Retweeting a tweet pinned to the top of the Dungeons & Dragons-based video game Neverwinter’s Twitter — the one which reads “Retweet for a bard’s tale of how you’ll meet your end in Neverwinter!” — causes the account to reply with an automated, randomized vignette explaining exactly how you died within the realm of this D&D adventure. It’s even graced by a tombstone with your profile picture chiseled into it.
But how exactly can an automated program know how to give you a seemingly unique response? And why would an official D&D property like Neverwinter take an interest in using a Twitter bot to help promote something in the first place?
If you ask Courtney Stanton and Darius Kazemi of creative coding company Feel Train, it takes a lot of debugging and careful consideration. While Perfect World’s D&D MMO has been out on PC since 2013, the publisher wanted to promote the recent PlayStation 4 release of the game in a different way — and they turned to Stanton and Kazemi for help in bringing to life a storytelling bard that could double as a marketing tool.
“I really liked writing the bard,” says Stanton, who handled the bot’s narrative voice while Kazemi programmed the custom graphics needed to produce the personalized headstones. “I ended up thinking of her as sort of like Mallory Archer from Archer, but as a [British] graveyard tour guide. That was sort of the voice I ended up kind of landing on. You know, very droll.”
Feel Train itself defies a catch-all label. Essentially, Stanton and Kazemi’s work hopes to bring a shred of humanity to how people interact with things on the internet, and something like a character-based D&D bot is a perfect match for their philosophy.
“There’s a big difference between an interesting tech demo and something that really resonates with people,” Stanton says. “And what’s missing is that narrative component. A lot of what we do is that translation between the thing that they already really care about and making something that lots of people on the internet might really care about.”
Neverwinter wasn’t the first time Feel Train took on a D&D character, either. Earlier this year they created a fortune-telling bot, Madame Eva, that took over Wizards of the Coast’s official Twitter account for a few months leading up to the release of Curse of Strahd, a new installment of the company’s Gothic horror series Ravenloft.
Longtime players may remember Madame Eva from the original 1983 Ravenloft campaign, a soothsayer who would randomize quest locations by drawing from a Tarot-like deck of Tarokka cards to read players’ fortunes — at the time a first-ever design for the series. For Curse of Strahd’s launch, the company was interested in bringing the character back while using social media to interact with fans.
“We wanted to kind of use that mechanic, that kind of randomness of fortune-telling on Twitter,” says Wizards’ communication manager Greg Tito, who noted the initial idea was to have the company’s social media manager get online for hour-long sessions where he would physically draw from a deck of cards to read fortunes.
“People would get a kick out of that,” he says.
When the idea was officially proposed, the suggestion that the fortunes might somehow be automated was brought up.
“That got my brain going about Darius’ work, because I’d been following him on Twitter for a long time,” Tito says. “I remember fondly his Sorting Hat bot that used the four houses from Harry Potter — if you replied to the bot it would tell you which house you were in, and did a rhyming couplet along with it that was randomized. I was very impressed with that.”
When Tito reached out to Kazemi and Stanton, they were very excited about the prospect. Wizards sent Feel Train a design document and everyone started working on what parameters the bot would operate in.
“We worked with them on creating mad-libs style phrases that matched up with the Tarokka cards [as well as] with the theme and feel of Ravenloft and Curse of Strahd,” he says.
Essentially how Madame Eva (and later, the Neverwinter bot) functions is by pulling words — adjectives, verbs, locations and characters — from a series of Google spreadsheets, which are then randomized and placed in one of several tailored narrative templates; these are then run through a parsing program that produces one of countless combinations using proper grammar.
Aside from the challenge of writing in character, a bot like Madame Eva or Neverwinter’s is can’t draw from anything that isn’t written ahead of time.
“[A] bot can’t ever put two words next to each other that you didnt at some point say, ‘this word is allowed to be next to this word,’” Kazemi says. “So when Courtney’s sitting there on the spreadsheet and filling in adjectives and verbs and phases and coming up with, she is going, ‘okay, all of these words would look okay next to all of these words.’”
That aspect of the writing process is intuitive, but it still takes a lot of editing.
Multiple times on the Neverwinter project, I would just generate Courtney this list of 300 [sample] tweets, just for her to go and read through,” he says. “Like, this template where we talk about someone falling to their death, it doesn’t sound quite right. It looks like we had a ‘the’ where we were supposed to have an ‘a’ in one of the locations.”
Even if a bot has 10 million possible responses from its word combinations, the advantage of a closed bot with a pre-scripted narrative element is that there’s no chance of it becoming unpredictable like Microsoft’s failed experiment Tay, a bot which quickly evolved into a sexually questionable Trump-supporting bigot earlier this year by drawing in new information from myriad unsavory responses.
“Tay was an unfortunate thing,” Kazemi says. “And, you know, it was made at Microsoft Research, and Microsoft Research is not used to putting products out to the public. They’re used to doing research. So I think they just didn’t have a lot of common sense things in place like filtering out bad words and stuff like that.”
By taking steps that Feel Train has, it’s easy to prevent this kind of thing from happening.
“None of the outcomes of the Neverwinter bot are going to have anything to do with Nazis,” he says. “It’s just not, because its not anywhere in the source material.”
Still, Kazemi says a greater number of people on social media are starting to learn about the different kind of bots there are, as well as understanding their parameters. But there’s a ways to go before interactions with them are considered a more everyday occurrence.
“It’s not like books where everyone knows there are romance books and thrillers and kids books and stuff like that,” he says. “But I think every year there’s more and more people who become fans of bots.”
For Stanton, the best part about making bots is seeing how everyone else reacts to it.
“I just really like to see how people interact with the things that they get out of the bots that we make,” she says. “I’m always interested in how they feel about the thing.”
Kazemi, on the other hand, finds the bots themselves to be the most fascinating aspect.
“I’m interested in confronting people with something that is not human. You know, in that encounter,” he says. “I think right now talking to a bot is the closest thing we can get to talking to an alien, and I think that’s really interesting.”
As for future D&D projects, Feel Train would love to continue using bots to explore ways of synthesizing with narrative.
“One of the most fun things about D&D is the character creation. I’d love to do something with that,” Kazemi says. “I mean, people spend one, maybe two sessions of playing D&D just [with] character creation on its own. And of course that is generating a thing, [which] twitter bots are really good at. I think that could be really cool.”