INFINITE PREDICTIONS GROUP (IPG)
ROLE
Founding Product Designer
SKILLS
Product Strategy
Systems Thinking
Cross-Functional Leadership
TIMELINE
3 weeks
OVERVIEW
Building AI simulations of company target users, so product managers can capture insights at 1/100th of the original time.
With a model based on real human data, IPG allows PMS to continuously engage with simulated human agents and make faster, more informed decisions.
THE SOLUTION
Using real human data, generate thousands of people at once, and interact with them to gain insights.
#1 FIND PATTERNS.
#2 TALK TO USERS— ASAP.
#3 UNCOVER DEEPER INSIGHTS.
#1 FIND PATTERNS.
CURRENT SPACE
Small product teams have never had more data, and yet they know less than ever about their users.
Even the best PMs rely on fragmented, biased, or stale signals to make decisions. Traditional user research is slow, expensive, and limited to a tiny fraction of the actual user base.
SO WHAT?
Access to users — and the ability to learn from them quickly — is structurally scarce and operationally heavy.
Every product team today faces the same systemic limitation: they can only talk to a fraction of their users, a fraction of the time.
Only 1/5 of users
20%
40%
60%
80%
100%
THE PROBLEM
User research is expensive and time-consuming for small teams, leaving many PMs to rely on proxy or intuition.
THE GOAL
Enable PMs to access user-grounded insights continuously without requiring dedicated research teams or long timelines.
THE GUIDING QUESTION
How can we seamlessly eliminate research bottlenecks so PMs can move faster with confidence?
AUG
APR
MAY
JUN
JUL
LOW CONFIDENCE
TIMELINE BOTTLENECK
USER RESEARCH
DISCOVERY PHASE
VALIDATION PHASE
DEFINITION
INTERNAL
RESEARCH
INSIGHT
PMs don't simply want mass data— they need the insights that matter. But how do they get there?
How do we design a workflow that returns insights quicker than traditional cognitive processes?
THE PHILOSOPHICAL PROBLEM
Are we outsourcing our autonomy to LLMs?
LLMs may remove a layer of human curiosity. If you treat AI as a shortcut for answers every time, and skip the thinking, it’ll dull curiosity and deep learning about users over time.
LIGHTBULB MOMENT
Real PM workflows are nonlinear. LLMs allow PMs to generate data and explore them however they want, furthering autonomy.
Mystery
Heuristic
System
Insight
Knowledge Funnel
PRODUCT THINKING
ITERATION #1
Categories only worked for a bounded problem space.
Our initial MVP was built for college applications, where the primary goal was exploration rather than decision-making. What worked for exploration became a liability when teams needed specifics.
ITERATION #2
Traditional filtering was too heavy-weight.
A classic, dashboard-style filter system required PMs to think like analysts. It created friction and bottle-necks in their workflow.
ITERATION #3
Pure clustering of patterns felt arbitrary and untrustworthy.
Clusters emerged, but PMs couldn’t see why. Without transparent logic, the grouping felt like a black box, or discreditable. Why were specific patterns more important than others? I also wanted to design for equity and account for potential bias.
ITERATION #4
A single chat interface felt like a black box and lacked ethos.
A lone “ask anything” box gave no sense of structure or grounding. It offered answers, but not the transparency or credibility PMs needed.
DESIGN PRINCIPLES
BALANCING USER INTENT AND AI COGNITIVE LOAD
How might we help product managers trust insights enough to act on them, without constraining their autonomy?
Keep understanding stable.
By keeping outputs about core insights stable, while allowing exploration to expand, PMs can act with confidence without being boxed into a single interpretation.
Dynamic graphs are one example of a system component designed to absorb change, while the summary remains intentionally fixed, so product managers can trust what they’re seeing even as context shifts.
Filters scale through a consistent interaction model, allowing teams to pursue more complex lines of inquiry without redefining the system or introducing new friction.
Make the surface feel credible.
Every insight is paired with traceable evidence: quantitative signals, source links, and methodological context— so users can understand not just the outcome, but the reasoning behind it.
Quantitative numbers and symbols for ethos
Interactive links let users trace their insights
Micro-animations that feel human.
Human-anchored design means interactivity, and movement. Almost like it's talkin to ya!
Movement represents the act of "listening"
Movement represents the act of "paying attention"
Movement represents having a "presence"
FEATURE DEEP-DIVE
FEATURE #1: INTERVIEW CAMPAIGN CREATION
CONTEXT-AWARE QUESTION GENERATION
Kickstart research in seconds.
PMs describe their goal, and the system automatically generates targeted, context-aware interview questions grounded in user behavior, evidence, and most importantly: your goals.
REVISE, REFINE, FOLLOW-UP
Edit, refine, and deepen your questions with a single prompt.
They can refine, adjust tone, or add follow-ups — ensuring every question maps back to the insight they’re trying to uncover. Recommendations from artificial intelligence are not primary, but rather, a secondary suggestion— for a further sense autonomy for PMs.
ITERATE SMARTER AND FASTER.
Generate a complete interview guide in an instant.
PMs have a research starting guide in only seconds, without the blank page.
FEATURE #2: TALK TO YOUR USERS
DYNAMIC CHAT INTERFACE FLOW
Receive instant answers from the simulated agents.
After the interview, users can talk to the interviewed data-base, or talk to specific cohorts of similar patterned individuals.
HYBRID FILTERING SYSTEM
Segment the users and patterns which you want to interact with.
Users can talk to the interviewed data-base, or talk to specific cohorts of similar patterned individuals,
GRANULARITY WITHIN DATA
Zoom into any segment in one click— the dashboard shifts dynamically according to PM needs.
Instead of overwhelming PMs with hundreds of filters, the system reveals insight layers progressively. Each step gets more specific only when PMs ask for it.
USER-LEVEL DEEP DIVES
Truly— any user.
PMs can click any individual user in a cohort to inspect their personal habits. It takes what would normally require hours of 1:1 interviews and condenses it into a deeply contextual profile.
Reflections
Is Traditional UI Dying as Agentic UX Rises?
We’re building something that adapts to user context and autonomy, but honestly: the hard part isn’t the AI. It's knowing when to stay out of the way. Too much adaptation and people feel like they’ve lost control. Too little defeats the point.
As technology becomes more omnipresent, the role of the designer will evolve from designing screens to defining moral guardrails.
We are inherently shaping the moral guidelines around humanity interacts with machines— how can I ensure a strong foundation of morals and ethics as I design around data?
Founder first, designer second.
I had to have a strong vision going into this role. Being able to translate "designer language" into "product language" helps us (as designers) create more space for the users, and drive further impact.