Before you start
- Plan: the Growth plan or above for CLI access. See Plans and limits.
-
Access: a CLI login with these scopes.
sitegpt loginwith no--scopeincludes them all.Add--scope conversations:delete --scope leads:deleteonly if the agent must delete tags, conversations, or leads.
Steps
1
Pick the chatbot
2
List the conversations that need attention
3
Read each conversation
The CLI calls the conversation ID Note the visitor’s goal, the last question, and the last answer. Note if a team member should take over. Note any answer with a
<thread-id>.NEGATIVE reaction, and any contact details the visitor gave.4
Tag the conversation
Create tags if they do not exist yet:Assign tags. The
--tag values replace all tags on the conversation, so include the tags it already has.5
Star, resolve, or mark as read
6
Escalate, or return to AI mode
To send a conversation to human support:To give it back to the AI:Both commands fail on a resolved conversation.
escalate also fails while a team member has taken over the conversation, unless it is already escalated.7
Update leads
8
Record content gaps
For each weak or wrong answer, record the conversation ID, the question, the answer, and the missing content. If the team approves an answer, add it as a custom response:This command needs the
knowledge:write scope. For larger gaps, use Keep a chatbot’s content up to date. See also Fix a wrong answer.Check that it works
Run the lists from step 2 again:--status open. Conversations that you marked as read no longer show with --read false.
Hand back to the human
Report:- The number of open, escalated, and unread conversations.
- New and starred leads.
- Topics that came up more than once.
- Conversations that need a team member.
- Suggested custom responses and new content.