Course Overview

Agentic · Foundation

How AI Agents Work

Moving from the conceptual to architecture: a practitioner’s guide to agentic systems.

We examine the agentic process to understand the underlying logic of the loop. This course provides the structural foundations required to design, debug, and govern agents with technical confidence.

When you complete this course, you'll be able to:

  • Trace the complete inference cycle to understand precisely where the orchestration layer intervenes.
  • Internalise tool-calling as the core functional bridge of agency, identifying where latency and risk accumulate.
  • Dismantle the "persistent entity" illusion to understand the function of memory layers.

Duration

~3.5 hours

Modules

3 modules

Level

foundation

Format

Self-paced online

Audience

Technical leaders and practitioners who need to move past the "AI agents as an employee" mental model to a system-oriented reality.

Access period

12 months

$129

Full course · One-time payment · 12 months access

Tax included · Price shown in your local currency at checkout.

Buy Course - $129

Registration required to purchase.

Log in to access purchased courses.

  • All 3 modules · access on any device
  • Progress tracking
  • 12 months access from purchase

What you'll learn

  • Trace the complete inference cycle to understand precisely where the orchestration layer intervenes.
  • Internalise tool-calling as the core functional bridge of agency, identifying where latency and risk accumulate.
  • Dismantle the "persistent entity" illusion to understand the function of memory layers.
  • Equip yourself with tools to look "behind the curtain" and assess the reasoning gap.

Modules in the Course

1

The Agent Loop

We move from high-level descriptions to a step-by-step walkthrough of the inference cycle.

Available 45–60 mins
2

Memory and Identity

Dismantling the anthropomorphic framing to see the state-management beneath.

Available ~75 mins
3

Managing the Reasoning Gap

Traditional logs aren’t enough. Learn to manage the gap between agent execution and human oversight.

Available ~75 mins

Further Reading

Safety

Constraint Architecture for Autonomous Agents

10 min read

Technical

The LLM-as-Judge Problem Nobody Is Talking About

7 min read

Governance

The Inference Audit Trail: Making Every AI Decision Accountable

8 min read
All insights