AI can do more of the work. People should still own what matters.
acacia90 explores better ways for small teams to work with AI — giving AI more of the execution while people keep direction, judgment and ownership.
This is not a finished framework. It is a practice we are testing through real work.
More capability can still create more work.
AI can draft, build, analyze and produce faster than before. But without careful workflow design, teams can end up with more outputs to review, more uncertainty and more repeated explanation.
We are testing a simple way to divide work between people and AI.
People set the goal, context and constraints.
AI takes on drafting, building and repetitive production.
Made does not mean ready.
People own the judgments that matter.
A few principles we keep returning to.
What we're learning.
-
Context often matters more than a better prompt.
The right background knowledge often beats another wording tweak.
Read note → -
More automation can create more review work.
Speed without structure can multiply oversight.
Read note → -
Continuity is not the same as learning.
Keeping history is different from improving the next cycle.
Read note →
We test these ideas through real work.
This is not a finished framework.
acacia90 is an ongoing exploration of how small teams and AI can work well together.