[PRODUCT]
The Emotix.co evals stack, in detail
What we learned shipping an agentic product to real users.
Six weeks is not a constraint. It is the point.
Our build sprints are short on purpose. Here is what that forces.
Clients sometimes ask whether we could do a twelve-week sprint. The answer is yes, but we would rather not, and the reason is not scheduling. It is that six weeks forces decisions that twelve weeks lets teams avoid.
Six weeks forces decisions that twelve weeks lets teams avoid.
What gets cut
In a six-week sprint there is no time for a roadmap document that reads like fiction. There is no time for a design system that outlives the product. There is no time for the phase-two-preview slide. What survives is what ships.
What gets kept
A working product. Evals. Observability. A handoff document that a single engineer can read in an afternoon. That is it. That is the whole deliverable.
MORE FROM THE JOURNAL
[ESSAYS]
Why “AI-first” is already the wrong frame
The interesting question is not whether to use AI. It is what a product becomes when you build as if intelligence is free.
[ESSAYS]
We stopped calling ourselves consultants
The word stopped doing useful work. Here is what we replaced it with and why clients noticed.
[AI PRACTICE]
Evaluating agentic systems beyond the demo
Demos lie cheerfully. These are the evals we actually run before we ship.