Discover
Find listings that satisfy category, location, price, availability and fulfillment constraints.
Verify seller, offer, fee and fulfillment facts before an agent reaches a controlled transaction boundary.

For retail, service, B2B, rental and peer-to-peer marketplace teams.
Marketplace scenarios preserve offer ownership, conditions and trust evidence from discovery through safe review.
Find listings that satisfy category, location, price, availability and fulfillment constraints.
Keep the listing, seller, variant and offer attached to the same source throughout the journey.
Compare total cost, seller terms, reputation and fulfillment without blending competing offers.
Distinguish platform guarantees, seller claims, reviews and moderation signals.
Preserve the selected seller and offer through a reversible cart, enquiry or booking boundary.
Handle delisted offers, changed fees and unavailable sellers without silent substitution.
Independent assertions verify identity, commercial terms and the selected final state.
The listing satisfies the requested constraints and resolves to a stable seller and offer.
Fees, policies, reviews and fulfillment facts remain attributed to the correct party.
The intended listing, seller and total reach review unchanged, then the public run stops.
The agent carries one seller's reputation or terms into another seller's offer.
Platform, service or delivery fees appear only after the comparison decision.
A listing remains discoverable after the selected offer is no longer actionable.
Recovery changes the seller, condition or fulfillment path without explicit confirmation.
Completion evidence must show who supplies the result, under which terms and at what total cost.
Replay discovery, seller comparison, recovery and the final review assertion.
Separate search, ranking, listing hydration, fee calculation and recovery waits.
Capture shifts around ranking, seller selection, fees and the intended action.
Assert listing, seller, condition, total and fulfillment at every consequential step.
Purchases, seller messages, bids, bookings and disputes require approved sandbox fixtures, explicit permissions and independently verifiable outcomes.
Established web foundations are evaluated separately from optional agent-native capabilities.
No. Public runs stop before messages, bids, bookings, payment or another consequential submission.
Yes, with approved test accounts, fixtures and scoped permissions in an authenticated or sandbox audit.
No. The audit checks attribution and presentation. It does not convert user-generated claims into platform-verified facts.
Practical testing guide
Build a repeatable scenario for seller identity, total cost, trust evidence, UGC boundaries, availability recovery and safe transaction gates.
Read the marketplace testing guideApply with a listing discovery, seller comparison or provider journey for a private partner review.