After you’ve started designing a chatbot with Botsociety, there are a few ways for you to share your chatbot mockup with your team and receive feedback. One of these is the Export feature, which allows you to easily create an Excel, MP4, GIF, or AVI file of your conversation for use in meetings, presentations and more. Here’s how!
Select your export format
Once you’re ready to share your design, hover over and click on “Export.” From there, you’ll have the option between “Export Video” and exporting for “Export Excel.”
Exporting to Excel
To export to Excel, simply click on the Excel option and your conversation flow will automatically download.
Then, you’ll be able to open and view that conversation in Excel!
Exporting to video
To export to video, click on the video option. Then, you’ll be able to customize your export to suit your exact needs.
Protip: make sure to click on “Advanced” for more preview options.
After that, click on the “With frame” or “Without frame” options and a ZIP file containing MP4, GIF and AVI files will be emailed to you. From there, you’ll be able to view your design and share it with your team.
And that’s it! By using Botsociety, you can easily share your chatbot mockup with your team for easy and effortless collaboration. Want to give it a try? You can start for free today at Botsociety.io
Let’s say you’ve just finished designing an awesome chatbot for Facebook Messenger. But what if you wanted to see how this chatbot design would look on Slack, or on your own website? With a bot prototype tool like Botsociety, you can use the Conversion feature to easily convert and prototype your bot design into any other platform. Here’s how!
Select your prototyping platform
To convert your chatbot design to another platform, hover over to “File” and then select “Convert to another platform” from the drop-down list.
After that, select which of platform you want to convert your bot design to and then click “Next.” For this tutorial, we selected the “Generic Template” platform.
Preview your conversion
Following that, make sure that your bot and your user messages are being attributed correctly and then click “Next.”
From there, you can preview your conversation in the platform you’ve selected and then click “Convert.”
With the conversion complete, you can continue to edit and prototype your design in the new platform as you normally would.
And that’s it! If you want to start building bots for multiple platforms, you can start for free today at Botsociety.io!
When designing for voice, it may be tempting to think many of the same old UX rules apply. In reality, designing for voice is completely different from designing other digital products. You need to understand both the psychology of how people naturally use their voices to communicate, and how you want them to use their voice to get the most out of your product. Whether you are designing a product with voice serving as a compliment to other features, or you are designing hardware where voice is the main feature, here are a few best practices to consider.
How do people naturally communicate?
You are probably familiar with the notion that more than 90 percent of communication is nonverbal. The researcher Albert Mehrabian is most often credited with the formula for nonverbal communication: 7 percent is verbal, 38 percent is tone of voice, and 55 percent is body language. While there is some debate over the accuracy of these numbers (every situation is different), there is some truth to be found here. Mainly, when we use our voice to communicate, we’re used to pairing it with additional cues to convey our true meaning to the other person. Obviously, when a user is talking to a device, they can’t rely on body language. When designing for voice, we have to both account for and leverage the user’s intuition.
Voice Design Best Practices
Set expectations. Whether the product includes other features in addition to voice, or it relies entirely on verbal commands to operate (like Amazon’s Alexa), voice is meant to be a more convenient option. So avoid making it more cumbersome than it needs to be. It does no good to use voice and ask for concert tickets if that’s out of the scope of what the product can do. When designing for voice, the first thing you should do is set user expectations so they know how to use their voice with your product. Siri does this with a combination of audible and visual cues. How many times have you accidentally activated Siri, only to see these words flash across the screen: “Some things you can ask me: ‘FaceTime Lisa’”?This is Apple’s way of setting realistic expectations for what Siri knows how to do. The same goes for your own product’s voice interface design. As soon as possible, tell the user what they can expect to get when they use their voice to make a command.
Hold the user’s verbal hand. Unlike devices that rely primarily on text or navigation, where a user can clearly see where they are or can control their ability to get to where they want to go, voice-based products need to keep the user aware of the path they are following. The Interaction Design Foundation uses the example of a weather app. Rather than responding with “sunny and dry,” a better response would be “Today’s weather forecast is sunny and dry.” This not only clarifies the user’s supposed intention (maybe they wanted the forecast for the next hour, not the entire day), it also provides an example for how they can ask for information in the future. Design conversation paths so you can direct the user where they want to go.
