The Thirteenth Loaf
What gets harder when intelligence gets easier? An operator’s investigation of coordination, shared mistakes, and trust.
Read the essay on Substack ↗What gets harder when intelligence gets easier?
b.akery is being built to help people and AI agents keep work moving across projects and tools. Decisions, context, and corrections should travel with the work, without you having to keep the whole business in your head.
For founders and operators already using AI agents.
What done looks like.
Decisions and their reasons stay connected to the work. Your agent can find what matters now, recognize a correction, and see which other work it affects.
That is the experience I’m building toward. You work through the agent you already use, without a habit of saving notes or repeating the backstory. An optional view should make blockers and the next decision clear.
Keeping work moving should take less of your attention.
The Thirteenth Loaf
All essays →
Essays, field notes, and open questions. Read here; subscribe and join the conversation on Substack.
Three questions behind the work.
-
Coordination Tax on Intelligence
What gets lost when work moves between people, projects, and agents? Count the repeated explanations, missed decisions, and corrections alongside the useful work. Where does the effort go?
-
Confabulation
Why do humans and agents fail together, honestly? Trace a shared mistake: what the person assumed, what the agent added, and where either could have interrupted it.
-
Trust & AI
What does an agent need to know before it acts? Can we trace a decision, see what changed, and recognize when the available context is incomplete?
I’m James Nichols.
I work with the agents, too.
b.akery is developing an early coordination alpha to carry decisions, context and corrections across people, projects and AI tools.
I work with AI agents across my projects. Building software is part of that, along with the decisions and follow-through that keep the business moving.
The question is how to keep that shared understanding useful as people, projects, and tools change, without making me manage another system.
The first alpha is in development. The writing and real work will help test whether b.akery reduces repeated explanations and intervention, including the effort it takes to set up and use.
Bring a real piece of your work.
Think of a recent task where a decision got lost, a correction didn’t reach the next agent, or you had to explain the same thing again. What happened, and what did you already try?
I’m looking for founders and operators willing to discuss those experiences and try the alpha when it is ready. Before you take part, we’ll explain the task, the time involved, and what we’re trying to learn.
Register testing interest