Course 1

Product Design with Agentic AI

High-quality static models — chairs, lamps, appliances — designed by prompting AI agents in Blender.

Learn to specify intent precisely enough that an agent builds a clean, correctly-scaled model, and to catch the constraints it silently drops.

Choose your track

Track A (designers/artists): focus on judgment — reading agent output critically and steering it toward your intent.

Beginner

First prompts, basic constraints, reading agent output.

Your first product prompt

ABC ~7 min

Ask an agent to "make a chair" and it returns something chair-shaped, floating above the floor, three centimetres tall, with its origin marooned at the world centre — the failure isn't the geometry, it's every constraint a human designer holds without noticing.

Reference images and locking proportion

ABC ~7 min

Hand the agent a reference photo and it will confidently describe a different object than the one in the image — agents narrate what they expect a "lamp" to be, not what they see, so proportion drifts toward the average of their training data.

Intermediate

Multi-step prompts, references, recovering from common failures.

Materials, bevels, and making it read as real

ABC ~7 min

The agent's model looks fake for a reason you can name in one word — edges. Real objects have no perfectly sharp edges; the agent leaves every edge razor-sharp because nothing in the prompt told it that perfection is the tell.

Advanced

Repeatable workflows, quality gates, edge cases the agent fumbles.

Generating a controlled family of variants

ABC ~7 min

Ask for "five variations" and you get either five clones with a different colour or five unrelated objects — the agent has no concept of which features are the brand and which are the variable, so it randomises the wrong axis.

Master

The capability boundary: where you stop trusting the agent and take over.

Knowing when it is done — and handing off

ABC ~7 min

The agent will always tell you it is finished — "done" is its favourite word — so the one judgment it can never make for you is the only one that matters at this stage: is this model actually ready to become a game asset?

← All three courses