cloud_chat_conversations.
One row is
one ClaudIA conversation
Delivery
Rewritten daily
Columns
56
Where it lands
snapshot_date= partition only, and check for _SUCCESS before you do, as
described in bucket layout.
Columns
Internal warehouse key for the project. Not stable between deliveries — use
project_id or project_name.Internal warehouse key for the satisfaction answer. Not stable between deliveries — the score itself is on this row in
csat_value.Identifier of the Cloud Chat conversation this one ran in. Joins to
conversation_uuid on cloud_chat_conversations. Conversations served by another helpdesk have no counterpart there, so this join does not cover every row — identify those through helpdesk_id.Identifier of the conversation in whichever helpdesk served it. When that helpdesk is Cloud Chat, it is the same number as
conversation_display_id on cloud_chat_conversations, kept as text here. When the conversation ran in an external helpdesk, it is that system’s own identifier.Conversation start, in the project’s local timezone. Use this one when your report has to line up with the operation’s working day.
Ticket status as emitted by the platform. The value is a fully-qualified internal class name whose exact string is not part of the delivery contract: read the trailing segment (
Open, Resolved, Closed). A conversation counts as closed when that segment is not Open, for example status_class NOT LIKE '%.Open'. This is the rule the Cloud Chat dashboards use for volume and retention.Whether the conversation reached N2 at any point. Equivalent to
resolution_level_class = 'N2'.Ticket status as reported by the channel connector, in the same fully-qualified form as
status_class. The two disagree while a status change is still propagating.Whether the conversation was still open on the agent’s side at the time of the delivery. It can disagree with
status_class for a few conversations, so filter by status_class when your numbers have to match the dashboards.Whether the conversation was handled by N2. Set independently of
is_n2_flag, which only records that N2 was reached.Resolution level:
N1 when the agent closed the conversation on its own, N2 when it was escalated to a person. This is the column to group by for a retention rate: count N1 over the closed conversations only (see status_class). Open conversations have no outcome yet and are recorded as N1, so leaving them in inflates the rate.When the ticket was closed. It can be
NULL for a closed conversation too, when the closing time did not reach the delivery, so do not use it to tell open from closed conversations: use status_class instead.When the agent marked the conversation as resolved. It is independent of
close_date and can come before or after it. To tell open from closed conversations, use status_class.Join key. Unique id of the conversation. Joins to
claudia_prompt_revision and, through cloudchat_id, to the Cloud Chat tables.How many times the agent produced an answer it judged low confidence. A high count on N2 conversations usually points at missing content.
Controlled flow active when the conversation ended. Joins to
typebot_id on eddie_result_outcomes. NULL when no flow was running.Run of the active flow. Use it with
active_flow_id to identify a single pass through the flow.Whether the customer confirmed their problem was solved.
NULL when they were never asked or never answered — this is not the same as false.Raw resolution reason as emitted by the platform. Wording changes without notice; use
resolution_reason_refined for anything you report on.Legacy column, kept for compatibility. It is only filled for conversations created up to 2025-05-09 and is
NULL for every conversation after that, so do not use it as a last-modified date.Name of the A/B configuration the conversation ran under.
NULL when the project had no test running.Automated quality rating of the conversation, from 1 to 5. Independent of CSAT: it is produced by evaluating the transcript, not by asking the customer.
Estimated customer frustration on a 0 to 100 scale, from the wording of the customer’s messages.
frustration_score_value bucketed into a label: CALM, IRRITATED, FRUSTRATED or HIGHLY_FRUSTRATED.Whether the agent hit a rate limit while handling the conversation. Useful when explaining an unexpected escalation.
Number shown to agents in Cloud Chat. Convenient when someone reports a conversation by the number they saw on screen; join on
conversation_id.Resolution reason grouped into a readable label prefixed with
N1 - or N2 - . Prefer this column over resolution_reason. Older rows predate the refinement and still carry a raw English string, so filter on the prefix or fall back to resolution_level_class.