What this book is # This is a practical account of how I actually work with AI agents as a data engineer, written so I can hold myself to it and so anyone doing similar work can borrow what fits. It is not a survey of every tool, and it is not a promise that the machine will do the thinking for you. It is a record of the habits, the setup, and the guardrails that let me hand real work to an agent and still stand behind what ships.
Introduction # AI only makes sense as a tool once you have already been through the cognitive struggle yourself. The struggle is not the obstacle to learning, it is the learning, and it is the only thing that lets you judge what a model hands back instead of accepting it blindly.
Introduction # Speed without ownership becomes expensive very quickly. When an agent operates in an area you do not understand deeply, you end up with changes you cannot explain, verify, or recover from with any confidence.
Introduction # AI has moved from side-task support to operational systems, and that shift changes the bar. Prototype-era habits are fine for a sketch, but production work demands measurement, reliability, and a much higher standard of verification.
Introduction # The fastest way to replicate this way of working is to get the environment right once. A single multi-repo workspace, a few core settings, one rule, one skill, and a verified set of connections do most of the heavy lifting before any real work starts.
Introduction # No single model wins every task. I keep several in rotation on purpose and pay the switching cost so I can match latency, reasoning depth, and tool behavior to the work in front of me that hour.
Introduction # Rules, skills, and commands are how you encode intent directly into the tools so the agent starts each task already knowing your standards. When AI is the primary consumer, letting it draft these first usually produces clearer execution structure, while you keep policy and final approval.
Introduction # MCP is how the agent reaches the tools where the work really lives, including issue trackers, repositories, and databases. Wired well, it turns a messy brain dump into a structured issue that becomes the contract the agent reads while it implements.
Introduction # Guardrails are not brakes, they are the lane markers that let me drive fast because I know exactly where the road edges are. The goal is never to slow the agent down on the work that is safe, only to remove the handful of ways it can do something I cannot undo.
Introduction # As models get more capable they get more confident, and that confidence makes them take liberties, such as pushing to a primary branch or running a query nobody asked for. The last chapter described the guardrail pattern. This one explains why those guardrails need to exist before the model gets a chance to improvise.
Introduction # AI brain fry comes from too many parallel prompts, rapid context switching, and weak stopping conditions. The workload feels productive while the cognitive overhead compounds, so sustaining the practice means managing yourself as carefully as you manage the agent.
Introduction # Tests and documentation are the most neglected parts of data engineering because they are tedious to write by hand. An agent that reads a model, infers the business logic, and generates the matching definitions gives you the rigor without the manual overhead, as long as you still review the result.
Introduction # The first AI move around history is not asking the agent to build a history table. It is asking the agent to argue against needing one. Stored history is stateful, expensive to recover, and easy to misuse, so the assisted workflow has to begin with restraint rather than generation.
Introduction # AI agents work best when the system they are helping with is legible. Declarative pipelines make the desired result visible in one place, which gives both the agent and the human reviewer a better surface to reason over than a scattered chain of tasks, schedules, and merge scripts.
Introduction # The best AI-assisted modeling work happens where the pattern is strong and the judgment boundary is clear. Data Vault 2.0 is a useful example here because hubs, links, satellites, and effective satellites are repeatable enough for an agent to scaffold, while the decisions that make the model correct still belong to the human.
Introduction # Working fast with agents makes it easy to sprint until you break. Leaving room to breathe between pushes is what keeps the work sustainable and keeps the judgment sharp enough to be worth accelerating in the first place.
Introduction # Big systems and good habits are both built the same way, little by little, one small rep at a time. Shipping one piece at a time keeps the work grounded and keeps momentum alive long after the initial enthusiasm fades.
