customerFeedback_insights_report

writeAmazon Seller (SP-API)·sp.customerFeedback_2024-06-01

An async job: returns data.job_id at once; poll customerFeedback_insights_report_status every ~4 s until data.status is 'done' (the report is data.report) or 'error'; a report takes 1–3 minutes. A credits hold is taken at submit (price it with credits_quote) and settled by the worker; nothing is charged when the marketplace has no buyer-feedback data (US, UK, FR, IT, DE, ES, JP only) or the build fails; HTTP 402 with error_code insufficient_credits when the balance is short — top up at sellersheetai.com/billing. Amazon SP-API · getItemBrowseNode · GET /customerFeedback/2024-06-01/items/{asin}/browseNode Amazon SP-API · getBrowseNodeReviewTopics · GET /customerFeedback/2024-06-01/browseNodes/{browseNodeId}/reviews/topics Amazon SP-API · getBrowseNodeReturnTopics · GET /customerFeedback/2024-06-01/browseNodes/{browseNodeId}/returns/topics Amazon SP-API · getBrowseNodeReviewTrends · GET /customerFeedback/2024-06-01/browseNodes/{browseNodeId}/reviews/trends Amazon SP-API · getBrowseNodeReturnTrends · GET /customerFeedback/2024-06-01/browseNodes/{browseNodeId}/returns/trends Amazon SP-API · getItemReviewTopics · GET /customerFeedback/2024-06-01/items/{asin}/reviews/topics Amazon SP-API · getItemReviewTrends · GET /customerFeedback/2024-06-01/items/{asin}/reviews/trends Amazon SP-API · searchCatalogItems · GET /catalog/2022-04-01/items

Call itCopy Anchor Link

{
  "name": "customerFeedback_insights_report",
  "arguments": {
    "store": "myStore-US",
    "asin": "<asin>"
  }
}

curl -X POST https://api.sellersheetai.com/api/v1/tools/customerFeedback_insights_report \
  -H "Authorization: Bearer $SELLERSHEET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"store":"myStore-US","asin":"<asin>"}'

ArgumentsCopy Anchor Link

ResultCopy Anchor Link

Every tool answers {notification, data, human_action}; data carries:

• data.job_id — the job; data.status 'pending'; data.credits {charged, balance}.
• data.report — supported false means the marketplace is not covered and nothing was charged — reason choose_marketplace | no_matching_category | marketplace_unsupported, with candidates to pass as via or category. Otherwise credits {charged, balance}; category and category_chosen_by; report_version 3; tiles (the three headline
• data.report.findings — type, topic, number, unit, chips, so_what, question n); cluster (one sentence when several topics are one fact); verdicts[] (every complaint topic: kind fix | watch | pre_empt | fine, priority, you vs category vs the top-25 % sellers as gap and gap_leaders, trend, star, category return share, subtopics with quotes, so_what — what to do in the LISTING); strengths[], pre_empt[], category_complaints[], category_praise[], returns[], star_lifters[] (the evidence tables); questions[] (one per FACT: n, group, question, why, buyers_say, example — a complete sample answer with {number} and {detail} slots — line with {answer}, listing_use, coverage from_listing | from_draft | partial (+missing) | contested (+disputed_by) | needs_you, answer, source {field, quote}); skipped[] (return reasons the product cannot have); keywords[] (buyer-language phrases). Read the tiles and so-whats, then answer the questions — a sample answer is a starting point, never a fact until confirmed.

asin*: string
marketplaceId*: string

browseNodeId*: string
marketplaceId*: string
sortBy*: MENTIONS | STAR_RATING_IMPACT

browseNodeId*: string
marketplaceId*: string

browseNodeId*: string
marketplaceId*: string

browseNodeId*: string
marketplaceId*: string

asin*: string
marketplaceId*: string
… (18 more lines; the Docs link above)