Writing

For years the architecture visualization industry has been stuck with a strange limit. Studios can produce a still render so convincing you cannot tell it from a photograph, but the moment a client wants to move through that space, the cost jumps by an order of magnitude. Animation means cameras, keyframes, render farms, and days of compute per shot. So most projects ship as a handful of gorgeous frozen images, and the sense of actually being there never makes it to the viewer. Two things changed that recently. Image-to-video models can now invent believable motion from a couple of stills. And coding assistants like Claude can turn that footage into a polished, interactive site in an afternoon. I wanted to see how far that combination goes, so I built a small experiment. This is how it went. ...

There’s a lot of “AI copywriting” out there and almost all of it does the same thing: you give it a prompt, it gives you five variations, you pick one, the end. It’s a better autocomplete. It writes once and forgets everything the moment the message goes out, including, crucially, whether anyone clicked. The agent we built at Comify is the opposite of forgetful. It researches a brand before it writes a word, generates message templates with actual intent behind the wording, ships them, watches what real people do, and then changes how it writes based on what worked. It’s a closed loop. And closing the loop is where it stops being a writing tool and starts being a system, with all the upside and all the ways that can go wrong. ...

When people hear that Comify’s backend is fifty-some AWS Lambda functions moving more than fifty million messages a day, the usual reaction is “isn’t serverless expensive at that scale?” It’s the right question with the wrong assumption baked in. Serverless got chosen because of the scale and the economics, not in spite of them. But you only get the good version if you design for it deliberately. The naive version is genuinely a trap. ...

Every e-commerce catalogue has a dirty secret, and it’s a number nobody likes to say out loud: the percentage of products that have a proper photo of a real person wearing them. Ours was 73%. Which means more than a quarter of what we sold, thousands of frames, was represented online by a flat shot of the product on a white background, while its neighbour had a crisp image of a model looking great in it. The model shots convert better. Everyone knows this. The problem is that closing the gap means a physical photoshoot, and a physical photoshoot does not scale. We took catalogue coverage from 73% to 100% in about a month. Not by shooting faster. By not shooting at all for the long tail. ...

Virtual try-on has a problem nobody puts in the marketing video: it works beautifully for people who don’t already wear glasses. For everyone else (which, at an eyewear company, is most of your customers), the experience is broken. You point the camera at your face, the app renders a gorgeous new frame, and it sits on top of the glasses you’re already wearing. Two pairs of glasses. It looks ridiculous, and worse, it doesn’t answer the only question the customer has: do these look good on me? So we built the thing that sounds impossible when you say it out loud: remove the glasses the user is wearing, live, from the camera feed, before rendering the new ones. On the phone. Fast enough that it feels like video, not a slideshow. ...

There’s a version of a scaling story that’s all dashboards and Kubernetes. This isn’t that one. This is about a phone-number-verification product called CODAC that, at its peak, placed more than ten million calls a day, made around $12M a year, and was run by three people. We did it on a cluster of telephony servers that mostly looked like pets, not cattle, and the hardest problem we solved had nothing to do with the volume. ...