However, there\u2019s a perception that AI agents can only function over chat. Our research has shown that many customer service leaders continue to equate AI to chat experiences, rather than thinking about how it can deliver support across multiple channels, just as human agents can.<\/p>\n
Well, we\u2019re changing that perception with the latest updates to Fin AI Agent \u2013 customers can now get instant responses to their emails.<\/p>\n
![](\"https:\/\/www.intercom.com\/blog\/wp-content\/uploads\/2024\/10\/Fin2-Announcement-16-Email_b.jpg\")
<\/p>\n
Customers can now get AI answers to their emailed support questions<\/em><\/p>\n Getting Fin AI Agent to work over email presented some interesting technical and UX challenges \u2013 here, we dive into the process and share some of our learnings.<\/p>\n When a user contacts a business\u2019 customer support team via email, Fin AI Agent will automatically jump into the conversation to resolve the issue. Fin\u2019s answers use generative AI technology to create the answer based on a range of support content using the Retrieval-Augmented Generation (RAG) framework<\/a>.<\/p>\n Fin not only provides direct answers to queries, it\u2019s also more conversational, with the ability to ask clarifying questions if the user\u2019s initial message isn\u2019t clear enough to find the best response. For the most complex cases that Fin isn\u2019t able to answer, Fin will seamlessly hand over to a support agent.<\/p>\n When Intercom launched Fin AI Agent in March 2023, it was the first generative AI-powered customer service agent on the market. We tapped into learnings from our previous machine learning-based product, Resolution Bot<\/a>, to inform what a generative AI Agent could look like. Since then, we\u2019ve continued to improve and expand our offering by introducing completely new features or rolling out improvements to the underlying model, thereby increasing resolutions.<\/p>\n When it came to defining how we would build Fin over email, we didn\u2019t have a blueprint for what the solution should look like. Email as a channel is very different from chat, so we were unsure whether Fin over email should work in the same way. This is where our \u201cThink big, start small, learn fast\u201d<\/a> principle became relevant, and pushed us to apply first principles thinking.<\/p>\n We started with research to better understand why email automation was important for customers, what kind of requirements they had, and what impact we could anticipate if we built Fin over email. The insights were summarized into a doc called an “Intermission”, which we create at the start of all product initiatives, in keeping with our \u201cStart with the problem\u201d<\/a> principle.<\/p>\n We decided to start small with an alpha version as there were many assumptions to validate. The team proceeded to build the technical foundations and a very simple teammate experience \u2013 just enough to be able to set Fin live on email, but with no bells and whistles. Since we already had a lot of the building blocks in place \u2013 a solid email solution<\/a> and a very flexible automation system (Workflows<\/a>) \u2013 we were up and running quickly.<\/p>\n “This close partnership is at the heart of how we work in R&D \u2013 it allows us to move fast as we have tight feedback loops with the customers who will use and benefit from our product”<\/p><\/blockquote>\n We reached out to a handful of Fin AI Agent customers, who have a high number of monthly email conversations, to provide us with feedback on what we had built so far. This provided us with enough insight to define scope for our open beta release.<\/p>\n At Intercom, we are very fortunate to be able to partner with our customers as we make progress on our thinking. We work closely together to understand their needs and gather feedback on our initial solution. This close partnership is at the heart of how we work in R&D. It allows us to move fast as we have tight feedback loops with the customers who will use and benefit from our product.<\/p>\n The early feedback helped us shape our open beta. At this stage, we kicked off a more in-depth design phase, resulting in an artifact called an “Interconcept”. This phase of development is driven by the product designer and outlines a set of different approaches, each with a list of pros and cons.<\/p>\n When we were ready to start building, the lead product engineer created a project plan to outline what we needed to build and in what sequence, making it very easy to bring the rest of the team together. Once we launched Fin over email to open beta, we focused on monitoring usage and gathering as much feedback as possible, aiming to uncover any necessary improvements or new functionality required for general availability.<\/p>\n Despite the team working on Fin AI Agent for over a year, amassing deep usage insights and seeing a great deal of success, making Fin work over email came with its own challenges.<\/p>\n In 2022, prior to the generative AI explosion, Intercom launched the ability to run automations and chatbots over different channels, such as WhatsApp, SMS, and email. At the time, email already proved to be a more complex channel to automate.<\/p>\n From a technical perspective, some examples of challenges we faced when working with email automation were:<\/p>\n Besides the technical challenges, we also had to solve problems that impacted the end user experience.<\/p>\n For most end users, talking to an AI agent over email is a much less established habit than talking to one over live chat, which meant that we had to design an experience that took all the standard expectations around email into account, rather than trying to replicate a chat experience over email.<\/p>\n It was also important for us that the experience felt natural and intuitive so that end users felt comfortable with interacting with an AI agent over email.<\/p>\n We had to consider many differences between live chat and email when designing the new experience, such as:<\/p>\n Lastly, with the learnings gathered from both the technical and end user experience challenges, we partnered with Machine Learning scientists and engineers to create a new component in the AI agent\u2019s underlying architecture specifically for email. Different to our original AI agent over chat, this new agent was developed with the specificities of email in mind, such as:<\/p>\n As the expectation for a response over email isn\u2019t as instantaneous as chat, we were also able to perform some more complex LLM querying for better and more robust answers without significantly impacting the response times.<\/p>\n The impact for our customers has been immediate. For instance, Robb Clarke<\/a>, Head of Technical Operations at RB2B<\/a>, reported these astonishing results:<\/p>\n “RB2B 2x’d its user base in the last 58 days but my support team is fielding 45% LESS inquiries thanks to one major change, Fin AI Agent started handling email replies. This simple yet powerful change saved us from handling an additional 493 tickets. At 15 minutes per ticket, that’s about 123 hours saved. If you’re not using it yet, you’re missing out. The efficiency and time savings are game-changers \u2013 12 months from now, our team of 2 is going to be acting like a team of 20.”<\/p><\/blockquote>\n Within the first month of release, Fin processed over 1 million end user emails. Fin has provided an AI-generated answer to over 81% of the email conversations it has been involved in, automatically resolving more than 56% of them on average.<\/p>\n Fin over email is available now. Learn more<\/a> about how it can transform your customer support experience, or check out this instructional video, which shows you how to set it up to support your customers.How Fin for email works<\/h2>\n
Our development journey<\/h2>\n
Starting from first principles<\/h2>\n
Iterative development<\/h2>\n
Challenges and considerations<\/h2>\n
Technical challenges<\/h3>\n
\n
User experience considerations<\/h3>\n
\n
Adapting our underlying AI architecture<\/h2>\n
\n
Fin over email in action<\/h2>\n
\n