Incorporate visual cues. If most communication if nonverbal, then it makes sense to leverage that reality in voice interface design. Example: when a user asks Alexa a question, lights appear to show that the device is processing the request. Similarly, when a user asks Siri to search online for an answer to a question, Siri will display the text of the question as she understood it. Both of these are different types of visual cues that reduce frustration for the user. Think about the visual cue that makes the most sense for your product, and incorporate it into the overall voice interface design.
Find your voice
Start designing for voice today at Botsociety.io
As people increasingly use devices to multitask, voice functionality will likely continue to grow. Botsociety can help you approach voice interface design thoughtfully. By keeping the unique characteristics of verbal and nonverbal communication top of mind, you can design the best possible user experience.
If you want Alexa to help you find a restaurant’s business hours or a list of fun places to visit in San Francisco, then you’ll need more than a one-word answer to get the information you need. To take your conversational design to the next level, you’ll need a sample dialogue. A sample dialogue is a model for the different dialogs and flow of conversation between your voice assistant and users. It’s a part of conversation design that is similar to a wireframe for voice interfaces, and it offers several benefits. Here’s why sample dialogues are important and how you can design one.
You can design your own sample dialogue for free at Botsociety.io
Why a Sample Dialogue Matters
Simple questions usually only need simple answers. But when the questions become more complex or may have several possible answers, then conversation design is important. A sample dialog ultimately helps you create great conversations between your target audience and your voice assistant. A sample dialogue is important for helping you quickly get a sense of the experience users may have with your voice assistant. You also get to experience what the conversation feels or sounds like sans issues for grammar recognition, diagrams of conversational flow and other technical distractions.
Start designing your own voice interface today at Botsociety.io
Creating a Sample Dialogue for Success
If you know that conversational design is the right fit for your voice assistant, then you’ll want to dive into creating a sample dialogue. But designing a sample dialogue requires following a few tried-and-true approaches to enhance the process. Here are some best practices for creating a sample dialogue for success:
Think about the scenario. The scenario you choose helps direct the topic of the conversation and the dialog your voice assistant will have. So, it’s important to design the sample dialogue around the scenario. Consider creating scenarios that can help users, such as a scenario where the user wants to inquire about their account balance.
Streamline the process. Streamline the process by focusing on one scenario and persona at a time. This makes it easier to design an effective sample dialogue quickly without making the conversation complicated.
Focus on the conversation. Keep the conversation in mind by designing scripts that focus on the spoken conversation to support an intuitive conversational flow.
Embrace Role-Playing. Partner up with a developer or someone on your team to test the sample dialogue. By having one person act as the user, you can test the conversational flow and the efficiency of the script to get a feel of the experience. You can also better identify issues with the script when you role-play.
Get help from conversational designers. Conversational designers have experience creating sample dialogues. You can take advantage of their expertise to design a sample dialogue that considers the different aspects of conversational flow you may overlook.
Design for errors. Include prompts for typical errors users may have. For example, you can include quick replies to delays in the flow of conversation, such as “I’m sorry. Say that again.” This keeps the flow of conversation natural.
Use prototyping tools for testing. Test your sample dialogues with the help of a prototyping tool, such as Botsociety. For example, you can use Botsociety to create high-fidelity prototypes of your voice assistant so you can test the conversational flow based on your sample dialogue. You can also detect errors, adjust them and repeat the process to finetune your voice assistant before finalizing it.
Improving conversational design helps make questions that require an in-depth conversation more natural and effective for users. That’s why it’s important to include a sample dialogue in your conversational design process. By creating your own, you can enhance your conversational design and the user experience.
Want to design your own sample dialogue? You can start for free today at Botsociety.io!
The following article was adapted from the thesis work of Jennifer Spatz. Jen is a Master of Industrial Design from Rhode Island School of Design. For more on her ideas, process, and final deliverables check out her portfolio.
Voice user interfaces excite us because they give us a glimpse into what the future might sound like. They require us to activate the senses that often remain dormant in most of our day to day interactions with technology. Unlike the graphic user interfaces of our phone and computer screens, a VUI ever so politely commands the use of our speech and hearing in order to interact.
