Thumbnail

Fin: Salesforce's GenAI Chatbot

Helping Users Find What They Need: Without the Hard Sell!

UX Design

UX Design

UX Design

AI Chatbot

AI Chatbot

AI Chatbot

Conversational Design

Conversational Design

Conversational Design

project type

Industry sponsored academic project

GoaL

Supporting discovery with clear assistance that naturally leads to sales.

Target Audience

First-time Salesforce website visitors

ROLE

UX Designer

team

9 UX Designers, 2 Mentors

tools

Figma, ChatGPT, Salesforce Lightning Design System

Date

Dec 2024

Duration

4 months

TL;DR

We designed Fin, a context-aware, GenAI-powered chatbot for new customers visiting the Salesforce website. Fin guides users through product discovery using a personalized, human-like experience while balancing the business need of driving sales. From behavioral triggers to proactive help, Fin keeps the sales journey smooth, smart, and stress-free.

Project Highlights:

  1. Insightful, Empathetic, and Structured: Designing Fin’s "Personality"

  2. Smarter Conversations: Behavioral Triggers for Adaptive Support

  3. Product Comparisons Without the Sales Pitch

  4. When Users Go Quiet: Inactivity Recovery That Respects Autonomy

Overview

Salesforce came to us with a challenge…

Create a chatbot that welcomes new explorers, helps them discover products with ease, and seamlessly guides them to sales conversations at the right moment.

We went around in cycles of poking, sketching, and pausing—each loop bringing us closer to answering the question…

How might we design a conversational experience that balances helpful product discovery with subtle, timely nudges toward sales?

Methods

+

Contextual Inquiries as discovery research

+

Competitor Analysis for benchmarking

+

Rounds of Iteration and Prototyping

+

Cognitive Walkthroughs for testing

Highlights

1

Insightful, Empathetic, and Structured: Designing Fin’s "Personality"
Insightful, Empathetic, and Structured: Designing Fin’s "Personality"

To find the right tone, we simulated chatbot personalities (fun, formal, and empathetic) in ChatGPT and tested preferences across 16 users. Insights led us to craft Fin, a dolphin-inspired bot whose personality aligns with Salesforce’s brand and users’ professional expectations.

Fin is:

  • Curious, empathetic, informative, warm

  • Structured and detail-oriented

  • Formally toned—but friendly, never robotic

To find the right tone, we simulated chatbot personalities (fun, formal, and empathetic) in ChatGPT and tested preferences across 16 users. Insights led us to craft Fin, a dolphin-inspired bot whose personality aligns with Salesforce’s brand and users’ professional expectations.

Fin is:

  • Curious, empathetic, informative, warm

  • Structured and detail-oriented

  • Formally toned—but friendly, never robotic

To find the right tone, we simulated chatbot personalities (fun, formal, and empathetic) in ChatGPT and tested preferences across 16 users. Insights led us to craft Fin, a dolphin-inspired bot whose personality aligns with Salesforce’s brand and users’ professional expectations.

Fin is:

  • Curious, empathetic, informative, warm

  • Structured and detail-oriented

  • Formally toned—but friendly, never robotic

2

Smarter Conversations: Behavioral Triggers for Adaptive Support
Smarter Conversations: Behavioral Triggers for Adaptive Support
img
img

Users struggled to phrase queries and often abandoned chats. We implemented behavioral triggers:

  • Clarifying Questions: Triggered by vague prompts to nudge users with gentle follow-ups

  • Suggestive Prompts: Triggered by 3+ backspaces or rephrasings, offering optional guidance

Users struggled to phrase queries and often abandoned chats. We implemented behavioral triggers:

  • Clarifying Questions: Triggered by vague prompts to nudge users with gentle follow-ups

  • Suggestive Prompts: Triggered by 3+ backspaces or rephrasings, offering optional guidance

Users struggled to phrase queries and often abandoned chats. We implemented behavioral triggers:

  • Clarifying Questions: Triggered by vague prompts to nudge users with gentle follow-ups

  • Suggestive Prompts: Triggered by 3+ backspaces or rephrasings, offering optional guidance

3

Product Comparisons Without the Sales Pitch
Product Comparisons Without the Sales Pitch
img
img

Let users compare options directly within the chatbot interface — no more jumping between tabs or forced sales calls.

