Slide 1
Slide 1 text
Keynote
Shunya kimura
Mercari / Vice President, CTO Japan Business
Slide 2
Slide 2 text
Shunya Kimura
・2017/9 establishing R4D, Mercari’s research
・2022/7 Vice President of Platform
Engineering
・2024/7 Vice President, Chief Technology
Officer (Japan Region), General Manager
(Japan Region Platform)
・2025/3 Vice President, Chief Technology
Officer (Japan Region)
・2025/7 Vice President, CTO Japan Business
Mercari / Vice President, CTO Japan Business
Slide 3
Slide 3 text
From 2018 to the present
Slide 4
Slide 4 text
Since 2018 to the Present of Mercari Group
● 出来事
○ 2017年11月：メルペイ設立
○ 2018年10月：英語化（グローバル新卒メンバー
44名入社）
○ 2019年2月：メルペイリリース
○ 2021年4月：メルコイン設立
○ 2021年10月：メルカリShopsリリース
○ 2023年3月：ビットコイン取引サービス提供開始
○ 2024年3月：メルカリ ハロリリース
○ 2024年3月：メルカリモバイルリリース
○ 2025年1月：メルカリNFTリリース
○ 2025年9月：グローバルアプリリリース
Slide 5
Slide 5 text
No content
Slide 6
Slide 6 text
No content
Slide 7
Slide 7 text
No content
Slide 8
Slide 8 text
No content
Slide 9
Slide 9 text
No content
Slide 10
Slide 10 text
No content
Slide 11
Slide 11 text
“We will fundamentally transform our
organization and products, with AI as
the foundation for everything.”
– Shintaro Yamada CEO of Mercari
Slide 12
Slide 12 text
Why Go AI-Native Now?
Slide 13
Slide 13 text
No content
Slide 14
Slide 14 text
Solid Achivements
Slide 15
Slide 15 text
Current Status: Solid Achievements
95%
Engineer AI Tool
Adoption rate
≒70%
Code Generation
by AI tool
64% UP
Development
Speed (YoY)
Slide 16
Slide 16 text
But We're "Just Getting Started"
However, we don’t consider this state to be
“AI-Native”
This is where the real transformation
begins.
Slide 17
Slide 17 text
Paradigm Shift “Human-Centric” to “AI-Centric”
Human-Centric
Based on human
limitations (time, focus,
processing power)
● 8-hour workday
● 2-day weekend
● 7-person teams
● weekly meetings
AI-Centric
Based on vision and
value propositio
Rebuilding Optimal:
● systems
● teams
● roles based on value
Slide 18
Slide 18 text
The AI-Native Worldview
Slide 19
Slide 19 text
AI as a Creative Partner
AI is a creative
partner and a
team member,
driving us toward
our mission.
この画像はこだわりな
い
Slide 20
Slide 20 text
What’s Important Before
Becoming AI-Native
Slide 21
Slide 21 text
The Most Critical Prerequisite for AI-Native Transformation
“Knowledge Management”
The key to making AI work is
providing the right context.
Slide 22
Slide 22 text
Why is “Context” is so important?
AI Agent ?
Low quality
output
Rework
(time lost)
Context AI Agent
High
quality
output
Effective
utilization
Without Context
With Context
background, decision logs, etc.
Slide 23
Slide 23 text
The Most Important Context: Decision Information
Without information like "What is the project's goal?" or "What
is permissible?", AI accuracy won't improve.
Slack
Decision Making Information
Docs JIRA Confluence
Slide 24
Slide 24 text
Our Approach
Discussion
Minutes
Structure
Database
Actionable
context for AI AI Agent
Stronger alignment between top-down and bottom-up
Accelerated company-wide decision-making
“Structuring Tacit Knowledge”
Slide 25
Slide 25 text
AI-Centric Development
Slide 26
Slide 26 text
AI-Centric Development: Current Challenges
Inconsistent
Prompt
Quality
Varying degrees of
AI utilization
among individuals
Gathering
Context
Inability to find or
provide the right
information
Quality of
Generated
Code
Increased review
costs and bug
risks
Lack of regulations for AI usage leads to inconsistent
quality across teams and individuals.
Slide 27
Slide 27 text
Agent-Spec Driven
Development (ASDD)
Slide 28
Slide 28 text
Project Double
Agent-Spec Driven Development (ASDD)
Enables anyone to achieve high-quality,
reproducible development through specs
optimized for AI Agents.
Slide 29
Slide 29 text
What is ASDD?
ASDD is More than Just a Spec
Slide 30
Slide 30 text
What is ASDD?
To make the entire team's implementation
a reproducible process.
API Definitions
Data Models
Process Flows
Test Scenarios
Implementation
Steps
Service Spec
Dependencies
Architecture
Prompts
Slide 31
Slide 31 text
Scope of ASDD
ASDD: Orchestrating End-to-End Development with AI Agents
Devlopment
● Backend
● Web
● Mobile
● UI Design
Quality
Assurance
● Auto QA
● Test case
● AI Review
GRC
● Risk
● Compliance
● Legal Review
● Security
Check
● CS
Slide 32
Slide 32 text
Overview of ASDD
Assets
PRD
Figma UI
Codebaase
Double Planning
Requirements
Short Agent Spec
Double QA
Test Cases
PJ Aurora
UI
Double Client
Agent Spec
(Client & FE)
Implementation
(Client & FE)
Double Backend
Agent Spec
(Backend)
Implementation
(Backend)
Double QA
Test
Implementation
Double QA
test
Implementation
Release
PJ Double
Slide 33
Slide 33 text
What is ASDD?
