Often not quite — sold items still shown as live, prices out of date, links that land on a search page instead of the listing, and attribution lost on the way.
05Prioritised fixes, each stamped with model and date
03 / What you getsample structure
03 / What you get
Every listing an assistant recommends is checked with a live request under a declared user agent, at a low rate: is it still live, does the price match, does the link open the listing itself, and is the click attributed to the assistant.
Listing quality across recommended listingsIllustrative · your report shows your values
Check
Passed
Typical failure
Listing still live
71%
sold or expired item shown as available
Price matches
83%
price from an older crawl
Deep link to the listing
64%
link lands on a search results page
Attribution kept
58%
tracking parameters stripped
04 / Limits
What this does not claim
We check what assistants show; we cannot see why their index is stale.
Live checks use a declared user agent at a low rate and respect your robots rules.
Results are a sample per market and period, not a full crawl of your catalogue.
05 / Next
Request this instrument
We reply with a scope, a fixed price and a start date.
---
title: Do assistants show my listings correctly?
canonical: https://chosenbyagent.com/questions/are-my-listings-shown-right
updated: 2026-10-22
audience: marketplaces
offers:
- A2
evidence:
- price-stock-failures
- api-consumer-overlap
- answer-instability
---
# Do assistants show my listings correctly?
Short answer: Often not quite — sold items still shown as live, prices out of date, links that land on a search page instead of the listing, and attribution lost on the way.
## What the research shows
- **41%** — The most common points of failure for agents are inconsistent prices and promotions (41%) and unsynced stock (40%). [Agile Brand Guide (Salesforce research), 2026, vendor](https://agilebrandguide.com/agentic-search-becomes-the-new-front-door-to-commerce-salesforce-research-finds/)
- **15–32%** — Brands named in API answers overlap with what consumer assistant apps show on only 15–32% of brands. [Surfer, 2026, vendor](https://surferseo.com/blog/llm-scraped-ai-answers-vs-api-results)
- **64%** — About 64% of the top-5 brands changed between adjacent runs of the same assistant question. [MentionBird, 2026, vendor](https://www.mentionbird.ai/blog/chatgpt-vs-gemini-answer-stability)
## Routing & listing audit
A2 · from €2,500 (one-off) · indicative · scoped per engagement
Where assistants send your buyers, how they show your listings, and what to fix first.
- Routing share against named competitors, with the reasons assistants give
- Listing quality: live or sold, price match, deep link, attribution
- Agent access: WAF blocks, JS-only content, missing schema
- Manual calibration in the consumer apps
- Prioritised fixes, each stamped with model and date
## What you get
Every listing an assistant recommends is checked with a live request under a declared user agent, at a low rate: is it still live, does the price match, does the link open the listing itself, and is the click attributed to the assistant.
**Listing quality across recommended listings**
| Check | Passed | Typical failure |
| ------------------------ | ------ | --------------------------------------- |
| Listing still live | 71% | sold or expired item shown as available |
| Price matches | 83% | price from an older crawl |
| Deep link to the listing | 64% | link lands on a search results page |
| Attribution kept | 58% | tracking parameters stripped |
_Illustrative values — your report shows yours._
## What this does not claim
- We check what assistants show; we cannot see why their index is stale.
- Live checks use a declared user agent at a low rate and respect your robots rules.
- Results are a sample per market and period, not a full crawl of your catalogue.
## Request this instrument
We reply with a scope, a fixed price and a start date.
Agents: POST /api/engagements (application/json) with {"offer_id": "A2", "on_behalf_of": {"email": "…"}, "agent": {"name": "…"}}. The person confirms by email before we see the request. Details: /agents.md
### Related questions
- [Where do AI assistants send my buyers?](/questions/where-do-assistants-send-buyers.md)
- [Does my ChatGPT app or MCP work as intended?](/questions/does-my-ai-app-work.md)
- [Do buyer and seller agents behave safely on my platform?](/questions/are-agents-safe-in-my-chats.md)