Skip to main content
Your agents’ quality reviews of the ClaudIA agent’s work: whether the customer’s problem was solved, whether the conversation should have been escalated, and whether the tag was right. A conversation nobody reviewed has no row here.

One row is

one review

Delivery

Rewritten daily

Columns

19

Where it lands

The partition delivered today holds the whole table. Read the latest snapshot_date= partition only, and check for _SUCCESS before you do, as described in bucket layout.

Columns

bigint
Internal warehouse key. Not stable between deliveries — join on conversation_feedback_id instead.
varchar(510)
Join key. Unique id of the review.
varchar(510)
Join key. Conversation being reviewed. Matches cloudchat_id on claudia_conversation.
varchar(510)
Project the reviewed conversation belongs to.
boolean
Whether the reviewer judged the customer’s problem solved.
varchar(65535)
The reviewer’s written comment.
integer
How serious the reviewer considered the problem, from 1 to 3, where 3 is the most severe.
boolean
Whether the reviewer judged the conversation closed correctly.
boolean
Whether the reviewer thought the conversation should have been escalated but was not. Rows with true are the missed-escalation cases.
boolean
Whether the reviewer thought the agent could have resolved it without escalating. The mirror of conversation_should_scaled_to_n2_flag.
varchar(510)
Who left the review.
timestamp
When the review was left.
timestamp
When the review was last edited.
boolean
Whether the reviewer agreed with the tag assigned to the conversation.
varchar(510)
The tag the reviewer says should have been used. Populated when is_tag_correct_flag is false.
varchar(256)
Id of the tenant. NULL for rows with no tenant mapping.
varchar(256)
Name of the tenant. NULL for rows with no tenant mapping.
timestamp
When the datamart last wrote this row. Use it to spot reviews added or edited since your previous load.
date
Partition column. Date of the delivery that wrote this file, in YYYY-MM-DD.