Botsociety for Education: Rhode Island School of Design - YouTube
At present, most voice user interfaces use a conversational, often casual approach that mimics human interaction. Ask a question and “she” will respond by reading off information that the user will (hopefully) find useful. Sometimes Alexa is diplomatic, and sometimes Siri has an attitude. The mainstream VUI hopes to resemble a useful and efficient human that assists diligently in retrieving information and performing technology-based tasks such as playing a song or making a list.
It is important to note that although it seems easy and even novel to interact with a virtual human at your beck and call, it isn’t necessarily the most efficient. With human conversation, there is excess. Although the excess brings us closer to one another and helps us to connect, for a VUI, it is essentially theater. And at the end of the day, we are more likely to bond with a coffee table book or feel more connected to a teddy bear than we would a VUI that mimics human conversation—even with its technological capabilities.
Scoping The Problem
How, then might we interact with a VUI with the level of familiarity and comfort we experience when clicking, tapping and scrolling through our screens? Graphic user interface design must rely on entirely separate criteria than voice user interfaces, but the ways in which humans relate to technology remain conceptually similar across both interfaces. GUI design mimics real-world objects much in the same way VUI now mimics human-to-human interaction. iBooks were originally stored on what appeared to be a wooden bookshelf, just waiting to be dusted off and read in the archetypal overstuffed armchair.
However, as GUI design advanced, so did the pseudo-object representations. They were stripped of their excess and novelty and streamlined. The result is graphic user interfaces more confident in their own essence without attempting to obviously mimic real-world experience. There is elegance and authenticity found in technology for the sake of technology itself. And as users, we feel more at ease with a design that does not attempt to mirror our lives in a virtual reality. Rather, we appreciate its function and efficiency but have come to understand its use through the unmet needs of our real-world experience.
Observing strict conversational formalities when interacting with voice user interfaces creates unnecessary obstacles in accessing information.
How might voice user interfaces follow? The implications of advancement in VUI design are enormous both for the personal and professional lives of non-sighted individuals. Furthermore, voice user interfaces may change the way in which we interact with technology. The human senses associated with technology use have the potential to synthesize in such a way where one may optimize the other—a technological integration that remains surprisingly untapped.
The blind and visually impaired are often entirely excluded from mainstream graphic user experience. The use of screen readers, which refer to apps such as VoiceOver, do not replace the technologies used to consume digital content visually. They remain a supplemental tool at present, secondary to the visual content which they translate. Screen readers are effective in their ability to eliminate the excess and theater of a more novel and conversational VUI, but they aim to reproduce, not reimagine the way in which we interact with sound itself.
Possibilities and Capabilities
One possibility for the future of VUI is a more gestural and non-conversational approach to sound design. With the use of gestural sounds to communicate effectively and non-graphically, sound design could positively stray away from the frustrations and inefficiency of mimicked speech, and into something more elegant and less verbally skeuomorphic. Much in the same way that GUI design has advanced, VUI design has the potential to deliver content to us without the excess of speech. In turn, this could allow for us to rely more on voice user interfaces and open up a world of possibility for both sighted and non-sighted individuals to work and go about their daily lives with more ease and efficiency.
Our brains often respond more strongly to monosyllabic, natural and gestural noises such as a swish or a series of gentle taps that help us navigate large amounts of information. These subtle, non-speech indicators can limit the frustrations of conversational speech that already saturates our daily lives. There even exists the possibility of navigating through the use of symbolic sounds that both lead and alert, rather than simply dictate directions. Gestural, non-speech sound design eliminates a lot of unnecessary confusion between the interface and user, resulting in a more efficient means of communication.
Ideas can be distilled into short groupings of words that carry meaning even though they don’t sound like conventional language.
We are used to triggering monosyllabic sounds by turning something on and off, or sending an email. But what remains dormant is our ability to use technology through interaction with this type of sound. The possibilities are endless. The present of VUI design is oriented around human-centric interaction that mimics the world we already know. If voice user interfaces parallel the advancement of GUI, perhaps the future will reveal a more elegant and less obvious discourse with sound design.
You can experiment with some of these ideas for yourself over at Botsociety.
