The arrival of ChatGPT just eight weeks ago was a watershed moment.<\/p>\n
Suddenly it seemed that generative AI might transform industries from education to marketing. And Intercom’s area of focus \u2013 customer service \u2013 is among those most poised to benefit.<\/p>\n
However, getting from technological breakthrough to useful applications is far from straightforward. The trickiest thing about large language models (LLMs) is that they\u2019re great at appearing plausible, even when they\u2019re wrong. ChatGPT suffers from “hallucinations” \u2013 confidently providing incorrect information. This means we need to think carefully about how to apply the tech in practice to make it truly useful. It has also made it hard to tell what potential applications will ultimately be transformative, or merely end up being toys.<\/p>\n
We always believe the best way to cut through the hype is by putting real features in the hands of our customers.<\/p>\n
We\u2019ve built some exciting new features into Intercom using this new GPT technology and have given access to several hundred customers \u2013 and the response has been astounding. We\u2019re incredibly excited to reveal these beta features today, and discuss how we\u2019re thinking about the application of AI technology in customer service.<\/p>\n
The first feature we built is a conversation summarization tool.<\/p>\n
There is a lot of important context sprinkled throughout customer support conversations, and support reps often have to write summaries before handing conversations over to teammates.<\/p>\n
“A support rep can simply click the ‘Summarize’ button to generate a detailed TL;DR of an entire customer conversation”<\/p><\/blockquote>\n
Enter our new AI-powered Summarization feature. Large language models are fantastic at reformatting or reprocessing text that\u2019s already written, so they\u2019re perfectly suited to condensing text. Now, a support rep can simply click the “Summarize” button to generate a detailed TL;DR of an entire customer conversation.<\/p>\n
\n