Analysing Intercom’s AI strategy

Simulating natural human conversation is a challenge. We’re definitely not at the stage where we have a system that’s intelligent and can hold the context of a conversation.

Creating a machine learning system that’s fit for users continues to be tough. Often you can build a very powerful machine learning system that will do 90% of a task well enough, but then you’re left with this remaining 10% that prevents it from entering the wild.

We had seen the magic of a couple of real end users having their questions successfully answered by a bot, and we knew time spent improving accuracy with real machine learning wouldn’t be wasted

Our technology interfaces are gradually becoming more conversational, and we’re just starting to see the quality of natural language understanding get good enough to unlock them.

We sketched out a few AI-powered features we thought could be useful, went into production, and put a beta version in front of 160 customers.

The ability of GPT-3.5 to edit and change text makes it very valuable for customer service, and it can already handle tasks such as summarizing text and adjusting tone.

we built a feature and did a couple of rounds of iteration with a summarization feature in the inbox. You could just press a button or use a keyboard shortcut to basically say, “Hey, I want a summary of this feature, put it on my composer so I can lightly add to it.” It’s not perfect. You might need to add a little bit to it, but it’s a huge time saver.

GPT may disrupt the customer service industry, but if automation increases the agent’s productivity, it can ultimately unlock capabilities that enhance their value to the business.

we have a wave of other features in prototype form that are not quite there yet – big-ticket value things – but we think we see a line of sight to that

The big goal, though, was creating a GPT-powered chatbot that could answer customer queries directly. To do this, it needed to be able to harness the power of large language models but without the drawbacks posed by “hallucinations”. Initially, we weren’t sure how long it would take to crack this problem, but now, with the release of GPT-4 by OpenAI, we can reveal that we’ve built a chatbot that can reliably answer customer questions to a high standard. We’ve called it Fin.

We’ve reduced hallucinations by about 10x, building constraints that limit Fin to queries relating to your business, based on a knowledge base you trust.

Yes, customer service teams will get smaller. This is inevitable, but it isn’t the doom and gloom people project. Many teams have high staff turnover, and constantly open roles, and this will reduce pressure. It will give managers more time to invest in growing their people.

The customer service job will get much more interesting, and rewarding. Reps will only deal with more complicated questions, or really important customers. The job will still be about human connection, empathy, but also deep problem solving. Reps will have more time to provide the excellent customer service they are striving for.

New types of jobs will emerge in the customer service team. The customer experience that blends AI and reps needs to be designed, to be orchestrated. And it needs to be analysed and improved.