Conversation Design


Design Framework

Discover • Define • Ideate • Develop • Test • Analyze

The design framework I follow provides high-level visualization of the design process from start to go-live and beyond. I use it to organize the information and ideas of the problem, enabling me to work on it more effectively.



Putting the framework in action

It isn’t every day one gets the opportunity to reinvent a critical function in one of the world’s most dynamic and vital industries. Yet this is precisely what we managed to accomplish by transforming the way a communications giant approaches its customer service function.

When a Fortune Global 500 Information and Communication Technology company decided to leverage AI to transform their business in 2018, a key frontier of their digital transformation journey was to introduce an Intelligent Virtual Assistant. In 2019, I became part of an ambitious project to deploy a customer-facing cognitive assistant on their website, to deliver personalized customer experiences at scale.

To comply with my confidentiality agreement, I have obfuscated classified information in this case study.

The designs below are a reinterpretation of the original.

The Brief

The client approached us with a clear objective — they wanted to automate customer interaction. The motives were simple: improve engagement, push down costs, and increase revenue.

To meet their transformation milestones, we knew we had to move fast. The challenge was clear. We had to demonstrate value in a month! We committed to delivering 2 use-cases (from a total of 40) on the platform in 30 days, developed and ready to play around with.

A key stakeholder summarized it well for us:

   "We want to automate customer-facing touchpoints to deliver a personalized experience 24×7 so customers can feel valued."

The platform allowed us to combine complex NLP, cognitive learning abilities, emotional intelligence, and autonomic task management, helping the virtual agent learn from and respond to text inputs in an engaging, personalized, and emotionally cognizant manner.

With that

The design journey started.

Kicking off the project in mid 2019, I took charge of the experience strategy and design.

The efforts of collaboration with a UX designer, two project managers, and a team of developers, resulted in deployment of a virtual assistant on the client’s website.

I worked on this project till early 2020. This is before the focus shifted on introducing other channels for interaction (SMS to begin with and voice later).

Discovery activities

Prompt, high‐intensity effort was put in for discovery, allowing us to gain empathy for users, become aware of the business problem (and opportunity space), define project milestones & metrics of success.

We took this time to understand our client’s vision, and research user needs, behaviors & pain‐points.

We arrived at an understanding by conducting workshops, interviews, contextual inquiries, problem definition sessions, and various other activities (including surveys, assumption mapping, affinity diagramming, etc.) with the client stakeholders and a representative group of users.

Key insights


In trying to uncover why people seek customer support from their internet service provider, the process they go through, and what works or does not work in that experience, we made some interesting discoveries.

32% of existing users would reach out to customer support for modem troubleshooting. Let’s focus on that in this case study.


The root cause

It was extremely frustrating for users to not have their broadband issues resolved at the earliest. When reaching out for help, they felt the advice wasn’t helpful; mainly because, the same information for self diagnosis was available online, and 8 out of 10 times, an appointment with a service expert would be required.


Background

63% of the company’s existing customers were broadband users. In our interviews, there was a consensus amongst users — they chose said company because of the superfast internet, despite the slightly higher price point.


The motivation

To troubleshoot broadband issues, whenever an appointment needed to be booked, they would never find an immediate time slot. This meant the customers would end up waiting for a day or more to have an executive come over to resolve the issue. We realized, there had to be a more efficient solution.


What we learnt

In making the choice to go for said service provider, customers knew they were paying a premium for fast, reliable internet. They felt the premium also covers fast, reliable customer support. When faced with an issue, they’d expect quick help and the right support, irrespective of when that support is sought.


Next steps

We needed to find a way that wouldn’t be as limited as self diagnosis and wouldn’t take as long as waiting for expert help. We wanted to add more value to the user experience, something that goes beyond online search results and forms a bridge between self help and expert help.


Defining the problem

With the goal to define and align on the problem that needed solving, formulating the user need statements (more often known as problem statements), helped organize learnings about the problem space, using what was learnt in Discovery about users and what’s important to them. The statement acted as a condensed explanation of who the problem affects and why we’re solving it (e.g. How might we free up customer service representatives for complex cases?).

Crafting Personas

With the goal to build empathy using representative symbols, I built personas to guide experience choices and decisions. Building personas helped focus design efforts on a common goal, understand user needs & expectations, and align stakeholders accordingly. The user persona acted as a fictional archetype of the most strategic (here the largest) focal point of the end user population. I also designed a persona for the virtual agent. This involved identifying the qualities and adjectives that would characterize the personality of the virtual agent, setting the tone and language the agent would use, and ensuring that the persona aligns with the brand being represented.

Mapping user journeys

With the goal to experience the product from a user’s point of view, map the entry point, frustrations, etc., I built user persona specific customer journey maps. Taking the series of user actions in a timeline with user thoughts and emotions (thinking, feeling & doing representations), helps with storytelling and visualization, two very powerful, effective mechanisms for conveying information in a way that is memorable and concise. The process of understanding the emotional journey helps identify where the design needs to focus. It also contributes towards creating a shared vision. This fosters a more user- centric approach to product design, which ultimately leads to better user experience.

Persona interaction path & Signposting

With the goal to build a foundation for the full conversational architecture, I designed the conversational pathway detailing the persona’s journey. The persona interaction path is the baseline conversation by which a user accomplishes the goal of a use case. I also used signposting to formulate conversational junctions, through which language cues are given to prompt the user & elicit responses important to take the conversation forward.

Conversational diagrams

With the goal to cover all possible user journeys, I designed the conversational flow, which offers:
– The full mapping of all conversational pathways
– Language signposts
– Notes on leveraging UI elements
– Conditional logic for pathway triaging
– Database or API references dependencies and
– Fallback routes.

Technical detail is added to the final iteration of the conversational diagram and is then used to develop the use cases.

Additional activities carried out



A/B Testing

Used to compare two differently designed versions of the experience to evaluate engagement & performance, to help make data-informed design decisions.

Conversation Analysis

Once the solution was developed and deployed, user engagement was assessed by analyzing conversational transcripts. This helped do a SWOT analysis on the design and the effectiveness of the solution.

Usability Testing

Structured sessions organized to observe users completing specific flows/tasks to evaluate the usability, and therefore value, of the solution.

Experience Measurement

The qualitative analysis of conversations gave way to quantitative analysis. Various parameters were used to provide metrics that helped evaluate the solution and measure it in terms of the KPIs.

User Acceptance Testing

Formed guidelines to allow for constructive UAT. The designed solution was opened up to a large group of users to generate feedback, in the form of suggestions or bugs, reported on observation.

Experience Enhancements

The analysis helped identify opportunities for enhancements. To meet user needs and cater a solution designed around the user and for the user, it is important to continually alleviate the experienced pain points and incorporate user feedback, whether shared explicitly or implicitly.

Say hi!

Looking to hire a designer, discuss design needs, or just chat about AI disruptions and innovative solutions?

Let’s start a conversation.

Drop a message here and I’ll get back to you. Or you can get in touch with me at chadharaagini@gmail.com.

 

Contact Form