Google · 2025 – Current · In active development The conversational analytics platform, powered by AI-Agent
The conversational analytics platform, powered by AI/ML
Designed an AI-powered conversational analytics experience that helps engineers explore complex manufacturing data through natural language, transforming how insights are discovered, validated, and acted upon.
Lead Product Designer · 0→1
Designed an AI-powered conversational analytics experience that helps engineers explore complex manufacturing data through natural language, transforming how insights are discovered, validated, and acted upon.
Google | 2025 – Current
48h → 80%
Prototype-first: working prototype of [3 core flows] in 48 hours, before any PRD.
50%
Faster design-to-development handoff: prototypes built on the production stack (AngularJS) double as the engineering spec.
12 wks → 2 wks
Concept validation cycle: prototype-first lifecycle vs. our previous PRD-first process.
Conversational Analytics enable engineers to ask questions in natural language and receive contextual, data-backed insights without navigating multiple tools or dashboards.
Agentic Insight Exploration guides users through multi-step analysis: specialized agents collaborate behind the scenes, surfacing follow-up questions and pointing to the next area worth investigating.
“Nexus AI” is a placeholder name for an NDA-protected product. Interface and data shown are illustrative.
Ask questions. Get insights.
No Analytics dashboards required.
Why conversation
Conversational Analytics
Ask questions. Get insights. No dashboards required.
Conversational Analytics lets users explore complex data through natural language instead of filters, charts, or queries. By turning analysis into a dialogue, it delivers contextual, actionable insights faster and with less cognitive effort—matching how people actually think and make decisions.
As AI capabilities advance, conversation is becoming the default interface for analytics and enterprise workflows.
My Role
Lead Product Designer. Owned the 0→1 AI Product Strategy and End-to-End Design (Visual/Interaction), translating raw, early-stage concepts into a functional AI product.
Team
Sole designer on a 10+ engineering-heavy team of TPMs and AI/ML engineers.
Timeline & Status
2025 – Current
Design Challenges
- How might conversational AI support complex analytical reasoning without oversimplifying expert workflows?
- How can agentic systems guide users while preserving user autonomy, trust, and transparency?
- How can conversational UX integrate into existing enterprise tools without disrupting established workflows?
Overview
Modern manufacturing analytics involve navigating highly fragmented data across multiple systems, making insight discovery slow and cognitively demanding.
As the Product Designer on this initiative, I designed an agentic, conversational UX layer on top of existing analytics workflows, so engineers can explore data through dialogue rather than manual configuration.
The design centers on human-AI collaboration: the AI synthesizes data and suggests next steps, while engineers stay in control of interpretation and decisions.
This work builds on earlier AI summarization efforts and marks the shift from static insights to interactive, exploratory analytics, setting the direction for future AI-powered manufacturing experiences.
Three patterns from the work
Challenge 01 · Fits existing tools
One workflow replaces dashboard sprawl
Centralizes fragmented data, tools, and intent into a single conversational workflow: engineers move from question to insight to action without switching between tools.
Challenge 02 · Control & trust
Agents that show their work
While agents run a multi-step study, the UI narrates each step in plain language and keeps it interruptible. Users can redirect the plan mid-run instead of waiting for a black-box result.
Challenge 03 · Expert reasoning
Progressive depth, not simplified answers
Every answer opens with the conclusion, then lets engineers unfold the evidence: clusters, distributions, and the raw records behind them. Output formats were defined through Golden Set validation with domain experts, so each answer arrives as the text, chart, or table that reads fastest.
See the full story
The full case study is confidential and shared on request.
Happy to walk you through it.
Works
*This website is best viewed on desktop.
2025 Bryan Oh • Product Designer 😉
© 2026 · Forged in pixels, shaped by chaos—powered by bubble tea 🧋
“The technology we design to make life easier should not only understand our needs but also recognize our struggles, reminding us that true innovation begins with empathy.”
"AI-driven UX should be empathetic, empowering users with seamless agentic workflows that adapt to their needs”