To orient itself toward the future, VUI design must consider that the ears and the voice are well equipped to perform what we perceive to be the work of the eyes. We must reimagine VUI design so that it embodies the full spectrum of human capabilities, for sighted and non-sighted individuals, rather than assuming a supplemental existence to the limitations of what we achieve only on the screen.
Want to design a user-focused, functional VUI of your own? You can start for free today at Botsociety.io!
Tools that offer real-time collaboration allow their users to work alongside each other to complete tasks openly and efficiently. From Google Docs to Zoom, there are countless dynamic platforms that let teams cooperate and collaborate simultaneously. Now with Botsociety, you and your team can seamlessly design chatbots together, making it easier than ever to build a chatbot that everybody will love. Here’s how!
Finding Your Design
After you open Botsociety, track down the design that you and your team is collaborating on.
Protip: you can make multiple folders on Botsociety if you have different projects you’re working on.
Here, we selected the Real Time folder:
Then, select the appropriate design within that folder. Here, we picked a Google mockup:
Once the design is opened, we can see both ourselves and our teammates. The left box with the orange icon and clicker is a teammate’s mouse—we can see where they are moving and can guess if they are going to add or change a design selection.
Editing Your Design
After identifying a typo in our design—”HERE IS IS”—we can correct it. Upon saving this edit, it will automatically update the design on my teammate’s screen without them needing to refresh the page.
Here, we can now see our updated mockup:
And that’s it! By using Botsociety, you and your team can easily work together to create chatbots that your users will love. Want to give it a try? You can start for free today at Botsociety.io
Throughout Pakistan, there is a stunning lack of resources for women regarding their reproductive health, human rights, and education. Thankfully, the Pakistani startup Aurat Raaj is using chatbots and conversation design to help lessen this glaring disparity. Founded by activist Saba Khalid, Aurat Raaj built a chatbot called Raaji that addresses and informs women about reproductive health. Use of a chatbot offers these women an anonymous, safe environment where they can learn about sex and reproductive health without fear of any backlash.
Aurat Raaj - YouTube
Before building Raaji, Aurat Raaj created playful, empowering animated content for girls and young women to approach otherwise taboo health issues. They then felt a need to create an around-the-clock interface for women to access:
We envisioned building a chatbot that would give information, provide emotional support, and connect women with specialists in the field.
This was when they stumbled upon Botsociety. Using the platform, they were able to build interactive flows with quick replies for ease of use, in addition to tracking these conversation flows in real-time. Beyond designing their chatbot, Khalid adds that Botsociety’s ability to import their design into Dialogflow and Rasa has been more than meaningful:
You can experiment with conversation design and the Dialogflow/Rasa export for yourself for free over at Botsociety.io
Botsociety helps us save time in taking the data from a flow diagram and manually feeding it into the two platforms to train the AI models.
As Aurat Raaj has improved upon its tech and increased its reach across Pakistan, it hasn’t been for a lack of challenges. They were rejected by twelve funding groups before finding sponsorship with UNICEF, UNESCO, and Transforming Education Through Arts. Despite whatever criticism they may receive in Pakistan, Aurat Raaj remains dedicated to using innovative digital content to empower women to hopefully end gender violence and inequality.
Want to design a chatbot that impacts your community? You can start for free today at Botsociety.io
When the bots you create can support the natural flow of conversations, they can help you enhance the experiences users have. But improving conversational design often requires following a few best practices to simplify the process. That’s where the Cooperative Principle comes in handy. The Cooperative Principle is British philosopher Paul Grice’s theory that the typical conversational flow is based on norms that people implement. Here’s why it matters and how you can implement it in conversational design:
Why Cooperative Principle is Important
The conversational flow is important for ensuring users achieve their goals. The flow of conversation needs to be natural and one that offers information that can help users get the answers to their questions and make their lives more simple. That’s why the Grice’s Cooperative Principle is important when designing your chatbot. Even leading companies like Google employ the concepts from the Cooperative Principle in their conversational design. With proper conversational design, you can enhance the user experience.
Build better text and voice interactions for free at Botsociety.io
How to Design Bots Using the Cooperative Principle
Designing your bots for success using the Cooperative Principle requires relying on Grice’s Maxims, including the maxims of relation, manner, quality and quantity. By taking these maxims into account, you can improve your conversational design and enhance the user experience. Here are some best practices to implement:
Be Clear. When you provide clarity, you can help users understand what your bot is communicating. Avoid dialogues that can facilitate ambiguity. For instance, design your bots to advise users of the next steps to expect after the bot collects information for a prospective sale.
