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

  1. Endless scrolling

  1. Ineffective product discovery

  1. Too robotic

  1. Push to contact sales repeatedly and at the wrong time

Our preliminary research helped us identify areas that we could potentially target

  1. Create personalized, context-aware interactions that feel human

  1. Create personalized, context-aware interactions that feel human

  1. Improve product exploration with intelligent suggestions and comparisons.

  1. Improve product exploration with intelligent suggestions and comparisons.

  1. Build a trustworthy chatbot that increases engagement without overwhelming the user.

  1. Build a trustworthy chatbot that increases engagement without overwhelming the user.

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

  1. Personality and tone

Goals for designing the personality of the chatbot?

  1. Improving user engagement with the chatbot through language and tone

  2. Increasing user retention

  3. Designing a seamless bot to human(Sales-rep) transition

fin (they/them)

fin (they/them)

Representative of Salesforce AI Chatbot

We designed them to be-

Curious

Engaging

Result oriented

Initiator

Encouraging

  1. 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

  1. Users expect the chatbot to simplify product discovery by providing quick information to help them decide whether to explore further.

  2. 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..

  1. Simplify product discovery and recalling past interactions to ease decision-making?

  2. Help users navigate through different sections within the lengthy chatbot conversation, and retrieve needed information more easily?

  1. 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..

  1. Design the chatbot to prompt users for clarification or elaboration?

  2. End ensure they feel confident it will understand detailed responses?

  1. 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

  1. To improve team collaboration in research process, we broke into two sub-groups which improved efficiency in a nine-member team.


  1. Weekly feedback sessions helped us get real-time feedback and a sense of stakeholder expectations.


  1. We gradually learned the balance in assisting users while allowing them the autonomy to independently explore the chatbot.

Impact & outcome

  1. Enhanced engagement through a thoughtfully designed chatbot personality.


  1. Reduced friction in product discovery with guided recommendations.


  1. 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.

Hit me up for conversations on art, books, films, music and anything design!

All rights reserved

Hit me up for conversations on art, books, films, music and anything design!

All rights reserved

Hit me up for conversations on art, books, films, music and anything design!

All rights reserved