Zaga · AI Lab — an engineering point of view

Building with AI.

Keep the decisions. Hand production to the agent.

This is how we think about engineering now — the shift that changed the work, the eight principles that follow from it, and the engineer we hire, grow, and promote because of it.

01 · The shift

The work moved up the stack.

When producing software became fast, the work moved up the stack. Less time goes into writing code. More goes into deciding what matters — and checking that the result is right.

Coding was never the easy part. What changed isn't the difficulty; it's the split.

The same tool cuts two ways. When building becomes cheap, more gets built — for better and for worse. The outcome depends less on the tool than on the discipline of the team using it.

AI unlocks speed. A playbook keeps the team on course.

AI-assisted engineering
Using AI models in how you build — drafting specs, generating and reviewing code, debugging, monitoring. A way of working, whatever the software is. This is what we mean.
AI product development
Building software where AI is the product — the feature the user touches.
Agentic engineering
Designing systems of autonomous agents. Also about the product, not the process.

"AI engineering" gets used for all three. We mean the first — nothing here requires the product to have AI in it.

One line holds all of it

Own the judgment, delegate the production.

02 · The work

So the work splits in two — around the agent.

Leverage moved upstream. Grounded practice is no longer about writing code; it's about directing, reviewing, and verifying what does.

Upstream — where the leverage moved Decide · shape · design
U1

Know what's worth building

Is this worth doing at all?

Read the need behind the request, and push back when scope or complexity outrun the value. Generation is cheap, so the default becomes to build more — knowing what to leave unbuilt is half the job.

U2

Shape the system

How the whole fits together.

Hold the whole-system view and the concerns no single task raises. The model can draft architecture now: set the direction and judge what it proposes — never let it design unsupervised.

U3

Design the work

Break it into pieces you can steer and check.

Units small enough to steer and verify. Set the agent up to succeed before it begins — inputs, a clear definition of done, and the checks decided up front.

U4

Craft the context

Give the model the right inputs.

Context is an asset you curate and reuse, not a throwaway prompt. Give each task exactly what it needs — relevant, complete — and keep the project's knowledge organized.

U1–U2 are the judgment band: what gets built. U3–U4 are the craft band: how the agent is set up to build it.

The agent writes the code

Grounded practice — how building changed Direct · review · verify
G1

Own the system, not the tokens

You answer for what ships.

"The model wrote it" is never an excuse — and "it works" is not the bar. You own whether the code is simple, reuses what's there, stays in bounds, and doesn't drift.

G2

Build verification around the work

Confirm it's right with systems, not inspection.

Volume outruns line-by-line review, so verification becomes a system: risk-weighted spot-checks, tooling, monitoring — heavier where a miss is expensive. This is where the work bottlenecks now.

G3

Keep your hands in the work

Stay sharp, stay hands-on.

Supervising well is not a step down from the craft — it takes more of it. Disengage and the decline is quiet: you won't notice until you can't debug what the agent can't.

G4

Be fluent with the tools

Know what to use when — and where they fall short.

Know which tool to reach for, where the models are confidently wrong, and when not to reach for AI at all. Fluency is a moving target — spend the expensive models where they earn it.

G1 holds the standard. G2 proves it at volume. G3 and G4 keep the skills and the tools sharp.

03 · The engineer

How we build shapes who we look for.

A playbook provides structure, but people determine the outcome. These are the six traits we hire for, develop, and promote — the anatomy of an AI-fluent engineer.

01

Judgment

Decides well — what's worth doing, what the real problem is, which way to go.

02

Taste

The eye for what good looks like, in systems and in prose.

03

Ownership

Answers for the outcome — whoever, or whatever, typed it.

04

Discipline

Does the unglamorous checking; holds the bar under pressure.

05

Excellence

The standard. Cares that the thing is actually good, and won't let it slip.

06

Curiosity & self-drive

Needs to know why and how; stays current as the tools move.

The tools will change. These traits matter regardless.

Two traits, not one

Taste is an eye. Excellence is a standard.

They look like one trait, but they aren't — you can have either without the other.

Excellence →

Rigor, wrong aim

Holds the bar — but can't tell good architecture from bad.

What we hire

Sees what good is — and won't let it slip.

Ships slop

Neither the eye nor the bar.

Eye, no refusal

Sees good work — still ships slop under pressure.

Taste →

Taste lets you see the gap between good and mediocre. Excellence is the refusal to ship the mediocre once you see it. Name both, and you know which is missing — a taste gap and a care gap take different coaching.

The failure underneath

Almost every failure is one move: handing over the judgment.

Taking the brief as given. Letting the agent design the architecture unsupervised. Trusting an all-passing test suite. Rubber-stamping what reads clean.

Outsourcing the judgment, not just the production

The root of the rest. Keep the decisions and hand over the work — not the other way around.

Trusting fluent output as correct output

AI errors read clean, confident, and plausible — which is exactly why verifying, staying hands-on, and tool fluency are what catch what confidence hides.

Abdication — handing over the judgment, not just the production. The inverse of the one line.

How we operationalize it

The coding test was a stand-in for judgment. AI severed it.

A clean solution used to be cheap, fast, hard-to-fake evidence of the skills underneath — decomposition, debugging instinct, trade-off judgment. It isn't anymore.

1

It was a proxy

A clean solution stood in for the judgment underneath. Cheap to run, and hard to fake.

2

AI severed it

When anyone can produce a clean solution, the solution no longer proves the skill.

3

So we measure it directly

Decomposition, trade-offs, product sense — plus the new skill: directing and distrusting agents.

This is what "AI-fluent" means at Zaga. Not that our engineers use the tools — everyone does. That they're vetted on the judgment the tools can't supply, and held to it on your team. We'd rather be honest about what's still an open question: the proxy broke, that much is clear. Whether the new formats fully predict on-the-job success is something the whole industry is still learning.

AI multiplies what a team already has.

If you want engineers who bring judgment to multiply — not just hands to add — let's talk about what you're building.

Talk to us