One row is
one flow run
Delivery
Rewritten daily
Columns
41
Where it lands
snapshot_date= partition only, and check for _SUCCESS before you do, as
described in bucket layout.
Columns
varchar(64)
Join key. Unique id of the flow run. Matches
response_bot_result_id on claudia_prompt_revision.varchar(75)
Project the flow belongs to.
varchar(255)
Id of the project. Prefer it over
project_name, which can be renamed.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.varchar(64)
Id of the flow that ran. Matches
active_flow_id on claudia_conversation.varchar(256)
Name of the flow, as set by whoever built it.
varchar(50)
Instance the flow ran on.
timestamp
When the run started.
date
Date of the run. Convenient for grouping without casting
result_created_at.boolean
Whether the customer actually entered the flow.
false means it was triggered but never began.boolean
Whether the customer reached the end of the flow.
boolean
Whether the customer started the flow and stopped partway. Pair it with
last_group_title to find the step people give up on.varchar(256)
Id of the last step the customer reached.
varchar(512)
Title of the last step reached. This is the column to group by when looking for where a flow loses people.
varchar(14)
How the last step was determined:
entry from the step the customer entered, subflow from a nested flow, sem_edge when the step had no outgoing path, nao_encontrado when it could not be resolved.varchar(510)
Conversation the run belongs to. See
key_source for which identifier this holds before joining on it.varchar(9)
Which identifier
conversation_key holds: helpdesk for the external helpdesk id, session for the flow session, result_id when neither was available. Check this column before you join.boolean
Whether a satisfaction survey was sent on the conversation.
boolean
Whether the customer answered it.
integer
The score they gave, from 1 to 5.
NULL when unanswered.double precision
Minutes to the first response, in wall-clock time.
double precision
Minutes to the first response, counting only the operation’s working hours. Use this one when comparing against an SLA.
double precision
Minutes from start to resolution, in wall-clock time.
double precision
Minutes from start to resolution, within working hours.
double precision
Minutes the conversation was actively being handled.
double precision
Minutes actively being handled, within working hours.
boolean
Whether the conversation was handed to a person.
boolean
Whether the conversation reached N2.
varchar(2)
N1 or N2, matching the conversation’s resolution level.varchar(510)
Resolution reason of the conversation, in the same refined form as on
claudia_conversation.boolean
Whether the customer came back with the same subject after this run. A flow with a high completion rate and a high recontact rate is answering the wrong question.
varchar(5)
Who handled the conversation:
AI or HUMAN.boolean
Whether an AI agent handled it. The boolean form of
agent_type.smallint
Frustration estimated for the conversation, from 0 to 100.
varchar(50)
frustration_score_value bucketed into a label: CALM, IRRITATED, FRUSTRATED or HIGHLY_FRUSTRATED.bigint
Errors recorded during the run.
boolean
Whether the run hit at least one error.
error_count > 0.varchar(14)
How the run ended, in one column:
completou finished, abandono was abandoned partway, escalou_n2 escalated, n1_com_decisao ended at N1 with a decision taken, nao_iniciou never started, em_aberto was still running, sem_conversa had no conversation attached. Labels are in Portuguese in the data.varchar(36)
Identifier of the workspace the run belongs to.
date
Partition column. Date of the delivery that wrote this file, in
YYYY-MM-DD.