Why it works: Empowers independent decision-making with side-by-side product cards and contextual feature summaries.

Let users compare options directly within the chatbot interface — no more jumping between tabs or forced sales calls.

Why it works: Empowers independent decision-making with side-by-side product cards and contextual feature summaries.

Let users compare options directly within the chatbot interface — no more jumping between tabs or forced sales calls.

Why it works: Empowers independent decision-making with side-by-side product cards and contextual feature summaries.

4

When Users Go Quiet: Inactivity Recovery That Respects Autonomy
When Users Go Quiet: Inactivity Recovery That Respects Autonomy

We noticed idle users often dropped off. Fin gently re-engages with 3 context-aware suggestions after periods of inactivity. We balanced helpfulness with autonomy:

  • Not too frequent

  • Suggestions based on chat history

  • Minimal friction to re-engage

We noticed idle users often dropped off. Fin gently re-engages with 3 context-aware suggestions after periods of inactivity. We balanced helpfulness with autonomy:

  • Not too frequent

  • Suggestions based on chat history

  • Minimal friction to re-engage

We noticed idle users often dropped off. Fin gently re-engages with 3 context-aware suggestions after periods of inactivity. We balanced helpfulness with autonomy:

  • Not too frequent

  • Suggestions based on chat history

  • Minimal friction to re-engage

Project Summary

  • Fin empowers users to navigate Salesforce confidently and independently

  • GenAI + human-centered research = smarter, kinder chat

  • Trust is built through transparency, context-awareness, and proactive help—not sales pressure

  • Fin empowers users to navigate Salesforce confidently and independently

  • GenAI + human-centered research = smarter, kinder chat

  • Trust is built through transparency, context-awareness, and proactive help—not sales pressure

  • Fin empowers users to navigate Salesforce confidently and independently

  • GenAI + human-centered research = smarter, kinder chat

  • Trust is built through transparency, context-awareness, and proactive help—not sales pressure

Reflections and Learnings

This project challenged me to design not just for usability, but for emotional nuance. Balancing user autonomy with smart, timely assistance made us rethink what “human-centered” means in an AI context. We had to make Fin helpful, but not overbearing — informative, but not robotic.

A major takeaway was realizing how small details — a nudge, a timeline marker, a pause — can completely shift a user’s experience. Designing behavioral triggers and adaptive responses taught me how to anticipate user hesitation and build trust through clarity.

Collaboration was key. Feedback from users, sponsors, and peers shaped every iteration. What started as a chatbot became a companion — one that could guide, adapt, and stay out of the way when needed.

This project challenged me to design not just for usability, but for emotional nuance. Balancing user autonomy with smart, timely assistance made us rethink what “human-centered” means in an AI context. We had to make Fin helpful, but not overbearing — informative, but not robotic.

A major takeaway was realizing how small details — a nudge, a timeline marker, a pause — can completely shift a user’s experience. Designing behavioral triggers and adaptive responses taught me how to anticipate user hesitation and build trust through clarity.

Collaboration was key. Feedback from users, sponsors, and peers shaped every iteration. What started as a chatbot became a companion — one that could guide, adapt, and stay out of the way when needed.

This project challenged me to design not just for usability, but for emotional nuance. Balancing user autonomy with smart, timely assistance made us rethink what “human-centered” means in an AI context. We had to make Fin helpful, but not overbearing — informative, but not robotic.

A major takeaway was realizing how small details — a nudge, a timeline marker, a pause — can completely shift a user’s experience. Designing behavioral triggers and adaptive responses taught me how to anticipate user hesitation and build trust through clarity.

Collaboration was key. Feedback from users, sponsors, and peers shaped every iteration. What started as a chatbot became a companion — one that could guide, adapt, and stay out of the way when needed.

Available for full-time opportunities starting May '26

Photo

Let's Connect!

Happy to talk about all things design!

Logo

Made using template by @Framertemp 2025

Available for full-time opportunities starting May '26

Photo

Let's Connect!

Happy to talk about all things design!

Logo

Made using template by @Framertemp 2025

Available for full-time opportunities starting May '26

Photo

Let's Connect!

Happy to talk about all things design!

Logo

Made using template by @Framertemp 2025

Create a free website with Framer, the website builder loved by startups, designers and agencies.