2 min read

Talking to Conversational AI powered Paper Airplanes

Talking to Conversational AI powered Paper Airplanes

We’ve got AI. Who needs designers?

That’s the question that popped into my head when watching Google’s incredible LaMDA demo.

Google used a new type of neural network, called a ‘Transformer’, and fed it with data. But not just any data. They gave it transcriptions of dialog. Conversations.

What came out was quite incredible. The chatbot had a very natural-sounding chat with one of the researchers. As a rather interesting twist, it pretended to be a paper airplane! And Pluto (the dwarf planet). Yes, you read that right.

Here’s an extract of the conversation…

A picture of a paper aeroplane with an extract of a chat between an researcher and an AI program pretending to be an Aeroplane

(Image credit: Google)

With AI that good. Do we still need Conversation Design? Do we need Conversation Designers?

Yes. Because your business doesn’t need to have random conversations about Pluto or paper airplanes.

You need to have conversations that help your customers get stuff done. That engage them. That communicate your brand.

Conversation Design isn’t just about crafting prompts and defining intents in your favorite IVR, voice assistant, or chatbot platform.

Yes, Conversation Design involves the nuts and bolts of conversation:

  • Predicting and understanding what customers say
  • Responding with language that’s easy to understand
  • Managing turn-taking
  • Handling misunderstandings

But great Conversation Design also involves activities that go much deeper and wider…

  • Deciding the right steps to solve a problem
  • Curating content that will help and inform
  • Converting that content into conversational form
  • Showing empathy
  • Managing expectations (customer and business)
  • Communicating brand attributes

The role of Conversation Designers will change over time. Right now we have to teach our Conversational AI platforms almost everything. In the future, they’ll handle more of the nuts and bolts of the conversation. Just like web and mobile frameworks make it easy to build functional websites.

But smart, helpful, friendly, resourceful… even emotionally intelligent? Will AI pick up the slack there too? Not for a long time.

The age of Conversation Design, and the opportunity for Conversation Designers has many, many years to run 😁

5 min read

Align Your Conversational AI Team by Framing Problems — Not Solutions

Align Your Conversational AI Team by Framing Problems — Not Solutions

Getting everyone on your conversational AI team on the same page is the only way to solve problems effectively. However, that’s not always easy. Holding a workshop to generate alignment is a great idea — but the focus needs to be in the right place.

Project managers and team members from various departments often get ahead of themselves. They rush toward solutions without stopping to work out what the real problem is. The result? In the majority of cases: Projects veer off-course, the team loses focus, and stakeholders are left puzzled as to why things didn’t work out as they expected.

So before you kick-off your next Conversational AI project, start by framing the problem, not the solution. A properly run problem-framing workshop is the key to avoiding those issues. Here’s how you do it.

How to Identify the Problem Your IVR, voice or Chatbots Must Solve

Conversational AI can be extremely good in very narrowly defined situations like routing someone to the right place, identifying who’s getting in touch, verifying they are who they say they are, giving status updates on an order, or arranging an appointment.

Coming up with solutions can feel more productive than identifying the underlying problem. But finding the right solutions requires a concrete understanding of the problem you’re trying to solve.

That’s why taking the time to discuss and align on the problems that are affecting your business before you start building your Bots is critical. That’s where the conversational AI Problem Framing workshop comes in. It’s a structured workshop that aligns teams around the problems that are affecting their business.

Conduct a Problem-Framing Workshop

Your problem-framing workshop has several goals. It should give your team an opportunity to:

  • Explore current business needs surrounding specific areas
  • Discuss and vote on the most critical problems
  • Look at what the business wants to achieve
  • Provide input to justify the need for change, and the cost if nothing changes
  • Consider existing team knowledge and expertise that will help them meet their goals
  • Evaluate any obstacles that could get in the way of achieving those goals

That’s the general idea of what you want your conversational AI problem-solving workshop to achieve. At this point, you’re probably wondering: How do I do all of that?

Successfully Framing Problems Requires Strong Facilitation. Keep Your Conversational AI Team on Track.

