Hey all,
My company uses chatflows to help customers. When I go to the details of a specific chatflow it shows me sessions: started; completed; and abandoned; (this is the top banner) below that I can add and remove actions as needed to analyze the week by specific action question.
Now the problem I’m seeing is that for the week I have 41 sessions started in ‘greeting questions’, (the first set of questions that start a session) but my top banner says 27 sessions started, 3 completed, 24 abandoned. This does not make sense!!
My question is- if a user goes through the chatflow and gets to the point of looping back to the greeting questions, does this start a new session? That’s the only thing i can think of as to why my greeting questions started are at 41, and not matching with the 27 analyzed?!?
Thanks
I’ve just checked a few of my chatflows, and the overall ‘Started’ figure is the same as the ‘Started’ figure for the intro message.
Does your chatflow look back to the opening statement? If so, then I’m inclined to believe that this won’t count as a new conversation having been started, but will count as the action having been started.
Might be better to loop to a different introduction further on in the conversation, something like ‘Intro 2’, perhaps?
Thanks for your response Oliver,
Yeah that’s what I figured. It’s kind of wonky don’t you think? haha
It’s out of my hands what answers are available for certain questions and the flow in general. Just wish it was easier to analyze. It seems the bot is doing well based on the completion of actions. But when it says 24 abandoned out of 27 it makes you think it’s not. My guess is people are getting the answers they need and not completing a closing action. Is there a better way to get consumers to close the chat? It seems the biggest abandon is when the bot asks ‘do you have other questions’.
Personally, when I’m reporting on chatbot conversion rates, I look mostly at number of new contacts generated/data points captured. I’ll compare this with the overall number of conversations started to look at conversion rates.
It’s difficult to tell if we’ve generated any new contacts. The bot says fill out this contact form for help, but when a user gets to that point it has started the action of contact info and will complete based on their next action. So it will start and complete even if the user doesn’t fill out the contact form.
You could look at the Contact property ‘Record Source’ for this. If the chatbot has generated a new contact, this will show as ‘Conversations’.
Caveats: if you’re using multiple inboxes, this won’t show you which chatbot/inbox has generated the record (you can bypass this with custom reports using the Conversations object), and also won’t be the case if your chatflow is directing users to fill in a form, rather than leave their information with the bot itself. This also won’t show for if existing Contacts interact with the bot, regardless of if the chat has been completed.
Thank you Oliver, this is very helpful!
Hi @viens666
That mismatch you’re seeing is something a lot of teams have noticed, and in 2025 the reporting around chatflows still works this way: the “sessions started” metric in the banner is tied to unique conversations, while the per-action counts below can inflate if users loop back into the same branch.
It does not start a whole new session, but HubSpot still logs that action as “fired again,” which is why your greeting step shows 41 when the banner says 27. HubSpot explains the difference between conversations and actions here: (the definitions section is worth a look).
(Analyze your rule-based chatbot's performance)
Your guess is also right: many “abandoned” sessions are really just people getting what they needed and dropping before hitting the final closing action. A good 2025 trick is to add a micro-conversion step right before the “do you have other questions” block something like a feedback quick-reply or a subtle CTA (“Would you like a transcript by email?”).
That way, you turn more of those exits into measurable completions. You can also filter reports using the Conversations object to analyze by outcome, which avoids relying only on the abandoned/completed split
(Report on chat and email conversations )
So the short answer: no new session is created when they loop, the inflated action count is expected behavior, and for 2025 the best workaround is designing exit points that feel natural but also mark a “completed” state for reporting. Hope this clears the confusion.
