Kakao i Dataverse
Overview
AI Data & Contents Management SaaS Platform
Company
Role
Product Manager
Product Designer
Deliverables
Product Strategy Roadmap
UX Design
API Architecture
Project Date
Mar 2022 - Aug 2023
6 Phases / 18 Sprints
Kakao i Dataverse is a SaaS platform for managing content & data, using Retrieval-Augmented Generation (RAG) to integrate metadata and vector searches for AI outputs.
Evolving from B2B2C projects, it enhances bot services by generating responses from data, aiming to allow non-technical admins to operate AI services with minimal engineering effort.
Context & Background
Problem Statement & Define Needs
A key issue was that bots and data administrators struggled to manage large volumes of data and found it difficult to use that data in bots or services.
Hyphothesis : HMW Approach
“How might we enable bot managers to easily manage, operate,
and improve both legacy bots and new generative AI-based bots?”
User Research
5 Stakeholders Interviews
Kakao AI Lab LLM Model Researcher
Kakao Search Engine Lead Engineer
Kakao AICC Service Product Owner
NH Investment Chatbot Manager
Hey Kakao Customer Service Agent
3 Proof-Of-Concept Projects
Integrated generative AI responses into the stock bot
(Hey Kakao and Kakao Work)Implemented generative AI responses functionality in AICC SaaS.
Implemented AI-driven answers for NH Investment & Securities' stock bot.
4 Defined User Needs
Codeless data and content storage with real-time integration for bots and services.
Provision of a private repository, allowing bots to execute processes while exempting data from model training.
Real-time analytics to track user data flow, identify drop-off points, and monitor conversions.
Role-based access control (CRUD permissions) for different team members.
XFN Collaboration : Communication Guidelines
To align on project goals and enable timely, transparent updates across teams, we established clear communication guidelines:
Share issues and decision points via project channel with @all mentions to ensure visibility
Request follow-up meetings without delay when further discussion is needed
Review and respond to questions or requests before the next daily scrum
User Testing : POC Projects
Testing with real end users is critical in B2B SaaS development.
Since access to users depends on partner adoption, we launched Proof of Concept (POC) projects to bring partners onboard and ensure user-centered product validation.
Proof of Concept Project:
Stock Knowledge search and Gen AI Bot
We conducted POC projects to test key quantitative and qualitative metrics, continuously collecting and analyzing user data.
Time on Task
Success Rate
Process Satisfaction
Data Transaction Stability(Amount, Speed)
Number of Service Connections
Test Feedback
CSV bulk upload would be helpful instead of full data integration.
“
Tooltips for key features would help non-developers.
“
“
”
”
Metadata setup was easy,
but deployment was complex.
”
Service Flow
Kakao i Dataverse can be directly served as a REST API for user’s own service
Build their own custom search engines
Independently connect and manage their data and content
Retrieval-Augmented Generation (RAG) capabilities through the integrated search engine and LLM
Outcomes
Kakao i Dataverse
A Low-Code based SaaS Platfrom for storing, managing and integrating Data&Content, with the potential to expand into Generative AI
Integrated Dashboard
Effortlessly track all data and content in one view
Monitor real-time data status with card views.
Quickly access detailed data with a single click.
Users can easily understand through well-placed tooltips
Easily check key status changes at a glance
Check data and content sync expiration through lists and status indicators.
Quickly understand which bots and services data is connected to, its expiration date, and current status.
UX Flow-based Data Analytics
Visualize user flow at a glance with a Sankey chart
Visualizes how users access and interact with data step by step, clearly revealing content and data usage patterns, as well as points where engagement drops.
Hover to view summary statistics without leaving the page.
Charts and graphs help provide clear insight analysis
To intuitively understand trends in large datasets, charts and graphs tailored to each insight are essential. Supports line graphs, pie charts, bar charts, and more for easy analysis.
Search Index & Meta Data Management
Create custom search indexes & rules to operate your own search service
Keyword and morphological data can be easily uploaded in bulk with a simple click of a button.
Search rules can be effortlessly created by selecting representative datasets and adding bubbles.
Generative AI Management
Connect and manage bots with data on a single page
Link bot via App Key to manage multiple bots with data.
Separate deployments for test and production environments allow safe and thorough integration testing before launch.
Supports data integration for AI, prompt setup and data annotation
Stored data can be easily connected to structured, vector search & LLM model.
Prompt testing allows user to preview responses in advance.
Data annotation supports management Gen AI Bot.
Data & KPIs
To ensure service sustainability, we defined and managed KPIs based on user behavior data, data transactions,
and the number of connected services.
4
User Behaviour Metrics
For Enhancing User Experience
Button Click Amount
User Flow(Success Rate): 30% Increased
Session(Time on Task): 20% Reduced
Voice of Customer(Real Feedback)
1,000,000
Monthly Data Transaction
Platform Engagement
10 Partners with various Domain
Mobility(Hyundai Motors)
Finance(NH Investment ....)
Retail (GS Retail, Daiso...)
Public (Sejong Self Governing City)
IoT (Samsung, Komex ...)
80+
Connected Bots & Services
Expanding User Engagement
60 Hey Kakao platform bots
10+ Partner’s bots
10+ Partner services
NEXT Projects
Hey Kakao
AI Voice Assistant Platfrom
Mobile App, AI Speaker, IoT Control Panel, Car Embedded AI