Field notes

How to manage something brilliant and fast — and forgetful.

craftagent is where I write down what working with AI agents actually taught me: the principles, the architecture, the moves that held up — earned from my own faceplants.

12topic clustersfoundations → meta
58field piecesbilingual · VI / EN
4control gatesthe backbone idea
KNOWLEDGE RADAR · 10 CLUSTERSlive
Cluster 4 · Shipping with AI. Four gates — plan, checkpoint, impact, verify — so an agent ships real work without breaking things.
5 piecessweep · hover to pick →
New here?

Never handed work to an AI? Start here.

Familiar desk-pains — and the narrow doorway to your first handoff without freezing at the blank field.

lost a sale at 11 PMreports stitched by hand foreveropen the chat, no idea what to type
The backbone idea

Four gates on the life of one task.

An agent is a forgetful genius junior. Place a human-control gate at each spot it tends to fall — tap to see the prompt.

The whole content map

Twelve clusters of managing an AI agent.

58 pieces · 12 clusters
01

Steering the agent

Make it understand the task before it acts — through command structure and forcing functions, not luck.

4 piecesEnter
02

Context & memory

Memory is a finite resource: what to keep, what to drop, when to let a script do the work instead of the AI.

4 piecesEnter
03

Orchestrating many agents

When one agent isn't enough: split roles, hand off work, gather results without chaos.

4 piecesEnter
04

Shipping with AI

Four gates — plan, checkpoint, impact, verify — so an agent ships real work without breaking things.

5 piecesEnter
05

Production in the wild

Faceplants from the field — retold with names stripped, so you can dodge them first.

8 piecesEnter
06

Economics & tradeoffs

Tenfold speed is the sticker price — what you take home depends on the cost of rework, checking, and trust.

5 piecesEnter
07

How you change

You do not learn how to work with an agent once and move on — you pass through four stages, and the dangerous one is not the beginning.

4 piecesEnter
08

Tools & setup

Your setup determines what the agent can do — and CLAUDE.md is not documentation, it is the operating law of your agent.

4 piecesEnter
09

Autonomy — how far to let go

"Can I trust it?" is the wrong question. The right one: for this task, with this reversibility, with these stakes — where does the gate go?

4 piecesEnter
10

Measure & improve

Without a number there is no improvement — only a shifting feeling. Three metrics that can actually tell the difference.

5 piecesEnter
11

Security & trust

When an agent touches a real system, the question shifts from "is it correct" to "what can it reach, and what leaves your hands".

4 piecesEnter
12

Working as a team

Rules in one head don't multiply to a team — when many people plus many agents share one thing, the shared rules must be written and shared.

7 piecesEnter

An agent is not a machine you command. It is a genius junior with amnesia — you manage it, you do not let it run loose.

01 / Manage, don't release

A brilliant junior who types ten times faster than you, fearless — but wakes up having forgotten yesterday. So you supervise. And supervising means placing a guard exactly where it tends to fall.

02 / The real cost

It goes rogue once, you lose trust, then you re-read every line. That tenfold speed you just bought — gone. That is the real bill.

03 / Scaffolding beats model

The stronger the model, the more the control scaffolding matters. You don't need a smarter agent. You need to become a better manager.

A suggested entry

Start from “Shipping with AI”.

5 pieces · bilingual
c
The author

Each story here wraps a lesson paid for in full.

craftagentsomeone building and learning at once

What are you building with agents? Want to trade notes, push back, or build something together — drop a line.

58pieces12clustersVI·ENbilingual

Get new pieces by email

Field notes on working with AI agents — occasional, no spam.