3
Empathize
Search expected keywords. Users expressed situations.
In this section
Research foundation
Key insights
Eventbrite
2026
0→1 AI Feature
Conversational AI Systems Design
Professional
Design Lead
Product Strategy
Opportunity
Framing
Experiment Design
Interaction Design
Statsig
Amplitude
FIGMA MCP
Cursor
Claude Code
Skills.md
Eventbrite's search was under pressure. Usage was declining on the app, competitors were gaining ground in event discovery. At the same time, AI was reshaping where and how people expected to interact with products — users were increasingly accustomed to describing intent, not translating it into keywords.
The system required precision. Users expressed ambiguity. And when a conversational UI was introduced, expectations shifted instantly — without the system being capable of meeting them.
Find out whether natural language search could help Eventbrite reclaim ground in discovery — improving how users express intent, surfacing more relevant results, and driving measurable impact on conversion.
Understand whether users would engage with NL search at all, what they would type when given the opportunity, and what expectations they brought from AI tools they already used in daily life. Identify the gap between Eventbrite's current capabilities and what users and internal teams believed AI should be able to do.
Users were already treating ChatGPT and Copilot as planning concierges. They brought those expectations in app — without the platform having the means to meet them yet.
Eventbrite wasn't a daily-use product. That limited the behavioral data available to personalize meaningfully — AI features had to earn trust faster, with less to work from.
Stakeholders agreed AI was imperative for discovery but many did not believe Eventbrite had the technology to deliver it. The design problem wasn't aesthetic but infrastructural.
Previous flow — Search & filter
Experiment 1 — Designed to learn, not to launch
Experiment 2 — “Honey, I’m home”
Experiment 3 - A house on pillars
Paid buyers went up +3.78%, paid orders by +3.73%. At Eventbrite's scale, this is meaningful volume — and validated that NL-augmented discovery was worth pursuing.
The design work wasn’t building the feature but figuring out which surfaces benefited from it and which didn't. That's a systems problem, not a UI problem.
Users don't experience a model limitation — they experience a bad interface. In AI products, the model's capability and the design are inseparable.