top of page

Yahoo! Monkey Pet Chatbot

IMG_7014.JPEG
IMG_7013.JPG

Yahoo! decided to create their own chatbots using open source AIML. Task was deciding on what kinds of bots would appeal and be most beneficial to Yahoo!'s userbase. 

Design Strategy

  • The Monkey Pet bot referred to itself as "me" instead of using "I" for first pronoun, as it was designed to be like a baby that the user could take care of, using emojis. 

  • Since Monkey Pet was more like a game for a younger audience, it was important that the voice felt fun and exciting. Adding emojis provided a fun and engaging experience. Inspired by the tamagotchi toy from 90s, users could send food emojis to the pet to feed it. Different foods, or even too much of one food could make it healthy or sick. 

  • In onboarding a new user, we wanted to mimic the language used in role playing games. Rather than having "yes" for one of the answers when prompted to adopt a pet, "I'm ready" was more appropriate. "Yes" was too formal.

My Role

Planning and Scope Definition
A lot of thought went into what kinds of bots Yahoo! should first launch. One of the first, being a Search bot, to leverage all the NLP work that was already present. In the end we decided to narrow our focus on the products that had the most engagement: Finance, News, Sports, Weather, with one "fun" bot. 

 

Content Strategy, Conversation Design

Developed and implemented guidelines defining the way the bots should speak for each audience.

 

Design Execution Executed journey maps, user flows, wireframes and design specs.

Oversight and Collaboration
After launching all bots, continued to monitor performance and iterate the copy based on feedback and data.

01 |  USER RESEARCH

purplepeople.png

What do users need?

People use the Yahoo! home page for many things, but not everything all at once. 

Pains

  • Navigating the home page can be confusing or overwhelming
     

  • Too many products offered—how can another product, a chatbot, simplify Yahoo!'s user experience and still provide value?

02 | COMPETITIVE ANALYSIS

What's out there?

Popular chatbots at the time, such as Sephora's shopping assistant or Hipmunk's virtual travel agent, were built for e-commerce or customer support. This didn't exactly align with the host and range of services Yahoo! had to offer, however.

In Hipmunk's bot, there's a chunk of 4 utterances from the bot. In smaller phones this would cause the user to scroll just to understand what's being said. It would have been nice to see more turn taking. 

Sephora's bot offers images of products, which is great for clarity. This is a great way to confirm that the product is what the user wants. 

sephora.png
hipmunk_edited.png
Yahoo! Bots

03 |  VALUE PROPOSITION

What could be better?

Finance, News and Sports are Yahoo!'s most successful products. We decided that starting with these made the most sense, and would keep things simple. Then we added Weather and a Tamagotchi-style pet called MonkeyPet for fun. 

These bots were launched in Facebook messenger and Kik.

Note: After Verizon Media bought Yahoo!, there was a change in priorities and the project was deprecated. 

04 |  CHALLENGE

How to manage multiple bots?

Our greatest challenge was building a consistent brand voice across a range of topics and user intents.

We knew that Finance Bot’s users would be different from MonkeyPet’s users, so it was imperative to identify and differentiate the voice and tone of each bot as well. For example, the Finance Bot should read as professional with short and complete sentences, while MonkeyPet should exude fun and excitement through lots of exclamation points and emojis.

And how do we do this?

Process

  1. Create bot personas:
    -Use data to Identify Yahoo! users into segments, which we'd later map to each bot
    -Write a golden set of include/exclude keywords specific to each bot

  2. Create bot playbook: 
    -Come up with a list of use cases for each bot

    -Define "success" and "areas of improvement" in bot-user interactions.

  3. Edit AIML

  4. Monitor user engagement 
    -After launching the bots, we'd analyze conversation length, user sentiment, retention rate, etc
    -Gather user feedback through survey prompts offered at the end of the conversation

  5. Iterate, iterate iterate!

MonkeyPet

Conversation Design

ONBOARDING

Finance: 

News: 

Bot should introduce itself as a bot. The user may feel distrust if they first thought they were talking to a human, and later find out it's a bot

This is the Yahoo Finance bot! Type a company name or ticker to get started.

CTA, moves conversation forward.

Hi! I'm the Yahoo News bot. I can find stories for you, tell you about what's trending, and provide top news twice a day. 

List 2-3 options, to minimize cognitive load

MonkeyPet: 

Food emojis fuel me up to travel to exotic places 🗽🏰🏯, send you pics 📷, and give you fun surprises 😄 Me  tum tum ready for treats now!

Use of emojis, lack of proper punctuation give this conversation a more casual lighthearted feel, in contrast to News and Finance.

CONVERSATION REPAIR | Error Handling

At some point, users will come across the bot's limitations. When that happens, it is important to apologize and provide the user with a path forward, whether that be a call to action or a reminder of the bot's function and abilities.

Weather: 

I'm sorry, I can’t see that far into the future. Type Help, to learn more about what I can do.

MonkeyPet: 

Me no support that yet! 😞 and me hungry

For MonkeyPet, the sorry is expressed with the emoji, thereby staying true to its voice.

Marlinda Galapon

 © 2022 by Marlinda Galapon

  • Grey LinkedIn Icon
  • Twitter
  • Grey Instagram Icon
  • Grey Facebook Icon
  • Grey Pinterest Icon
bottom of page