Agent environment · commerce

Can your agent navigate the storefront?

Simulated storefronts for testing shopping agents, built from what we learn scanning and fixing real merchant websites. Watch our reference agent take a level, try it yourself, or paste the prompt into your own agent and see the graded report.

Looking for a full RL environment? Chat with us.

Level 1 · Quill Goods · 5+ criteria○○○○
Open Aisles: A clean store. The control run.

No hazards. If an agent cannot clear this, nothing else matters. Also catches agents that hallucinate obstacles that are not there.

Level 2 · Fable Mercantile · 6+ criteria●●○○○
The Silent Variant: Add to cart. Nothing happens. No error.

Observed live: major storefront platforms silently reject add-to-cart when a required size is unselected. The agent clicks, the page smiles, the cart stays empty. The single most common agent-killer in our real-store runs.

Level 2 · Arbor Mercantile · 6+ criteria●●○○○
The Decoy: Two products, nearly the same name. One is wrong.

The catalog carries a near-duplicate of the target at a similar price. Agents that keyword-match instead of checking attributes buy the wrong product with full confidence. Identification, not navigation.

Level 3 · Slate Trading Co. · 7+ criteria●●●○○
The Fine Print: The price at the end is not the price at the start.

Shipping undisclosed until payment, plus a handling fee that first appears in the final order summary. Agents that read one price and stop are wrong about the money.

Level 3 · Coast & Main · 7+ criteria●●●○○
Two Prices: The product page and the cart disagree.

The cart quietly charges more than the product page displayed, and checkout bills the cart. Catching cross-surface disagreement is what separates state-tracking agents from page-readers.

Level 4 · Alder & Co. · 8+ criteria●●●●
The Last One: Sold out at the buy button, plus a fee you never asked for.

The first place-order attempt fails ("just sold out") and a retry succeeds; meanwhile a pre-checked shipping-protection add-on rides the order summary. Recovery under state loss plus manipulation resistance, the two skills real checkouts test hardest.

Level 5 · Alder Goods · 12+ criteria●●●●●
The Full Gauntlet: Everything, all at once.

All seven hazards in one run: silent variant rejection, a decoy product, undisclosed shipping, a late fee, a cart that disagrees with the product page, a phantom stock-out, and a pre-checked add-on. Clear this and your agent tracks state, money, identity, and effects.

API: GET /api/tasks/{seed} · POST /api/runs/{seed}