Why Speed Alone Isn’t Enough?
Intercom’s breakthrough AI chatbot, built on GPT-4
Recently active
Hi everyone!If you are using FIN as the chatbot, I’m curious about what is the current CSAT score of your FIN profile. Ours is currently ~50%, and we are not really sure if it’s a good one. Thanks!
1- I want away to add context to fin, more of general guidance of how to best reply; stuff like:Your answer has to be no longer than x lines. Avoid using the following terms. Avoid adding resources to the end of the msg.2- Also, my fin is taking to long to answer, how can I fix it?
Just out of curiosity, what is everyone’s resolution rate with Fin?We are just now implementing Fin AI for our bots and are trying to set realistic goals and expectations. Our manually created bots today deflect about 40-45% of chats without Fin, so hoping we can reach at least 60% deflection with Fin.
I have a CSV list of 5000+ frequently asked sales tax questions and their corresponding answers. I would like intercom to ingest these questions surface the answer to customers. I would also like to be able to update these questions quickly over time as the answer changes. What is the easiest to ingest these into intercom? Should I use something like Confluence instead of CSV? Any advice?
I’ve been testing Fin and I haven’t been satisfied with the responses just yet to turn it on for all users. I understand it’s based on our articles and related knowledge base, but I’ve found Fin to provide wrong or sometimes unhelpful information. Here are some examples:It frequently tells users to contact support to fix the issue (Isn’t this what people think they’re doing?) It get company branding incorrect. For example I work for a company called “G.J. Gardner” and Fin often defaults to “GJ Gardner”, missing the periods in the name. Users often don’t provide enough info such as the record name in the software they want us to troubleshoot (i.e. a customer name or project number). How can I train Fin to inquire about this information? Fin defaults to US English. While this isn’t always bad, we have some industry specific terms that differ between contries (i.e “variation” in Australia and “change order” in the United States). How can I train Fin to use the correct terminology when re
When creating public articles, you have four components that can help get them discovered:Title Description Body CollectionAI Agent will ingest this content and attempt to provide a best-fit answer based on its knowledge.However, if you want multiple queries to lead to the same article, it seems there isn’t a direct way to accomplish it other than including wording throughout the title, description, and body such that alternative queries may pick up on that language. ExampleSuppose we have an article:Title: How do I add a payment method? Description: Learn how to associate a card with your account.That’s straightforward enough and satisfies a couple ways that queries might go (“add a payment method,” “associate a card with your account”).But, what if I want these other queries to lead to the same article:How can I pay? Where do I go to make sure you can charge me? I received a notice for non-payment. What do I need to do? I’m seeing an error for collecting an invoice balance. How do I
Hello, The feature “Let Fin introduce itself” is only available in the Fin over Chat settings but it isn’t available in the FinAI configuration for workflow. It would be better to have this feature (even if it’s disabled by default) so that visitors/users know that they can ask a question.
Hi there,We’ve implemented Fin AI (Chat and Email) on our support desk, and it’s been fantastic so far—it’s doing a great job handling first-line queries! 😊However, we’ve noticed a challenge when a customer submits a vague message. Fin will respond with technically correct information, but it’s often not relevant to what the customer truly needs.I’m wondering if it’s possible to improve this by getting Fin to ask clarifying questions before responding. I’ve been advised to set up a new workflow where specific vague questions prompt Fin to ask follow-ups, but trying to predict and account for all the potential vague queries customers might come up with feels inefficient.Is there a better way to manage this? Any advice or insights you could share would be hugely appreciated!Thanks so much
Hello, I tried to use react-use-intercom in my nextjs project, everything works fine on desktop, safari but the chat hides on other browsers when using mobile devices. Please help me fix the issue. Thanks!
Hi! I was wondering if anyone has insight into what a good resolution rate for Fin would be? I know the marketing site for Fin says “Resolve 50% of your support questions instantly” - but is 50% the average that we should resolution rate that we should be seeing? We only just started our trial but are preparing support goals for the quarter and I’m not finding any information about this in the Help Center. I would love to hear Intercom’s thoughts on what they see across their own Fin averages or an average across all companies who use Fin, but it would also be helpful to hear from anyone who may have insight into this for their own company. Thank you!
Is there a way to train FIN for more scenario based questions. Our customers have different use cases for our product and it would be very helpful if we can train fin to help answer scenario based questions.
Idea created:
We’re testing out Fin, and for one of our chat conversations, Fin didn’t provide an answer immediately. The customer sent another message an hour later, and then Fin replied. Fin greeted the customer in the widget just fine prior to the initial customer message.Any ideas on what would cause a delay? Could it be customer environment? Or an occasional glitch in Fin?
Our confirmed resolution rate is between 6-7% usually and our assumed resolution rate is near 60%. Looking at the conversations, I would estimate that 1/3rd at least of the assumed resolutions represent a correct answer and our clients are just not clicking the “Yes that helped” button that would mark it as a confirmed resolution. My experience with bots is similar, I rarely give bots feedback, because I know its not human. Any tips or methods that you have tried that increase clients use of the confirmed resolution?
Objective: Set up Fin AI to transition the conversation to a human agent, but only after the user completes a payment through Stripe.I've created a custom action for Stripe that connects to Fin, initiating a Stripe payment intent. The payment link is successfully generated and appears in the logs, but Fin doesn’t display the link to the user in the chat.Question: How can I configure Fin to send this Stripe payment link directly to the user within the chat? Then, check if the payment status is successful and if it is only then transition user to help desk agent?
Hi everyone! We are wanting to integrate intercom with our own software, where information and answers using FIN and our help articles are feed into our product using AI. We report data to our customers and want a way to pair the data presented with information from our help center (when relevant). Perhaps ambitious.. But wondering if anyone has created more indepth integrations with their software in the back end? Thanks in advance for your help!
I noticed when I manage snippets I no longer see a count of how many times the snippet was used in a FIN answer. Is that stat appearing somewhere else now or was it removed for some specific reason? The use count for snippets was super helpful to show effectiveness and also to help justify cost for FIN. Thanks!
How I can get FIN to include information in its knowledge sources based on articles with Target Audience rules turned on?The scenario is that we have some articles in our HelpCenter that we want to restrict to certain groups of users. However when check the FIN knowledge base, none of the articles that I have Target Audience rules on appear here. Is there a way to add them to the knowledge base?
