Search for a command to run...
There's a pricing detail most product teams don't look at closely enough. Input tokens and output tokens are not the same price. Output tokens cost more. Sometimes 2-3x more depending on the model. Th
At first glance, you think there is no price tag for Nobody context windows. It's not listed in the model pricing. It doesn't show up in your planning. Your engineering team probably hasn't flagged it
There's a question that comes up a lot when teams start measuring AI performance. "Why does our model feel slow? We're using the same model as everyone else." The answer almost always lives in the sam
There's a meeting that happens on most AI product teams. The infra engineer pulls up a dashboard. Numbers. Percentiles. A latency chart with a line somewhere around 800ms. The PM looks at it, nods, an
How I went from "what if I could get an AI I trust to manage my multiple projects for me" to a live, multi-channel AI intern and the architecture behind it. Part 1: The Inspiration I run multiple pro
Most platform teams rarely struggle because they lack metrics. They struggle because the metrics they're measured on don't reflect the value they're meant to create. Adoption, usage, and number of int
Growth in product isn't always about doing more. At a certain point, progress comes from stopping the right things. One of the first things I intentionally stopped doing was solving every problem myse
When teams think about scaling, the instinct is to add. More process. More roles. More tools. More frameworks. Some of that is necessary. But in my experience, the hardest part of scaling product isn'
Building for multiple markets looks like a scaling problem. In practice, it's a decision quality problem. The first lesson I learned is that markets diverge faster than products do. Regulation, paym
