Appendix E: Glossary

How a role’s result is checked, by whom, and with what evidence. It is written into every Role Charter, before the work starts, and never rests on the occupant’s own word. See Chapter 9.

Human Resources for agents, a term coined by the author: the function on the org chart, run by a person, a bot or both, that writes charters, onboards agents, reviews their performance, settles duplicates and retires them. See Chapter 17. In brief: What Is Agentic Resources?

What the organisation is for, from the founder’s point of view: what you want it to give you and the people it serves. See Chapter 4.

The organisation documented well enough that you could stand it up again tomorrow: roles, charters, playbooks, Role Packs and the rules that connect them. The idea follows Michael Gerber’s "franchise prototype". See Chapter 3.

A record of what each role owes, to whom and by when, checked against evidence. It tracks what is owed rather than what is done, so problems surface before the deadline. See Chapter 13 and the template in Appendix B. In brief: What Is a Commitment Ledger?

The improvement loop: design a better way of doing the work, measure whether it is better, then lock in what proves itself. It follows Gerber’s innovation, quantification and orchestration. See Chapter 2 and Chapter 11.

What "finished" looks like for the organisation, including its shape and its mix of people and agents. See Chapter 4.

A short, blame-free review that turns a recurring failure into a change to the system, so the whole class of error stops. "The model got it wrong" is not an accepted root cause. See Chapter 16.

The third lock-in tier: a rule the software enforces whatever the occupant decides, reserved for irreversible actions, security boundaries and the acceptance check. See Chapter 11.

A step that cannot be undone once taken, such as sending to a customer, paying, deleting, publishing or merging. This is where humans and hard rules belong. See Chapter 14.

How firmly a step is fixed: plain English by default, a script for calculation and lookup, a hard rule only where nothing may go wrong. Lock in the checks, not the steps, and review every lock-in when the models improve. See Chapter 11.

Whoever currently fills a role: a person, an agent, or both. One occupant can hold several roles, and a role survives a change of occupant. See Chapter 5.

One sentence at the top of a Role Charter saying why the role exists, starting "To…". See Chapter 9.

A line in the Role Charter saying whether the role owns its answers or works as a helper for another role that does. See Chapter 9.

A documented procedure for a recurring piece of work, written in plain English by default, with the reason for each step and a tier marker where a step is locked in. See Chapter 10.

A position on the org chart, defined by the result it produces. An occupant fills it. Design the roles first, then fill them. See Chapter 5. In brief: What Is an AI Agent Org Chart?

A role’s one-page specification: outcome line, the work, standards (quantity, quality, behaviour), authority, acceptance, handoffs, sponsor. The same format serves people and agents. See Chapter 9. In brief: What Is a Role Charter?

A check that a role keeps three things consistent: the kind of work, the level of judgment it needs, and the occupants available to do it. If they pull apart, split the role. See Chapter 5.

Everything a role’s occupant needs to know to do the job on day one, with the reasons behind the rules, kept lean and linked to live sources. See Chapter 12.

The few numbers that say whether the organisation is working. See Chapter 4.

The second lock-in tier: a small program, often written by the agent itself, that does a calculation or lookup the same way every time. See Chapter 11.

A trial period in which an agent drafts or recommends but does not act, so its work can be compared with a human’s before it earns autonomy. See Chapter 14.

The three kinds of work: shaping what the organisation becomes, steering how it runs, and doing the work itself. They follow Gerber’s Entrepreneur, Manager and Technician. See Chapter 1. In brief: What Is Shape, Steer, Do?

The rule that only one role changes any given piece of work at a time, while others may advise or review. See Chapter 6.

The named human accountable for an agent’s purpose and lifecycle: why it exists, what it may access, and when it retires. See Chapter 7. In brief: What Is an Agent Sponsor?

The organisation’s purpose, written so that people and agents can make decisions from it. See Chapter 4.

The briefing rule: tell an occupant the result you need and why it matters, and leave the method to the role that owns it. See Chapter 8.

Making requests, handoffs and approvals in shared channels rather than private messages, so they can be seen, tracked and picked up. See Chapter 15.

An open standard, version 1.0 since April 2026, for agents from different vendors or organisations to talk to each other and prove who they are. See Appendix D.

