🎨 Design
Design
Problem framing, user needs, agent scope, tool selection.
Lesson 1
Designing agents — overview
What to decide before you build anything.
Open
Lesson 2
Do you actually need an agent?
Direct call → augmented LLM → workflow → autonomous agent.
Open
Lesson 3
The four types of agent
Narrow/broad × assistive/autonomous.
Open
Lesson 4
Managing agents like new employees
The manager metaphor — how onboarding, delegation, and oversight transfer to AI agents.
Open
Lesson 5
The Agent Canvas
Eight questions to answer before you build anything.
Open
Lesson 6
Problem framing & scope
Job-To-Be-Done, user needs, and scope-creep kills.
Open
Lesson 7
Getting started
Five tips for your first agent project.
Open
🎨 DesignQuick quiz
0/5
Q1.What's the best default starting point when you think you need an agent?
Q2.Which quadrant of the agent types matrix carries the highest governance burden?
Q3.What cell of the Agent Canvas is most important for preventing scope creep?
Q4.Which is the weakest default answer to 'how do you check the agent is working?'
Q5.A stakeholder wants to add a new capability during design. What should you do first?