Campaign Tech Awards: Winner, Most Effective Use of AI for a Campaign

A creative use of AI revealed the potential of the Messenger platform and got Stranger Things fans coming back for more.

Campaign Tech Awards: Winner, Most Effective Use of AI for a Campaign

‘Stranger Things: El Bot’ by Tangent

The people at Tangent were underwhelmed by their experiences of chatbots, which were often incoherent exchanges littered with "sorry I don’t understand"s. So they had a brainwave for a fun internal project – to use the nation’s excitement for Stranger Things to showcase the full potential of the Facebook Messenger platform.

Before they explored the technical potential of AI, they needed to get under the skin of Stranger Things fans to understand how their product could add real value and be something users would want to interact with again and again. Tangent also wanted to avoid the traps that had made their previous experiences with bots so lacklustre.

By combining demographic and psychographic data, Tangent profiled the show’s biggest fans, focusing on those discussing the programme on Twitter, to uncover their behaviours and preferences. Naturally TV came out on top, but there was also a love for gaming, comics, alternative music and the news.

This helped Tangent decide how some of Stranger Things’ themes could become key content pillars. El Bot (named after the character Eleven) encouraged users to explore the full breadth of features within Messenger via quick-responses and button prompts, without barring free-text input. Fans were rewarded for delving deeper, discovering embedded podcasts, Spotify playlists, video links and jokes.

The bot automatically customised the experience and even ascertained how far through the series viewers were, to avoid spoilers. By routing through a custom RunKit API, Tangent linked Chatfuel and Google’s Dialogflow to improve the bots’ natural language processing capabilities. This meant the bots could deliver relevant responses rather than error messages, providing a coherent, linear discussion.

The project started with an extremely modest media boost. Less than two months later, El Bot had handled more than 22.7k messages and achieved an 89% open rate for sent broadcasts. There was a 35% return to El Bot more than once, against an industry average retention rate of just 4%.

Topics