Your session needs a clear aim, and a facilitator. That could be you, someone else on your team, or someone from outside of your business. Let’s assume you’re going to facilitate.

As a facilitator, the first thing to remember is that your workshop is not about progress. It’s about aligning your team on a common problem. The best way to do that is to give everyone a chance to voice their opinions about the problems affecting the business, and why they need to be fixed. This process helps you to paint a big picture view of the types of problems that you’re facing today.

Keep these key points in mind as you facilitate your workshop.

  • Collaboration is a must. This shouldn’t just be a passive discussion. Experts on the team should write down their views, and invite others to read them, organize them, and vote on key ideas.
  • Workshops only work with open minds. During these workshops, participants can sometimes feel as though they’re revisiting old conversations. That’s absolutely fine. Encourage everyone to embrace the opportunity to share and to take the time to explore different perspectives.
  • Collaboration requires preparation. In-person collaboration requires familiar materials — whiteboards, sharpies, sticky notes, voting dots, etc. But remote collaboration, a necessity during travel bans and lockdowns, requires different tools. Software like Miro and Mural allow for remote collaboration by replacing whiteboards, sticky-notes, and voting dots, with digital equivalents. If your team is new to online collaboration, factor in some warm-up activities to allow participants to get to grips with the basics before you get going with your workshop .
  • Act as a guide, not an expert. A good facilitator helps participants access their own knowledge. They create a safe space for collaboration, with a clear structure and aim. Engage your participants, keep them interested, and challenge them. Keep instructions clear and simple. Don’t just tell them what they’re doing. Tell them, then demonstrate it, then sum it all up again.
Ask Questions About the Problems Your Voice, IVR, and Chatbots Face.

Asking questions helps avoid shifting your focus to solutions, keeping it on problems. There are some important questions that every problem-framing workshop should cover:

  • What undesirable situations or challenges exist? Encourage your team to think about this from the business and internal stakeholders’ perspective. What does the business need? Are too many calls hitting agents in the contact center? Is handling contacts currently too expensive? Sales too low?
  • What are you actually looking to achieve? Consider the problems your group identified, and imagine looking back on the project 20 years down the road. What would success look like? Where did it land you? What are the positive and negative impacts on your team, other teams, and the business as a whole? If the problem were resolved, would the results justify the effort? If you don’t get there, what does that future look like?
  • What’s happening in the problem space? Ask the group to think about ‘What they know or do already that can help move towards their goal’. What could hold them back . What obstacles stand between where they are today, and where they want to get to? These might be things like legacy technology, or broken internal processes — what’s taking the wind out of their sails?
  • How might we? Use “how might we” questions (HMWs) to generate ideas about correcting course. Once you’ve got your list of top issues to address with conversational AI, ask how you might avoid them. This is a great way of converting negative ideas into positive ones.  

3 Simple Tips to Avoid Common Pitfalls when Framing IVR, Voice, and Chatbot Problems

The whole purpose of a problem-framing workshop is to tee up your IVR, voice, and chatbots for better success. The last thing you want to do at this stage is create more problems.

Avoid doing so by:

  • Keeping your timeframe in mind. Make a plan for your workshop, and stick to it. When you need to move on, move on. Don’t keep it in your head — get your workshop plan down on paper and hold yourself accountable for sticking to it.
  • Preparing your collaboration space. We touched on this above, but it’s up to you as the facilitator to make sure the attendees have what they need for a productive session. In-person or remote, physical or digital resources — have it ready.
  • Understanding your audience. Great facilitation is key to a successful conversational AI problem-framing workshop. That means you need to work with your audience. Throughout the workshop, look out for champions, supporters, fence-sitters, blockers, and snipers among the attendees. Certain participants might need coaching to keep them engaged — or to prevent them from disrupting the session.

Keep all of this in mind going into your session, as you work through your exercises, and as you wrap up, and you’ll be in good shape. A fruitful workshop asks a lot of its facilitator, but you’ll succeed as long as you attack the challenge in a strategic, structured way.