Make your bot relatable. Give your bot a personality that users can relate to by including familiar colloquiums and dialogue. This helps to support a natural flow of conversation and enhance the user experience.
Be upfront. Don’t leave users in the dark about who is handling their concerns. Let your users know up front that they are speaking to a bot and make them aware of what the bot can do for them. When the bot needs to transfer the user to a live person, ensure the bot communicates this information.
Get help from a conversational designer. Conversational designers can also prove beneficial in improving the conversation design. Use the help of a conversational designer to review your script for your bot to ensure the information it shares is relevant and resourceful for users.
Be concise and give efficient information. Consider improving the flow of conversation by designing your chatbot for brevity. Include dialogue that provides users with sufficient information. Your bot should be brief with the information it provides. Limit it to what users need to accomplish their goals. For example, instead of providing a user with the rundown of every detail to expect from the forecast for the day, limit your bot’s answer to a weather forecast inquiry to the conditions for that morning and evening.
Test with a chatbot prototype. Prototyping tools, such as Botsociety, give you the chance to test your chatbot before you finish the product. For instance, you can use Botsociety to create a chatbot prototype and test the flow of conversation with beta users. This makes it simple to identify errors, fix mistakes and improve the overall quality of your chatbot before you present it to customers.
You can practice designing meaningful questions and voice interactions for free at Botsociety.io
Improving the flow of conversations requires meeting user expectations with conversations that flow naturally. Your chatbots can achieve this when you implementing the maxims of the Cooperative Principle in your conversational design.
When you design with the Cooperative Principle in mind, you can support a natural conversational flow, improve communication between your users and your chatbot and enhance the user experience.
Want to try designing your own cooperative conversation? You can start designing for free today at Botsociety.io
A lot of bot designers shy away from broaching difficult topics. Anything that might be deemed sensitive, personal, or embarrassing gets stamped “too risky” and scrapped.
It’s true that sometimes this impulse is spot on. It would be disastrous to replace crisis hotline responders with bots—these are conversations that need to be highly nuanced, and an error could mean the difference between life and death. You don’t really want that on your hands.
But by and large, I think people are too cautious in their assumptions about what may work as an automated conversation.
Provided the context is right and your interaction is designed thoughtfully, you can be really successful, and potentially do a lot of good.
Take this example from the journal Computers in Human Behavior. A 2014 study called “It’s only a computer: Virtual humans increase willingness to disclose” demonstrated exactly what you’d guess from the title: when people thought they were talking to a virtual health interviewer versus a real interviewer, they felt more comfortable divulging sensitive information and expressing sadness. This same effect has been observed with virtual human interviewers in other contexts. It’s not that people want to lie — it’s just that having a human in front of us can trigger our natural instinct to “impression manage,” or control how the other person is perceiving us out of fear of being judged. With a computer, this sensation is heavily decreased.
I’ve found this to be deeply true in my own experience in the healthcare industry. Initially, I had many of the same fears as others when a potentially dicey topic came up. Won’t people feel weird saying something so personal to a robot? Will they worry about some kind of malicious intent? I was quickly proven wrong. When we paid careful attention to crafting the interactions in a supportive, trustworthy way, people felt comfortable disclosing a litany of things I never would have imagined — like self-harm, depression, low food access, low medication adherence, and even health status markers like the results of a Hepatitis C test. Not only could we save time for busy clinical staff by handling these matters in an automated way, we could also do a better job helping patients feel safe enough to answer honestly. As a result, people were more often put in touch with the help and resources they needed.
You can practice designing meaningful questions and voice interactions for free at Botsociety.io
So, the power of automation should not be doubted. However, there are still many ways to go awry when it comes to designing such tough conversations. Let me walk through some things I’ve learned in the field.
Even though it’s a bot, you can’t be completely sterile and expect people to share at the same rates. A bot that barks “Do you have depression??” is going to feel a whole lot different than a bot that says, “Some people tend to feel a bit sad or low after leaving the hospital. Is this something you’re experiencing?” Make sure your users feel safe and supported. Also, don’t forget about your response post-disclosure: if someone does tell you “yes,” you need to address it in some way before moving on.
