Forward-deployed / Learning zone
Agentic AIa standalone module
A standalone module

Agentic AI for the AI PM

What agents actually are — the loop, tools, memory, and planning — and the reliability, security, and economics that turn demos into products.

8 lessons+ recapknowledge graphdiagrams included

A chatbot answers. An agent acts. Give a language model tools, a goal, and permission to loop — observe, decide, act, check the result, repeat — and you get software that can do things: research a market, fix a bug, book the logistics, run the workflow. That's the promise. The practice is a young discipline. It has real engineering behind it, but also a thick layer of hype on top — invented protocol acronyms, "8-layer stacks," and demos that collapse on contact with production.

This module is the honest map. It teaches what an agent actually is, and the machinery that makes one work: tools, context, memory, planning. It covers what changes when agents multiply — multi-agent systems and the real protocol landscape. And it covers the three disciplines that separate shipped agents from viral demos: reliability, security, and unit economics. Every lesson ships a diagram. The module opens with a knowledge graph so you can see how the pieces connect before you study them one at a time.

The knowledge graph

Agentic AI isn't a layer cake — it's a loop with disciplines attached. Everything in this module hangs off this picture:

What it knows · lesson 3

Context engineeringcuration · compaction · offloading Retrieval / RAG Persistent memoryfiles · notes · profiles Context windowthe working memory
▼knowledge flows into the model▼
The core · language model + loop
gather→ decide→ act→ observe
⟲repeat until done — or a budget says stop
planning & reflection steer each cycle ▼tools act on the world · results feed back

How it acts · lesson 2

Tools & function calling Integrations & MCP Sandboxes & permissions

How it thinks · lesson 4

Planning & decomposition Reflection & self-correction
many loops at once — orchestrators & subagents (lesson 5)

Why it's trusted · lessons 6–7

Traces→ Error analysis→ Evalsgates offline
Guardrailsblocks inline Security Human in the loop

Why it's a business · lesson 8

Unit economics→ Workflow captureoutcomes, not seats
Agent UX & trust→ Viable product

Read it in three passes. The spine: knowledge flows into the model. The model drives the loop. The loop acts through tools, and tool results flow back as new knowledge. That cycle is the agent. The amplifiers: planning and reflection make each cycle smarter. Multi-agent patterns run many cycles at once. The disciplines: every cycle leaves a trace. Error analysis turns traces into evaluators. Guardrails police the loop inline, while evals gate it offline. Security bounds every tool. A human approves the irreversible. Economics decides whether any of it is a business.

The lessons

Each lesson pairs the concept with a 🎯 For the AI PM briefing. It names the decision the concept should change, and the question it should make you ask. Each lesson also has a diagram to make it concrete. Builders who want to go deeper than concepts can construct this machinery hands-on in the Harness engineering track.

Connects to other tracks

📌 Close out the module: Recap & real-world examples.

The lessons

01

What is an agent?

Read lesson →
02

Tools & function calling

Read lesson →
03

Context & memory

Read lesson →
04

Planning & reasoning

Read lesson →
05

Multi-agent systems & protocols

Read lesson →
06

Reliability & evals

Read lesson →
07

Safety, security & governance

Read lesson →
08

Agentic AI as a product

Read lesson →
📌

Recap & real-world examples

Read recap →