Case study in progress — coming soon.
Ask Alfa — Driving
AI Agent Adoption
Product managers
Developers
ML engineers
Sales team
Stakeholders
Product Designer
Company
Role
Q2 2025
YEAR
Ask Alfa, Boosted.ai’s AI insights assistant, lets users query financial data in natural language to uncover patterns, compare performance, and manage risk.
Boosted.ai is a Toronto and New York based fintech company that provides AI-powered tools for institutional investors. The platform enhances investment decision-making by applying machine learning to financial data — helping portfolio managers, analysts, and advisors uncover patterns, manage risk, and improve performance.
Est. 2017
PROBLEM
After the initial rollout, Ask Alfa engagement metrics were below expectations. Users were hesitant to type prompts, unsure what the AI could do, and rarely returned after the first use.
Hypothesis
If we made prompt creation easier and demonstrated the value of AI through relevant examples and suggestions, users would be more confident and engaged — leading to higher adoption and retention.
Ask Alfa is an AI-driven insights assistant embedded in Boosted.ai’s investment research platform
Product

I owned end-to-end UX delivery, from IA to high-fidelity UI

Deliverables: wireframes, interactive Figma prototypes, and usability test documentation.
Information Architecture
Organized Prompt Library by user roles and workflows
[01]
Interaction Design
Defined logic for contextual prompt surfacing
[03]
Visual Design
Unified with Boosted.ai’s design system
[02]
Collaboration
Worked closely with PMs and ML engineers to align AI behavior and template logic
[04]
ECEXUTION
Deliver
Launching and measuring impact
Refined final designs, collaborated with PMs and engineers, and shipped improvements
to production. Post-launch data showed a 34% increase in retention and 48% more prompt interactions, validating the design direction.
Define
Framing the core challenge
Synthesized research findings into a clear design goal:
“How might we make AI interactions intuitive and valuable from the first prompt?”
This became the foundation for design exploration.
Develop
Designing for clarity
Ideated and prototyped multiple approaches, testing onboarding flows, guided prompts, and contextual examples. The most effective concepts — Prompt Library and Prompt Suggestions — emerged through iterative feedback.
Discover
Understanding the Adoption Problem
A look inside how we shaped Ask Alfa — from uncovering user pain points to designing a confident, AI-driven experience.
[sneak pEEk OF the process]
Analyzed usage data, conducted interviews with PMs and analysts, and mapped first-time user journeys to uncover why engagement was low.
→ Insight: users felt unsure what Ask Alfa could do and how to start interacting with it.
Double Diamond
🕵🏼‍♂️
🦸🏻‍♂️
PRINCIPLES
  • Reduce Friction – help users reach value in the first minute
  • Show, Don’t Tell – demonstrate capability through examples
  • Stay Contextual – guide users directly within their workflow
[ DETAILED PROCESS ]
DESIGN STRATEGY & PHILOSOPHY
KEY FINDINGS
  1. Users felt uncertain about what Ask Alfa could access or analyze
  2. The open text field created decision paralysis
  3. Existing onboarding didn’t connect to real user goals
  4. Most first-time sessions ended after one incomplete query
32%
dropped off after one session
46%
of users didn’t how to prompt
APPROACH
  • User interviews with PMs, analysts, and portfolio managers to capture frustrations
  • Usage analytics review to identify drop-off points and low-engagement patterns
  • Journey mapping of a first-time user to visualize friction moments
  • Heuristic audit of the Ask Alfa chat UX
[ DETAILED PROCESS ]
RESEARCH
STAGE 3: PERFORMING
IT CAN ALSO BE THE INITIAL DESIGN AND PLAN FOR USE, THEN LATER REDESIGN TO ACCOMMODATE A CHANGED PURPOSE, OR A SIGNIFICANTLY REVISED DESIGN FOR ADAPTIVE REUSE OF THE BUILDING SHELL THE LATTER IS OFTEN PART OF SUSTAINABLE

KEY SOLUTIONS

Prototype

Prompt Library
Curated, goal-based examples showing what Ask Alfa can do
Prompt suggestions
Curated, goal-based examples showing what Ask Alfa can do
To lower the learning curve and build trust, the design focused on turning uncertainty into guided exploration.
The result was two pivotal features:
KEY FINDINGS
  1. Users felt uncertain about what Ask Alfa could access or analyze
  2. The open text field created decision paralysis
  3. Existing onboarding didn’t connect to real user goals
  4. Most first-time sessions ended after one incomplete query
72 %
dropped off after one session
58%
prompts returned no result
81%
of users didn’t know what to ask
APPROACH
  • User interviews with PMs, analysts, and portfolio managers to capture behaviors and frustrations
  • Heuristic audit of the Ask Alfa onboarding and chat UX
  • Usage analytics review to identify drop-off points and low-engagement patterns
  • Journey mapping of a first-time user to visualize friction moments
RESULTS
Clear improvement in retention and engagement
Internal teams adopted the Prompt Library format for training and demos
+
+34%
retention among Ask Alfa users
+48%
increase in prompt interactions
−27%
drop in first-session drop-off
“Prompts feel intuitive and helpful to get started.”
“Now I actually know what it can do.”
Reflections & Next Steps
Lessons learned
  • Embedded guidance beats separate tutorial screens
  • Showing capability is more persuasive than explaining it
  • Progressive hints encourage learning while preserving user control
Next steps
  • Introduce analytics-driven, personalized prompt suggestions
  • A/B test more aggressive contextual hints
  • Expand library templates based on usage patterns