Design the runtime

A capable model still needs a runtime around it. This path covers what the agent sees, what it is allowed to do, and when it is required to stop.

Start with Context Engineering →

In order

The sequence, and why each step follows the last.

01Context Engineering: Why More Context Can Make an AI Agent WorsePractical explainer411m

The model can only make its next decision from what is in front of it. Context engineering is the practice of keeping that working set current, relevant, and deliberately small.

Practical explainer11 min read5 sections 02Harness Engineering: Why a Better Model Is Not the Whole AnswerSystems explainer511m

A capable model still needs a well-designed runtime around it. Harness engineering is the work of giving an agent useful context, tools, boundaries, state, and evidence of completion.

Systems explainer11 min read5 sections 03Loop Engineering: What It Means—and Why It Is More Than Letting an Agent Run ForeverEmerging concept510m

Loop engineering is an emerging label for designing repeated agent work: its trigger, state, feedback, boundaries, verification, and explicit ways to stop or hand off.

Emerging concept10 min read5 sections

The other paths

Path 01 · 3 pieces · 31 min

Understand the system

The moving parts, before you choose a framework or a model.

SequencedOpen →

Path 03 · 3 pieces · 34 min

Prove it works

From a promising demo to repeatable evidence and safer operation.

SequencedOpen →