Agentic Security
Engineering.

The field, defined — with its craft, its laws, and its anatomy.

§01The Term

Agentic security engineering is the discipline of integrating an agentic layer from first principles, as a first-class citizen of any defensive security system.

The term is often read narrower than it is. Two nearby ideas keep getting attached to it:

1

Securing the models themselves — hardening against prompt injection, jailbreaks, and the like.

2

Defending against AI-driven attacks — the adversary pointing models at you.

The field includes both — a system that reasons with models carries them in its attack surface, and AI-augmented adversaries are table stakes. But it is more than the sum of those parts: the heart of the discipline is the defensive system itself, with the agentic layer working inside it.

§02The Craft

If agentic security engineering is the what, applied harness engineering is the how.

Applied harness engineering is a way of thinking: knowing when, where, and how to integrate an agentic layer into a defensive system — and, just as importantly, when not to.

There is no one correct architecture to hand over — the right answer depends on your telemetry, your threats, your constraints. The craft is the way of thinking you apply to your own context.

§03The Object
agent = modelselected + harnessengineered

The model you select — you will realistically never train a frontier model, and beyond selection you change little. The harness you engineer — it is just an application, built exactly how you want.

A harness is the deliberate orchestration of three collaborators — human judgment, agentic reasoning, and deterministic code — each used only where it is strongest, and designed that way from the ground up.
§04The Laws
I

Collaboration is first-class, by design

The human–agent relationship is part of the architecture, not an afterthought — not AI bolted onto an existing product. The primary design question is how to shape that relationship so both operate at their strongest.

II

Amplify, don't automate

The analyst stays in the loop; the agentic layer plugs in at specific points as a force multiplier. The goal is a sharper analyst, not an absent one.

III

Three systems, used where each wins

Humans, deterministic code, and the agentic layer each carry real strengths and real weaknesses. Most of the work stays deterministic code — the agent is used only where it earns its place, and its weaknesses are contained everywhere else.

§05The Golden Rule

Only ever make things as complex as they need to be.

The rule that governs every decision across all nine systems — how much context an agent gets, how much machinery a job deserves. Match the need, then stop.

§06The Anatomy

There is no universal harness — which pieces it needs depends on what the agent is for. For a defensive-security agent, the terrain is nine core systems:

01

Data–Agent Interface

how telemetry is shaped for agents, and consumed

02

Shared State

findings persist across agents and hunts

03

Tools

external processes, mediated by the harness

04

Orchestration

arranging multiple agents, with gates

05

Skills

tacit hunting knowledge, made executable

06

Context Engineering

inference-time knowledge, provisioned

07

Feedback Loops

the system reflects, and improves itself

08

Evaluations

change measured, not vibes

09

Adversarial Resilience

the system defended from attacker influence

§07The Source

If you want to learn the field in practice — building the system end to end — the course is where to do it.