Earning Trust in AI Predictions  
full ux case study link

Background
Predictions & Insights was an AI-powered feature within Crunchbase company profiles. At launch, users could view predictions alongside their supporting context, including a plain-language prediction, timestamp, contributing factors, likelihood or timeframe, tooltips, feedback entry points, and additional details. But readability was not enough. Users could evaluate the prediction, but they could not yet evaluate the model behind it.

This case study focuses on the post-launch trust features we designed for Predictions & Insights:
Prediction Credibility UI: surface historical model performance metrics.
Win Predictions: surface confirmed outcomes that Crunchbase correctly predicted.
AI-Powered Company Header and Contextual Summaries: introduce AI-generated intelligence at the top of the profile, with its own set of trust and transparency decisions.
P&I Feedback Modals: give users a direct path to flag inaccurate data and close the loop between user input and model quality over time.

My Role
I was the Lead Product Designer for the post-launch evolution of Predictions & Insights, partnering with Product, Engineering, Data Science, Sales, and Sales Engineering. I defined the trust and transparency framework, designed the user experience for model performance, evidence, grounding, and feedback, and translated post-launch research into product improvements. The work required balancing user needs, model capabilities, and business priorities to determine what evidence could be surfaced responsibly and how credibility could be communicated throughout the experience.

The problem: the product explained the prediction, not its reliability
Users understood what the prediction was forecasting, but lacked the evidence needed to evaluate the model behind it. Predictions included supporting context, but nothing about historical performance, confirmed outcomes, or track record. Users could inspect the prediction, but not assess its reliability.

Engineering had built a Live Predictions Dashboard that Sales and Sales Engineering used on customer calls to demonstrate model accuracy, and it was effective at converting prospects and supporting renewals. None of that evidence existed in the product itself. Self-serve users saw the same predictions without the track record behind them. The opportunity was to bring that evidence into the product experience, where it could build trust at scale rather than one call at a time.

Post-launch research: what users still needed
Research confirmed the redesign was directionally right, but predictive content still lacked credibility cues.

What users validated: The interface felt cleaner and more modern. One-page scrolling was faster than the old tabbed experience, and the left navigation improved profile exploration.
What still needed work: Predictive content needed stronger credibility cues. Score definitions needed in-product explanation, not just tooltips. Financial data needed more prominence.
What came next: These findings shaped the next wave of work: tailored feedback modals, Prediction Credibility UI, Prediction Win banners, AI Overview, and AI contextual summaries.

"If you could give me some analysis I can click into, I'd feel more confident in the score, instead of just giving it to me vaguely."
"With the IPO and acquisition prediction, I still want to know how it's calculated, even though it's really interesting and valuable to me."

Research synthesis
The launch experience had the right foundation but solved only half of the trust problem. Evidence for each prediction existed: Contributing Factors and Rationale explained why Crunchbase made the claim. Evidence for the model did not. There were no confirmed outcomes, no performance data, and no visible track record — users had never seen a Crunchbase prediction come true.

A system for building trust
Trust in AI is not a single UI pattern. It required a system of product levers that let users evaluate the prediction, validate the model, challenge the output, and decide what to do next.

Below is the framework we used to instill trust in P&I offerings: 

Surfacing model accuracy
Prediction Credibility UI made model performance visible in the product. Rather than showing only the prediction claim, the UI surfaced scoped performance data — 93.7% recall for a Funding Prediction segment, with 2,231 confirmed and 150 missed predictions — so users could judge whether Crunchbase had been reliable in a relevant context. The design challenge was translating model behavior into a credibility cue that non-technical users could read: every metric had to be clear, scoped, and carefully worded, without oversimplifying what it measured.

Prediction Wins: confirmed outcomes
Performance metrics are useful but abstract. Confirmed outcomes are concrete. Prediction Win banners surfaced moments where Crunchbase predicted an event that later happened — when a funding round, acquisition, or IPO was confirmed, the outcome appeared directly on the card. The banner did not explain the model. It proved the model had been right before.

Improved P&I feedback modals
At launch, Predictions and Insights shared one general feedback path. Users could select a reason, but the modal collected too little context to make feedback actionable. Post-launch, we designed tailored feedback paths for each. The revised modal added a description field, a supporting-evidence URL, an explanation of the review process, and prediction-specific context around data points that could affect the model, such as funding history, employee headcount, estimated revenue range, and key leadership hires.

This turned feedback from a support channel into part of the credibility system: users who disagreed with a prediction could challenge it and supply better evidence.

AI Overview: a generated summary of company performance
The credibility work extended beyond prediction cards. Users needed help forming a point of view without assembling it themselves, so we introduced an AI-generated company summary in the header. The governing principle: AI can summarize, but trust comes from grounding. Every summary had to connect back to visible source data, so the overview read as synthesis of the profile rather than unsupported AI text. The same pattern extended to contextual summaries for News and Competitors.

Impact and current status
The work created a credibility system that now extends across multiple Predictions & Insights surfaces. At launch, predictions were understandable but not yet credible. The follow-up work built the missing trust layer: model performance, confirmed outcomes, structured feedback, and grounded AI summaries.

Live in production: Prediction Credibility UI for Funding Prediction; Prediction Win banners; updated feedback modals.
In engineering development: AI Overview; AI contextual summaries.

Reflection
Trust in AI is not built through confident language and polished UI. It is earned through evidence: proven performance, confirmed outcomes, accountability, and grounding.