Something like “I’m sorry to hear that, I’ll make a note” will make someone feel a lot better than a bald “okay.”
Even with a bot, it can make people feel vulnerable sharing sensitive things, so you want to make sure you meet those feelings with care and warmth.
Things don’t go over too well when you don’t explain the purpose of a question, and what you intend to do with their reply. If your user doesn’t have a reasonable means of inferring all that, lay it out for them. Something like “I’d like to confirm your birth date so I can make sure it’s really you before we proceed” will be met with less resistance than “What’s your birth date?” In this age of privacy concerns, even asking people for things like their date of birth, email address, or phone number could be met with a similar kind of anxiety as asking for sensitive health information.
In a similar vein, it’s important to make sure people don’t feel targeted by your content. Even if an individual question is designed sensitively, you still have the potential to make folks feel uncomfortable if it carries special weight for them based on their identity. For example, questions about drug use could be offensive to people like African Americans or Latinos who have been inaccurately stereotyped as using drugs at higher rates. They may wonder if you’re only asking these questions based on the demographic information you have. So if you’re asking the same questions to everybody who uses your service, explain that. Or, if you are targeting people in some way, like maybe asking specific questions of new parents, you similarly would want to explain how you got this information so they don’t feel creeped out.
Give them an out
It’s also important to provide a means for people to opt out of the sensitive conversation or question. Sometimes, however carefully you frame something, people just won’t want to engage, and you want to respect that. Let someone know they can skip, and if possible, explain how they can accomplish the task another way that may be more comfortable for them. When you provide an opt-out as part of the design itself, fewer users will be compelled to abandon the interaction altogether. Also, using autonomy-supportive language affirming that people have choices, it’s a good way to build trust overall, even with users who would have felt fine answering the question. If it feels like you’re forcing people to do things, that can trigger a psychological resistance reaction that makes people want to do the opposite.
Start building better questions and voice interactions for free at Botsociety.io
Know when to scrap it
Although on the whole, these sensitive conversations are avoided more often than they should be, you also need to know when you’re working with a bad idea. For instance, you ’re usually fine when a conversation is simplistic, like a yes/no question. But if your topic is complex, and your user’s input is likely to be diverse, you will run the risk of not understanding the user’s intent, leading to confusion and error messages. For non-sensitive complex topics, it’s sometimes fine to take your best guess, put it out into the world, and then iterate. The cost of a hiccup isn’t so high. But as you’d imagine, you risk a lot more damage in sensitive conversations.
I hope this primer helped get you started thinking about how you may want to handle difficult topics in your bot. Have any other insights to share? Thinking about a tricky conversation you may want to broach in your bot? Let me know in the comments! Check out Botsociety to get started designing questions of your own today!
At Botsociety, we are always eager to listen to feedback from our users. Why? Because you help us create all the features UX and conversational designers dream about. This month, we’re releasing a few more. Let’s start.
New Platform: Generic Desktop Preview
So you’ve decided to build a chatbot for your own website, but you wonder how you can model this experience on a desktop. With Generic Desktop Preview, you can now design and preview a conversational experience for your own website, on your own desktop.
Select the Desktop Layout option at the top-right of the screen, highlighted in green here:
That’s it, you can now preview your design in Desktop mode!
Here’s a tip: go to Settings at the top-left of the screen to customize your design assets and appearance!
New Feature: Revision History
Liked your first draft better than your second? You can now review all past edits as you build with Revision History. Track your changes and never miss a message throughout the entire designing process with this tool.
To access this function while designing, click on the new Revision History side panel on the left-side of the screen:
Revision History automatically saves a snapshot of your design with every 10 edits. All saved snapshots are listed in the side-panel. You can then revert to past designs with a single click!
We launched a new Search bar to help you find all your designs and folders across your entire workspace. You can find it here.
We improved the Design Preview experience. You can now pause the preview at any moment.
You can now customize designs for a generic application or website to a higher degree, for example by choosing chat backgrounds.
Sometimes, we make mistakes. We’ve found and fixed some bugs!
All of these features are ready to go! Head over to Botsociety to test them out now!