Practical takes on AI project management, async work, and shipping faster.
The market is finally ready for autonomous AI in business workflows. We spent 8 months building, observing 15 beta tenants, and we're ready to let it run on real teams.
The architecture, the prompt engineering, the eval framework. Real numbers from our beta: acceptance rate, token usage, latency. What worked, what didn't.
We pivoted our positioning from generic workspace to AI PM. Conversion went 2x. Here's the data and the reasoning.
When customer emails get fed into LLMs, prompt injection is real. Here's our defense stack and a sample attack we caught last month.
Why we're not raising VC, how we got to $40K MRR in 4 months, and the trade-offs of building far from the tech hubs.
In-app notifications vs Slack DMs vs email. Why founders actually open Slack. The 5 Block Kit patterns we ended up using.
An agency CEO's account of the first month with our PM Agent. The wins, the surprises, and the one thing that almost made them quit.