Remember, you can’t be a facilitator and a contributor at the same time. Facilitation is a great skill to learn and develop, but if you’re a key stakeholder, or subject matter expert, your skills and experience might be better deployed contributing to the workshop, instead of facilitating it. In that case, you should look outside your team for someone who could play the role of facilitator. Or look for a professional facilitator who can run a great workshop and make sure everyone who needs to contribute, can.

A problem framing workshop is a great starting point for building a Bot Strategy.

2 min read

Why your IVR, voice and chatbots need HR for AI

HR style management of a BOT workforce

There are two fundamental differences between conversational experiences, like IVR, voice and chatbots, and graphical user interfaces, like web and mobile experiences. These differences demand a different approach.

Learned vs Instinct

Web and mobile are learned experiences. They use physical metaphors like inertial scrolling, desktops and filing cabinets. But the interaction we have with them is learned.

We learn to use a touchscreen or mouse. We discover how to navigate the user interface. We adapt to the technology. And we can do that because we have big flexible brains that can adapt our behaviour to our environment. That’s what helped us populate every corner of the globe and imagine, build, and use digital devices.

But language is different. Conversation is different. We learn language at such a young age that we can’t unlearn it. Harvard Professor Steven Pinker describes language as an instinct. Just as babies instinctively attach to their parents for food and protection, they instinctively develop language. And we can’t un-learn it.


The other big difference is that most of the channels we use to interact with bots started as ways to interact with humans: the telephone, text messaging, web chat, WhatsApp and Facebook Messenger. These were all originally used for talking with other humans. Bots joined the party later. So customers interacting on these channels don’t just need bots to speak and listen like humans do. They also expect them to be smart, helpful and resourceful in solving problems, just like humans are.

Web and mobile experiences don’t have that human expectation problem. Most web and mobile customer service experiences are like forms and documents, in-store adverts or shopping catalogs. We expect those things to be useful and easy to understand. But we don’t expect them to be smart, helpful and resourceful.

These two differences set a really high bar when it comes to building bots.

We adapt to use web and mobile experiences, and we expect them to be useful. But we won’t, in fact we can’t adapt to the way bots talk, and we do expect them to be smart, helpful and resourceful.

They need to speak and listen like a human, then understand and act like a human would too.

A different approach

The best Artificial Intelligence (AI) algorithms today can match or exceed human performance in specific, narrow areas. We don’t have a generalized form of AI with anything like human levels of flexibility and robustness. But there is a fix for this.

You need to treat your bots like a workforce, that needs leading and managing, just like humans do. You need clear job descriptions for your bots, so they can excel in their narrow areas of expertise. And you need to review their performance and coach them to improve, just like you would do in regular 1-2-1s with your staff. We call it HR for AI.

It’s a big mindset shift, but once you look at your bots from that perspective, getting maximum ROI from your investments in conversational AI becomes as simple (and difficult) as applying management best practice to your bots.

In the next blog in this series, I’ll be looking at How to apply the principles of HR to your bot workforce.

If you missed the first one, check out what’s the best Conversational AI platform?

3 min read

Design IVR Conversations not Call Flows

Design IVR Conversations not Call Flows

Planning any type of automated customer communication can be tricky, but in the voice channel it’s uniquely tough. To start delivering natural, satisfying experiences through an IVR, designers are tasked with mechanising a very non-mechanical process: human conversation.

5 min read

Designing conversational AI chatbots and what we can learn from IVR

Designing conversational AI chatbots and what we can learn from IVR

Conversational AI chatbots are a hot topic. Looking at our Twitter and LinkedIn feeds, the interest and excitement bubbling around this area is vast. Having worked in conversational user experience (UX) over the last two decades,  it’s exciting to see that the industry is experiencing a rapid growth, and delving into emerging technologies like bots and agents.

5 min read

Improving the IVR Experience with Personalization

Improving the IVR Experience with Personalization

Personalisation has been a hot topic in IVR Customer experience (CX) circles over the last couple of years. Done well, personalised experiences have the potential to improve CX, increase loyalty, and reduce cost to serve.