12 PIECES · 05 SHELVES

What we learn building and operating our tools.

READING ORDER01—12

SHELF 01 · 03 PIECES

Persistent state

An agent system rents its model and owns everything else: the record of what it has done, the judgments on its past work, the rules and checks that encode its craft, and its standing with the people it serves. The owned parts are the ones that accumulate value, and the model is the part to plan on replacing.

07→08What compounds in an agent systemIn a blind comparison, a mid-tier model matched a frontier model on every dimension our tooling had encoded. The model is the part of an agent system to plan on replacing, and what compounds is the owned layer: the history, the verdicts, the encoded craft, and the standing it earns.ESSAYJUL 20265 MIN 08→09The value of the harnessA model in a chat window gives you drafts you still have to check. The same model inside a real pipeline produces finished work. This essay is about the harness, everything built around the model, and why each new model release multiplies whatever you have built there.ESSAYJUL 20266 MIN 11→12Ideas with bodiesAn idea held in a head or a note cannot be found by a stranger, cannot take a payment, and cannot learn from silence. Agents have made it cheap to form the body an idea needs to meet its market, meaning an address, an inbox, an account, and records that persist.ESSAYJUL 20266 MIN

SHELF 02 · 01 PIECES

Measurement

Most of what agents send into the world gets no response. When each stage of the path from sending to reply carries its own measurement, a non-response identifies the stage that failed, and each round of sends becomes an experiment that improves the next one.

09→10Silence is a signalMost work an agent sends into the world gets no reply, and a bare no-reply teaches the system nothing. Splitting the outcome into stages, received, opened, clicked, answered, turns silence into an error signal the system can actually learn from.ESSAYJUL 20265 MIN

SHELF 03 · 01 PIECES

Governance

The humans behind an agent system cannot review thousands of runs directly. Corrections recorded as written rules, and enforced by automated checks, carry their judgment into runs they never see, and the human role narrows to approval and correction.

10→11Encoding judgment as rulesMost of a person's judgment can be written down, and the written form is what governs. Corrections recorded as rules reach thousands of runs the person never sees, and every review makes the rules more complete.ESSAYJUL 20266 MIN

SHELF 04 · 06 PIECES

Foundations

Intelligence is now a resource anyone can buy, and a bought resource does nothing until it has a structure to run through. An agent is one such structure, an externalized piece of computation with a mind and a body, and agency is what the structures exist to expand: the power of a person or an organization to cause what they intend.

01→02Intelligence is waterIntelligence behaves like water. It presses on every surface it touches, passes through whatever opening exists, and takes the shape of its container, so the container sets the quality of what comes out.ESSAYJUL 20265 MIN 02→03Search that does not tireAn agent loop is a search algorithm: propose an action, carry it out, read the result, adjust. Retrying is the part of search that exhausts a person, and it is the part a machine gets at the price of a model call.ESSAYJUL 20266 MIN 03→04Shipping is mergingAgents made it nearly free to open parallel branches of work. A branch becomes progress only when its result is merged back into the one thing being built, and the merge is the step that did not get cheaper.ESSAYJUL 20266 MIN 04→05How to work with many agentsThe mental models that scale one person from ten agents to a thousand: hold macrostates, not microstates, and converge everything into one trunk.ESSAYJUL 20267 MIN 05→06The agent bodyAgent products all run on the same models, tools, and prompts, so the parts cannot explain why some improve and hold users while others stay demos. What separates them is the body: what persists between calls, where the boundary sits, and why the boundary is worth having.ESSAYJUL 20267 MIN 06→07Nothing grown in isolation survives transplantShipping speed and growth location look like one variable and are two: a team can launch every week while everything it builds grows against its own model of the market. Readiness is a product of contact with the destination, not a precondition for it.ESSAYJUL 20266 MIN

SHELF 05 · 01 PIECES

Economics

A startup is a temporary structure built to search for a working business, and the search has always been priced in human time. When agents supply the labor, the search is priced in compute instead, and markets too small, too thin, or too short-lived to repay a person's attention become worth searching.

12→01The granular startupSteve Blank called a startup a temporary organization searching for a repeatable business model, and nothing in the definition says how many people the search takes. When agents supply the labor the set of markets worth searching has to be recomputed, and at the limit the exploration of the markets startups ignore can itself be an automated process.ESSAYJUL 20265 MIN