. It was the safe middle. The mathematically calculated compromise between two people with individual needs. The average of the two of us is "nobody". A cheap John Wick clone. You know the drill. My name is Ken, I'm a service operations manager for spark spectrometers and I deal for a living with analytical instruments, some of which were already running before I learned to walk. Analytical thinking: yes. Software development: never. I hadn't written a single line of production code before that evening. But that night, in front of the TV, something must have triggered me. The problem Streaming algorithms estimate your taste based on your watchlist. But watch lists are contaminated data sources. What you eventually turned on depends on what was available, what your partner wanted to see, what's about to drop out of the catalog, what mood you happened to be in on some random Tuesday night... The signal is noise. Bad enough on a single profile, mathematically broken on a shared one. And everyone pretends it's fine. I wanted to build the opposite. An app that doesn't guess your taste from your history but asks you directly. 24 psychological scenario questions instead of thousands of watchlist data points. More direct. More honest. Mathematically cleaner. I had the name faster than the plan. PAVL: at the same time a nod to Pavlov's dog (assigning responses to stimuli - that's the core of the whole app) and a back door for a megalomaniac wordplay: Psychologische Analyse Visueller Latenzen (Psychological Analysis of Visual Latencies). It sounds like something a German scientist invented in a basement lab in 1973. That was exactly the effect I was going for. Before I'd written a single line of code, I had the logo. Black background, film-strip frame, the wordmark PAVL set in Gloock - one of those serif faces A24 has been plastering on their movie posters for years. Accent color purple, because I had no patience for the thousandth tech-blue. I knew what I was building because I knew what it was supposed to look like. Day 1 to 7: From whiteboard to first question In the first days I had no code. I had a whiteboard, a NotebookLM workspace, and three tools that would become my most important sparring partners. Cursor as the development environment, Claude as architectural validator and script generator, Gemini for bulk data processing via API. Some people now call this "vibe coding". That's a horrible term that sounds like it's describing a meditation app where a program emerges from water sounds and breathing exercises. What actually happens is an analytical translation process: you describe what you want, precisely, the system writes the code, you read, understand, correct, ask back, point out logic errors, demand a restructure... You have to carry the architecture in your head, even if you're not writing every line yourself. You have to be able to spot mistakes. You have to know when an answer is hallucinated and when it fits. What I needed was a psychological profile system. Ten dimensions that describe a person cinematically. How much cognitive demand do you tolerate, do you want to be challenged or entertained? How sensitive is your stimulus system to loud, fast, aggressive imagery? How much emotional exposure do you allow, do you want to feel along or keep your distance? Are you an escapist or do you want to be confronted with maximum reality? How strict is your aesthetic standard, does it have to be a work of art or is raw tension enough? How much darkness do you tolerate, where's your pain threshold? Plus humor affinity, empathy anchor, expectation shift, social modulation... Each dimension on a scale from zero to one hundred. The result is a ten-dimensional vector: a kind of psychological fingerprint that describes who you are as a viewer. The 24 questions had to be written in such a way that every answer produces clean, mathematically defensible shifts along these ten axes. This wasn't marketing work, this was calibration. I spent days reformulating individual answers because they would have hit too many dimensions at once. Or too few. One question, for example: "A child dies at the start. Slowly. The camera forces you to watch." Answer A - "I close the app." - lowers your darkness tolerance and your emotional exposure. Answer C - "I stay calm and look at why the scene is built this way." - raises your cognitive demand and lowers your emotional exposure. Both answers are valid. They simply describe different people. That's exactly the point. Day 8 to 14: The system learns Questions alone give you an estimate. But people lie, including to themselves. I looked at my own first result and thought: hm, I'm actually funnier than the system says. And then I realized that my "actually" might be a lie too. The system needed a mechanism that checks self-assessment against actual behavior. That's exactly what the deck is for. After the questions you get movies as swipeable cards. Right if you want it, left if you don't. Every swipe shifts your vector. If you like movies that are more intense, funnier, or darker than the questions had assumed, your profile adjusts. Your archetype can change. The math behind this is an adaptive learning rate that decreases over time. Early swipes move you a lot: you're new, the system knows little about you, every data point is gold. Later swipes barely move you, your vector stabilizes. Just like a human matures in their taste. There's a hard upper bound per update so a single deranged swipe can't destroy your whole profile. Negative ratings carry slightly more weight than positive ones because people are more honest and direct about what they reject than about what they think they want. Day 15 to 18: The architecture The frontend is a React Native app, built with Expo, because I knew from day one that I wanted to serve Android and iOS from a single codebase. A second parallel project for iOS would probably have killed me. The backend runs entirely serverless on Cloudflare. Workers for the computations, D1 for the database, R2 for the assets. No AWS, no containers, no self-hosted server waking me up at three in the morning with a push notification. The entire backend code runs at the edge. Meaning: wherever the user happens to be. When somebody in Hamburg opens the app, a server in Hamburg answers. When someone in São Paulo swipes, a server in São Paulo answers. Latency in the millisecond range, without me having to configure a single region by hand. Authentication runs entirely without passwords. Passkeys. The new standard Apple, Google, and Microsoft are jointly pushing. You log in with Face ID or fingerprint, your device authenticates you cryptographically against the server. No "forgot password?", no verification email lost in the spam folder. I just left out this entire category of problems. Cross-device login works through a six-digit code valid for ten minutes. Enough security, low friction. The biggest technical hurdle was the matching engine: the algorithm that decides which movie comes next in your deck. 26,000 movies are in the database, each one tagged through an automated API pipeline with Gemini into the same ten-dimensional space as the users. On every deck request, the system has to compute which movies fit your current vector best. My first attempt was a simple cosine similarity. Works for many recommender systems. In my case it plateaued. The recom