One row is
one model call
Delivery
Daily delta on
etl_updated_atColumns
33
Where it lands
etl_date= partition to reconstruct the table. One of them is
etl_date=__initial__, the first load, holding everything that preceded the
earliest daily partition. Check for _SUCCESS before reading a partition, as
described in bucket layout.
Columns
Join key. Conversation the decision belongs to. Matches
cloudchat_id on claudia_conversation.What the agent decided to do:
NO_ACTION to keep talking, FORWARD_N2 to escalate, RESOLVE_TICKET or CLOSE_TICKET to end the conversation.Which response strategy the agent chose. The value is a fully-qualified internal class name and its exact string is not part of the delivery contract: read the trailing segment, for example
AcceptableConfidenceResponse or NoValidContentResponse.The answer the agent produced, before any formatting applied on the way out to the channel.
Result of the flow run. Joins to
result_id on eddie_result_outcomes.The content section the answer was built from. Joins to
content_id on claudia_contents. This is the column that lets you attribute an answer to a piece of your base.First of the candidate sections retrieved for this question, in relevance order. The candidates are what was available to answer with, not necessarily what was used.
Error recorded while producing the answer.
NULL on decisions that succeeded, which is the vast majority.First candidate section considered when the agent asked a clarifying question instead of answering.
When the datamart last wrote this row. This is the cursor for the daily delta: a partition holds the rows whose
etl_updated_at fell on that day.