The secret: you already know this
Discover that the 7 principles are written people management for people who don’t guess anything.
What it is
Replace the word “agent” with “new employee” and reread the 7 principles: nothing feels strange to someone who has already led others. Intention describes the role; context is onboarding; data is the official system; criteria are goals; autonomy is the scope of authority; observation is the report; supervision is the 1:1 meeting. The report on “the new era of AI” gave a new name to old practices.
Why learn
People who think managing agents means learning everything from scratch get stuck before they even start. Realizing you already know a good part of the method removes fear and speeds up your first delegation. And it gives you a simple test: if you wouldn’t delegate like that to a person, don’t delegate like that to an AI.
Key concepts
- Role: intention—why the position exists.
- Onboarding: context—what you teach on day 1.
- Scope of authority: autonomy—“up to R$ 500 you decide.”
- 1:1: supervision—review, correct, promote or not.
What it is
A new employee infers a lot: they observe coworkers, notice the company tone, and ask in the hallway. The agent doesn’t do any of that; it works only with what’s written in the instructions and the data it has access to. Everything a person would infer has to become text: the tone, the source that counts, what to do when information is missing, and when to stop.
Why learn
Most agent mistakes come from what “seemed obvious” to the person who delegated. With a person, lack of clarity costs a lot by going slowly; with an agent, it costs immediately and at scale. Listing the implicit is the cheapest way to avoid this mistake.
Key concepts
- Tone: how you talk to a customer—formal or friendly.
- Source: which spreadsheet or system is the one that counts—and which one isn’t.
- If something is missing: what to do when the data doesn’t exist.
- Stop: what situation makes it call you.
What it is
Code agents, like Claude Code and Codex, are AI programs that work inside a repository—the folder of a project with all its history. Anyone who uses these agents practices the 7 principles every day: the plan mode (the agent proposes before changing anything), the CLAUDE.md or AGENTS.md (a file with the project rules), the repository as the source, tests (automated checks), permissions, failure log, and review.
Why learn
This shows the method isn’t stage theory: it already works in production, in the hands of thousands of people. Even those who don’t program benefit by copying these practices into other areas. And programmers gain a vocabulary to explain their own routine to managers.
Key concepts
- Plan mode: intention—combine before executing.
- CLAUDE.md: context—the house rules in a file.
- Tests: the readiness criterion—“done” is whatever passes the verification.
- Review: supervision—humans approve the irreversible.
What it is
In Claude Code, permission mode defines what the agent can do without asking. In plan, it only reads and proposes; in default, it asks for approval for every edit or command; in acceptEdits, it edits files on its own, but commands still ask; in bypassPermissions, it allows everything. It’s the same N0 to N4 autonomy ladder—just with a button instead of a conversation.
Why learn
Choosing the “on the fly” mode is the most common mistake people make when they start with code agents. With the ladder, the choice becomes rule-based: the level comes from the action and the risks, not from urgency. And it becomes clear what has to happen in order to move up a rung.
Key concepts
- N0 and N1: plan—only reads and proposes.
- N2: default—approves every edit and command.
- N3: acceptEdits—edits on its own; commands ask.
- N4: only with hooks and isolated environment.
What it is
Three pieces turn the principles into real configuration. The instruction file (CLAUDE.md for the Claude Code, AGENTS.md for Codex and others) sits at the root of the project and is read in every session. Tests are commands that automatically verify whether the work is correct. Hooks are triggers that run before an action and can block it; the allow and deny rules in the configuration grant or prohibit actions.
Why learn
Writing “don’t deploy” in the conversation isn’t enough: the conversation ends and the rule disappears. In the instruction file, it applies every time; as a deny rule or hook, it applies even if the agent forgets. It’s the difference between asking and guaranteeing.
Key concepts
- CLAUDE.md: house rules read in every session.
- Tests: a readiness criterion that doesn’t depend on opinion.
- Deny: an action prohibited by permissions.
- Hook: a lock that blocks the irreversible before it happens.
What it is
The 7 questions are the same ones a good manager always asked. Without intention, the agent efficiently does the wrong task; without a source of truth, it picks the information on its own and picks badly; without criteria, it says “done” and you only find out later that it wasn’t. And the design of the principles is a circle: supervision feeds back into intention, each mistake becomes a rule, and each clean week becomes a rung of autonomy.
Why learn
Blaming “the AI” prevents you from fixing what’s within your reach: delegation. When you treat each error as a missing rule, the agent improves week after week without switching tools. The circle turns the Agent Sheet into a living process, not a form you fill out once.
Key concepts
- Without intention: it does the wrong task well.
- Without a source: it picks bad information.
- Without criteria: a “done” that isn’t actually done.
- Circle: the observed error becomes a new rule.