salesforce conversational ai
Designing trustworthy and Human-Centric Chatbot Experience
Role
UX Designer
UX Researcher
Facilitator
Character Design & Illustration
Duration
August '24 -December '24
Team
Atharva Chavan
Callista Faustine
Chun-han Mei
Devi Kulkarni
Harshika Rawal
Jackson Fowler
Michelle Kim
Shantanu Thorat
Sumedha Kulkarni
Tools
Figma
FigJam
Procreate
ChatGPT (Simulation Research)
Have you ever come across an ai chatbot that creates stress more than successfully helping you find what you want?
The problem
Imagine Emma, a small business owner, landing on Salesforce’s website. She's greeted with a sea of products, jargon, and unclear directions. Frustrated, she clicks the chatbot, but instead of help, she gets generic replies and a push to contact sales. Frustrated, she closes Salesforce window and chooses to call a representative instead.
Key issues
Endless scrolling
Ineffective product discovery
Too robotic
Push to contact sales repeatedly and at the wrong time
Our preliminary research helped us identify areas that we could potentially target
Overarching project goal
How might we design a human-centered AI chatbot experience for small businesses using the Salesforce website for the first time with specific focus on product discovery.
Research
For research we split into two sub-teams for different focal areas of the project. Team A conducted research for product discovery while Team B conducted research on personality and tone of the chatbot.
Personality & Tone of the chatbot
18+
Participants
3
Personalities
Multiple
Insights
Ideation
We came back and brainstormed together based on our gathered research insights.
Final design
Personality and tone
Goals for designing the personality of the chatbot?
Improving user engagement with the chatbot through language and tone
Increasing user retention
Designing a seamless bot to human(Sales-rep) transition
Representative of Salesforce AI Chatbot
We designed them to be-
Curious
Engaging
Result oriented
Initiator
Encouraging
Product comparison and timeline
Chatbot will dynamically provide comparison table of products based on filters user chose. Users can save summary in the form of a downloaded PDF/ Excel table.
Key insights
Users expect the chatbot to simplify product discovery by providing quick information to help them decide whether to explore further.
Users expect an easier way to refer to relevant information in the chat, such as product suggestions and their inputs, reducing the time spent scrolling back and forth.
How might we..
Simplify product discovery and recalling past interactions to ease decision-making?
Help users navigate through different sections within the lengthy chatbot conversation, and retrieve needed information more easily?
Behavioral trigger: clarifying questions
After user types in vague or brief entries, chatbot will present 3 to 4 selections to clarify their need, ensuring more relevant responses. Not every user is a prompt engineer, the clarifying questions help users when they don't know what and how to ask. This in turn helps build user trust and reliance in the chatbot.
Key insights
Users expect the chatbot to provide accurate, relevant responses and inform them its capabilities.
How might we..
Design the chatbot to prompt users for clarification or elaboration?
End ensure they feel confident it will understand detailed responses?
Behavioral trigger: suggestive prompts
After user keeps backspacing three times, chatbot will show suggestive prompt that user can select to extend the entry. Suggestive prompt will constantly change according to user’s typing.
What does this address?
Struggle to structure potential questions to the chatbot, keep refining clarifying questions / follow-ups
Not every user is a prompt engineer, the clarifying questions help users when they don't know what and how to ask. This in turn helps build user trust and reliance in the chatbot.
*Note
At this point, Salesforce's Einstein was not an AI chatbot.
Reflections
Challenges & lessons
To improve team collaboration in research process, we broke into two sub-groups which improved efficiency in a nine-member team.
Weekly feedback sessions helped us get real-time feedback and a sense of stakeholder expectations.
We gradually learned the balance in assisting users while allowing them the autonomy to independently explore the chatbot.
Impact & outcome
Enhanced engagement through a thoughtfully designed chatbot personality.
Reduced friction in product discovery with guided recommendations.
Improved chatbot usability by addressing key pain points in navigation and conversation clarity.
This project provided valuable insights into designing AI-driven conversational interfaces while maintaining a human-centered approach, ensuring that AI solutions remain intuitive, adaptive, and user-friendly.