The AI Operating Sprint is a live working session, not a seminar.See the Sprint →
SET EARTH CONSULTING
How I think about it

This is the map of how I work: standing agents, durable context, running services. The work moves through it; I do the judgment.

The standing agent fleet The overlapping fields of standing agents, durable context, and running services. Standing agents, durable context, and running services overlap. The center is a fleet Braydon can see, steer, and keep running. STANDING AGENTS DURABLE CONTEXT RUNNING SERVICES They stay there separate workspaces They know the work memory · repos · tasks They keep moving backends · triggers A fleet I can steer visible · context-aware · task-bound The circles overlap because the work does. The fleet is the system. The chat window is one surface.
  1. Standing agents 20–50 workspaces
  2. Durable context memory · repos · task lists
  3. Running services backends · timers · triggers
The standing fleet. An agent is a workspace with memory, repositories, tasks, and services around it. I keep the fleet running and step in where judgment is needed.

How I think

The fleet is how I run more than one operation at once.

[01]

the unit

The unit is a standing workspace with memory, a repository, a task list, and the systems it is connected to. When I have work, I pick up a fleet that already knows the work.1

[02]

the standing fleet

A fleet is many of those units standing at once, kept separate by company and purpose. When work comes in, it goes to a workspace that already knows the operation. Agents get built and retired as the work changes; what persists is the memory.2

[03]

the overlap is the work

The work is in the overlap: one agent is rarely the whole job. A question moves through several worldviews and gets challenged. A build moves through research, planning, dependencies, and review. The shape is the same: context, task, execution, then a handoff I can inspect. Work that runs through this shape is on the examples.3

[04]

I decide

I design the contexts, assign the work, redirect it, and decide what becomes part of the next state. The agents keep the work moving.4

Notes

  1. [1] The fleet map above shows the three fields behind this: standing agents, durable context, running services.
  2. [2] The count (10+ fleets, 2–50 agents each) and the daily texture of the fleet live on How I run. Agents are built and retired as the work changes.
  3. [3] The workspaces behind those cases are in daily use. They aren't demos reset after a screenshot.
  4. [4] Operating sources: STRATEGY.md, OPERATIONS.md, notes/braydons-view-of-ai.md (internal).

The same pattern shows up in different kinds of work. These are not demos I reset after the screenshot. They are harnesses and workspaces I keep using.

01

Agent Designer

A multi-role harness for designing agents, panels, prompts, and assignments.

Leaves: Design and review
02

Shell Scenario Panel

Worldviews, scenarios, impact analysis, specialist seats, and a quality pass.

Leaves: Scenario brief
03

FDA and patient work

Research, rendering, planning, dependencies, and review moving through a graph.

Leaves: Reviewed work product
Set Earth Inc · Contracts and invoices under this entity · Reply to b@mcco.us