Project Aurora
Slide 34
Slide 34 text
Project Aurora
Automatically generate UI from Agent Specs
ASDD Prompt Aurora Agent
Auto-generated
UI using our
Design System
Slide 35
Slide 35 text
The Value of ASDD
Vibe Coding
Agentic
Development
● Handle more tasks
● Enable rapid trial and error
● Focus on solving difficult problems
● Focus on customer value
Slide 36
Slide 36 text
The Ultimate Form of Customer-Centricity
Being AI-Centric is the ultimate
form of being Customer-Centric
なにか画像が欲しい
な。。。
Slide 37
Slide 37 text
AI Task Force
Slide 38
Slide 38 text
AI Task Force
Drives Company-wide AI Transformation
Challenge
Speeding up the development process
alone does not improve the overall
time-to-release.
Slide 39
Slide 39 text
AI Task Force
We need to make all company-wide
workflows agentic.
Development [WAIT]
Legal
Review
[WAIT]
PR Review
[WAIT]
Security
Review
Release
Slide 40
Slide 40 text
AI Task Force
We need to make all company-wide
workflows agentic.
Development [AI Agent]
Legal
Review
[AI Agent]
PR Review
[AI Agent]
Security
Review
Release
Slide 41
Slide 41 text
The Pioneer of Agentic Work: Proaject Socrates
Socrates: Internal BI AI Agent
Slide 42
Slide 42 text
The Pioneer of Agentic Work: Project Socrates
Request data retrieval and
analysis using natural language
Anyone can access data without
complex SQL queries
A company-wide realization that AI can perform difficult tasks,
including decision-making.
Slide 43
Slide 43 text
Launch of the AI Task Force
Launched AI Task Force in July 2025
Accounting/Audit/Credit/Logistic/BI/IR/CorpDev/CoporateIT/CorporatePlanning/
CSTns/EngineeringOffice/Governance/HR/Kashima/Legal/Marketing/MS/PMO/P
ublic Policy/R4D/Risk/Sales/Security/Treasury/
Corporate domain
AI Product/Engineering/PdM/UIUX
Service Development Domain
Slide 44
Slide 44 text
Launch of the AI Task Force
Slide 45
Slide 45 text
AI Task Force: Responsibilities
3 Core Responsibilities
Take inventory of all business processes
Create AI transformation vision and roadmap
Execute on AI transformation according to the roadmap
1
2
3
Slide 46
Slide 46 text
AI Task Force: Achivements
4000
workflows
33 domain’s
roadmap
Quick
wins
Slide 47
Slide 47 text
Lessons from the AI Task Force
Cross-Domain Synergy
Engineers who moved
into non-tech domains
(e.g. Legal, Finance) came
up with innovative ideas
that led to improvements
by challenging the
existing assumptions.
New Growth for
Engineers
Tackling unfamiliar
domains led to new
skill sets and boosted
motivation.
Slide 48
Slide 48 text
Case 1:Enhancing Fintech CS
Quality with AI Role-Playing
Slide 49
Slide 49 text
Case 1: Enhancing Fintech CS Quality with AI Role-Playing
We used to conduct role-playing between people.
Now, AI is our training partner.
Practice Screen
We simulate actual vocal conversation
between the customer and the AI on the
CRM.
Evaluation Screen
The AI provides feedback based on
the conversation.
Slide 50
Slide 50 text
Case 2: Mercari Review Assistant
Slide 51
Slide 51 text
Case 2: Mercari Review Assistant
Slide 52
Slide 52 text
Case 2: Mercari Review Assistant
Slide 53
Slide 53 text
Future Vision
Beyond AI Transformation
Slide 54
Slide 54 text
Our Goal Beyond AI-Native Transformation
Circulate all forms of value to unleash
the potential in all people
デザインむずい。アン
リーシュ感出したい。
Slide 55
Slide 55 text
The Challenge of Global Expansion
Vision
A Global Marketplace and
Fintech Service
Slide 56
Slide 56 text
The Challenge of Global Expansion
Challenge
Global expansion was limited by human resources for
localization and operations
Solution with AI
Augmenting individual capabilities with agents to
achieve global expansion with a realistic number of
people.
Slide 57
Slide 57 text
Moving away from a
mindset of resource
limitation to a world
where we can achieve
what we want to
achieve
Slide 58
Slide 58 text
Toward Ultimate Customer-Centricity
By building on a foundation of AI,
we can focus more deeply on customer value.
This is the "AI-Native Company" we aim to be.
Slide 59
Slide 59 text
Session紹介
Slide 60
Slide 60 text
The Future of User Experience
- Mercari MCP -
Slide 61
Slide 61 text
Mercari MCP
Application
Layer
Mercari
MCP
Mercari tools and apis
- Authentication
- Search
- Listing
- More coming
soon
End Users
ChatGPT is a product of OpenAI, L.L.C.
Claude Code is a product of Anthropic PBC.
Claude
Code
Slide 62
Slide 62 text
Demo Video
Search in
ChatGPT with
Mercari MCP
Slide 63
Slide 63 text
Mercari MCP Roadmap Phases
P1 P2 P3
Whitelist Only Full Release Expand Tools
MCP accessible to
applicants only.
Validated
applicants will be
whitelisted
Anyone can try
with applications
that support MCP
Continue adding
more tools and
APIs (e.g. more
search and listing
capabilities,
logistics, analytics,
payments.)
Slide 64
Slide 64 text
Signup
Sign Up today, try
Mercari MCP in
ChatGPT and
Claude Code.
When it’s ready,
we will inform you.
Slide 65
Slide 65 text
Thank You!