An AI system given a goal that works towards it in a loop: deciding what to do, using tools, checking the result, and continuing until done or stuck. See Chapter 5.

An agent’s own account and name, separate from any person’s, so its actions can be traced, limited and switched off. See Chapter 7.

Several agents working on one task, either under a coordinating agent or as peers sharing a task list. Useful for parallel work; usually worse for sequential work. See Chapter 6.

A request for a human to say yes before an agent acts. People approve almost all of them, so a prompt is only useful at a genuinely irreversible point. See Chapter 14.

Rich Sutton’s 2019 observation that general methods which use more computation have beaten hand-built human knowledge in AI over the long run. This book applies it to management: over-specified instructions hold capable agents back. See Chapter 8.

What an agent does when its context window fills: it summarises the conversation so far and carries on from the summary. Details can be lost, which is one reason ledgers live outside the conversation. See Chapter 13.

Choosing what information an agent sees at each moment, aiming for the smallest set that gets the job done well. The technical side of a Role Pack. See Chapter 12.

The amount of text a model can consider at once, including instructions, documents and the conversation. Anything outside it, the model cannot see. See Chapter 12.

A setting that forbids an agent a particular action or file outright, whatever it has been asked. A common form of hard rule. See Chapter 11.

Software that records each step of a long-running job so it can resume where it left off after a crash or restart. See Appendix D.

Short for evaluation: a set of test tasks and a way of grading them, used to check that an agent does its job well enough and keeps doing so. See Chapter 16.

The person, agent or test that checks another occupant’s work. It works best with its own context and its own evidence. See Chapter 9.

Passing a piece of work, and responsibility for it, from one role to another. Most lost work goes missing here. See Chapter 15.

The software around a model that makes it an agent: it supplies instructions and tools, runs the loop, enforces permissions and records what happened. See Chapter 11.

A small piece of the harness that runs automatically at a fixed point, such as before a tool is used or before the agent says it is finished, and can block the action. A common form of hard rule. See Chapter 11.

A design in which a person reviews or approves an agent’s work at chosen points. This book’s version: humans at the irreversible points, not everywhere. See Chapter 14.

Giving any occupant, human or agent, only the access its role needs, for only as long as it needs it. See Chapter 7.

An open standard for connecting agents to tools and data, so one connection to your CRM or ticket system works with any compatible agent. See Appendix D.

Notes an agent keeps between sessions about what it has learned. Useful, but it drifts unless reviewed and merged into the Role Pack. See Chapter 12.

The underlying AI system, such as a version of Claude, GPT or Grok, that does the reasoning. An agent is a model plus a harness, instructions and tools. See Chapter 5.

An agent, or person, that breaks work into pieces, hands them to other agents and assembles the results. The manager in a hierarchy of agents. See Chapter 6.

Two ways of scoring repeated attempts. pass@k is the chance of at least one success in k tries; pass^k is the chance that all k succeed, which is what matters for unattended work. See Appendix D.

Showing an agent a short summary of each skill and loading the full detail only when needed, which keeps its context lean. See Chapter 12.

An attack in which text the agent reads, such as an email or web page, contains instructions meant to hijack it. A reason to limit access and keep hard rules outside the model. See Chapter 14.

Work an agent does at fixed times (every weekday at nine, say) rather than when someone asks. Engineers often call it a cron job. See Chapter 13.

A packaged set of instructions, and sometimes scripts and reference files, that teaches an agent one kind of task the way your organisation does it. The usual home for a Playbook. See Chapter 10.

A helper agent started by another agent for a narrow task, working in its own context and reporting back a summary. See Chapter 6.

The standing instructions an agent receives before any conversation, setting who it is and how it behaves. In this book, the thin part of a role: identity and limits, not the whole job. See Chapter 5.

The unit models read and write in, roughly three-quarters of an English word. Context windows and costs are measured in tokens. See Chapter 12.

An action an agent can take beyond writing text, such as searching, sending a message, querying a database or editing a file. Each use is a tool call. See Chapter 7.

A visual drag-and-drop tool for wiring steps and AI calls into a fixed flow. Precise, but this book argues plain-English playbooks usually spread further and adapt better. See Chapter 10.