Amoeba AI

AI Data Lab

A neuro-symbolic AI platform that acts like a data scientist embedded inside your go-to-market team — designed for marketers who need actionable insights without relying on a dedicated data science team.

22% → 8%
Abandoned Query Flows
2.3×
Weekly Active Users
60%
First-Query Setup Time Cut

Context

Amoeba AI is a neuro-symbolic AI platform that acts like a data scientist embedded inside your go-to-market (GTM) team. It is designed for businesses and professionals who need actionable insights from their data without relying on a dedicated data science team.

Problem

Currently, there exist too many ways to make an exploration. There is no clear distinction between explorations that are led by Amoeba and a pure custom exploration by the user. Most marketers are not technical, and are unsure how to start exploring their data.

Onboarding analysis showed that 22% of query construction flows were abandoned halfway through because users felt lost.

Solution — Data Lab

Users can create data explorations to uncover insights in their data. Users will chat with Amoeba, who behaves like a data scientist. Key deliverables:

  • 2 types of explorations: Amoeba-driven and User-driven
  • Chat field as landing page, emphasizing Amoeba-driven explorations
  • Latest Explorations section with easily accessible exploration projects
  • Conversational chat interface and features for users to engage with Amoeba and capture insights
  • Amoeba suggestion of relevant sources based on neurosymbolic processes

Results

60%
First-query setup time cut (Usability)
2.3×
WAU within first release window (Retention)
22%→8%
Abandoned query flows (Error Reduction)
9→4
Avg clicks to configure an analysis

Interface now serves as the foundation for Amoeba's upcoming multi-agent orchestration UI.

Launched Product

Launched Product Demo — Interactive Data Lab interface walkthrough.

Understanding the Data Lab & My Role

The purpose of Data Lab is to easily design, refine, and test marketing experiments without requiring a data science background. Validate strategies and creative ideas in a controlled, risk-free environment to see what works before committing resources.

My role ranged from product discovery to creating the flow of creating an exploration — to bookmarking insights and monitoring specific explorations.

Competitive Analysis

In order to combine both core AI chat functionalities and Marketing & Data discovery features, I reviewed leading AI analytics and task management tools.

Competitive Analysis Chart

Key takeaways:

  • Analytical AI tools utilize side panels with tabs (insights, notes, outline, etc.)
  • Conversational vs Research-focused AI agents (Gemini vs Perplexity)
  • Encouraging users to Custom Query vs using a Prompt

User Flow

User Flow Diagram

Product Discovery & Brainstorming

After creating low fidelity wireframes and critiquing them with the Product Manager and Engineers, I improvised and created mid fidelity wireframes to prepare for user interviews.

Iterations of Chat Interface Page with Insights, Bookmarks, and Sources
Iterations of Chat Interface Page with Insights, Bookmarks, and Sources.
Iterations of Data Lab Landing Page
Iterations of Data Lab Landing Page.

Customer Interviews

To understand the core pain points, I interviewed two customers who hold different roles.

DANIEL — Head of Marketing Team
  • Appreciated the open, spacious design for managing complex data.
  • Requested better organization of recent explorations, suggesting categorical grouping.
  • Proposed a monitoring feature for timely updates.
ALEX — Marketing Operations Manager
  • Wanted clear differentiation between Amoeba-led and custom explorations.
  • Preferred a chat-first interface.
  • Recommended color-coded pills to visually separate prompt types.
  • Suggested organizing explorations with custom tags.

These insights directly informed design priorities: clarity between exploration types, streamlined chat-based workflows, and enhanced organization and recall of insights.

Insights → Features

After rounds of interviews and iterations, I consolidated these key features for the Data Lab.

Monitoring

Subscribe to explorations, and receive a digest everyday to your preferred platform.

Bookmarking

Save important responses from Amoeba within-chat, and jump back to it later.

Summary & Insights

Amoeba generates summaries and insights based on user-Amoeba conversation. Allows manual refresh.

Auto Sources Integration

Amoeba is intelligent and selects sources for the user. Provides reasoning if asked.

Final Designs

Data Lab Landing Page Final Design 1 Data Lab Landing Page Final Design 2
Data Lab Landing Page — Emphasizing guided exploration prompts over a blank chat interface.
Chat Interface Final Design 1 Chat Interface Final Design 2
Chat Interface — Interactive workspace for bookmarking insights, exploring sources, and communicating with Amoeba.

Deep Dive into the Landing Page Challenge: Prioritizing Guided Prompts Over Custom Chat

The Data Lab's landing page presented a core design tension. While most AI applications feature a prominent custom chat field, Amoeba's primary value lies in its "Amoeba-led prompts" — curated starting prompts for data exploration.

Our challenge was to steer users toward these valuable prompts without completely hiding the familiar chat function.

After multiple customer interviews and design iterations, I came down to the version (right side) with an emphasis on Amoeba prompts, a clean interface for a data-heavy product, and information hierarchy.

Landing Page Comparison — V1 vs Final
Landing Page Final — Annotated

Prioritizing Amoeba-driven guided prompts is central to our business value proposition — it's what differentiates Amoeba in a crowded analytics market. By surfacing intelligent, context-aware prompts, we empower nontechnical teams to uncover critical insights without deep technical expertise. This unlocks broader adoption across organizations and drives tangible customer ROI, making data exploration accessible, actionable, and scalable for every business user.

Additional Designs

In addition to the Data Lab, I also worked on end-to-end design and implementation of other features that solved key pain points.

Nucleus — Progress Tracking

Nucleus — Screen 1 Nucleus — Screen 2

Pulse — Executive Reports & Updates

Pulse — Screen 1 Pulse — Screen 2

Takeaways

If I had more time, I want to work on prototyping interactions and spend more time with engineers to implement smoother transitions between tabs and pop-ups. Since the Data Lab is still in beta, I want to continue to gather user feedback from their usage (misclicks, time it takes to start an exploration, etc.).

Nonetheless, I appreciated this experience of working on an AI product as well as the close-collaboration with engineers. It was super rewarding when I saw my designs go from Figma to staging and ultimately production.

01

Designing an AI Product

Designing for AI required more than just a chat box. Research showed a blank prompt intimidated users, so my focus became designing the entire conversation. By using guided starters, query examples, and helpful empty states, I onboarded users to the AI's capabilities. A successful AI interface must actively guide the user and manage expectations from the very first interaction.

02

Designing a B2B SaaS Product

The core challenge was designing a data-heavy product for a non-technical GTM audience who needed answers, not raw data. My design approach prioritized actionable insights over complexity, using goal-oriented dashboards and clear AI responses. Effective B2B design must translate complex system data into clear, strategic actions for the user.

03

Product Discovery & Testing with Engineers

Many bugs and issues were discovered during user acceptance testing sessions and sprints with engineers. Working directly with engineers honed my ability to ship rapidly, iterate with agility, and resolve usability issues before launch — accelerating production by up to 40%.

04

Value of Customer Interviews

In interviews, users often requested out-of-scope features. Instead of dismissing these tangents, I learned to see them as signals of deeper pain points. Always listen for the underlying "why" behind a user's requested "what." This practice was crucial for maintaining a focused product vision while still solving the right core problems.

Results & Impact

Launching the Data Lab feature for Amoeba yielded strong initial momentum and validated key design choices:

9→4
Clicks to configure analysis (Workflow Efficiency)
60%
First-query setup time cut (Usability)
2.3×
WAU in first release window (Retention)