Review Response Triage
Pricing
from $2.00 / 1,000 results
Review Response Triage
Turn customer reviews into one deterministic, evidence-backed response-priority queue.
Pricing
from $2.00 / 1,000 results
Rating
0.0
(0)
Developer
Agent Workflow Lab
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
3 days ago
Last modified
Categories
Share
Turn heterogeneous customer reviews into one deterministic, evidence-backed response-priority queue. The Actor normalizes common Google Maps, Amazon, App Store, and generic review fields, scores each usable review with fixed rating and risk-signal weights, and returns short verbatim evidence for human handling.
No external API key or LLM is required. The Actor never generates or sends replies. It makes no external model or third-party API calls.
Input
Use the Source Dataset READ-only resource picker, pass reviews inline, or run {} for a clearly labeled embedded sample. Input precedence is: presence of reviews (including []), then nonblank datasetId, then sample.
Output and pricing shape
Every run writes exactly one review_response_triage_report Dataset item and the same report to OUTPUT. One aggregate queue equals one Dataset result. Synthetic Dataset-item charging is automatic; the code contains no manual charging.
Priority scoring is deterministic: a rating weight plus fixed billing/refund, breakage/failure, unanswered-support, and safety/fraud signal weights, capped at 100. Queue order is score descending, dated reviews oldest first, then source order.
Limits and privacy
- At most 5,000 source records; up to 500 queue items.
- Review text is normalized with the tested Review Intelligence boundary rules and evidence is capped at 240 characters.
- Keyword matching can miss context, sarcasm, language variants, and synonyms.
- Source Dataset access is READ-only and never writes to or deletes the source.
- User data is written only to the run's default Dataset and
OUTPUT; Apify retention settings apply.
