​Description

​AI-assisted software development is rapidly evolving beyond smart auto-complete and vibe-coding simple apps.  The emerging AI-native development process is a structured, human-mediated, multi-agent workflow, where agents are used across your full codebase and across the full end-to-end development process.

​Applying AI-native techniques to enterprise-class projects introduces substantial challenges around context engineering, agent memory management, code stability, and defining the relative roles of agents and humans.  In this workshop-style session, Kerry Champion explores how spec-driven development (SDD) and multi-agent human-in-the-loop workflows can address these concerns.

​Drawing from real-world experience, Kerry will illustrate broadly applicable lessons learned by walking through the use of two specific tools: BMAD (an open source framework rapidly growing in popularity) and CodeSpeak (the LLM-powered programming system from the creator of Kotlin).   Attendees will see state-of-the-art approaches for decomposing complex engineering work, coordinating multiple AI agents, and maintaining efficient human oversight.

​This event is aimed at engineers, technical leaders, AI tooling practitioners, and founders interested in AI-native software engineering workflows, developer tooling, agentic systems, and large-scale AI-assisted development.

​​Agenda

​18:00 Doors open

​18:30 - 19:15 Part 1 - Top-Down AI-native Development with BMAD Tooling

​19:15 - 20:00 Part 2 - Bottom-Up AI-native Development with CodeSpeak Tooling

​20:00 - 21:00 Networking

​21:00 Doors close

​Talk 1 - Top-Down AI-native Development with BMAD Tooling

​Kerry will demonstrate how to set up AI coding agents for success. The session will cover practical techniques for building long-term memory artifacts that provide the levels of decomposition and synthesis required by AI agent context window constraints.  Lessons learned from this demonstration apply beyond BMAD to the growing list of similar tools and frameworks.

​Topics include:

• ​Spec-driven development.

• ​Multi-agent orchestration workflows.

• ​Human-in-the-loop decision making.

• ​Context sharding and bounded-context design.

• ​Structured artifact pipelines.

• ​AI persona specialization and advanced elicitation.

• ​How to apply this to mixed greenfield and brownfield environments.

​Talk 2 - Bottom-Up AI-native Development with CodeSpeak Tooling

​In this session, Kerry explores how tools such as CodeSpeak are defining a new level of abstraction above traditional programming languages.

​Attendees will learn how to present a system as a higher-level specification reviewable by a broad set of stakeholders.  Edits to that specification can directly drive reliable updates to the underlying codebase. This maintains consistency and traceability between the specification and the code.

​Topics include:

• ​AI-assisted development for existing codebases.

• ​Minimizing hallucination risk and "slot machine" code generation.

• ​How end-to-end AI-native development changes roles across multiple teams.

• ​How and when to combine overarching agile methodologies (such as BMAD) with compiler-style AI tooling systems (such as CodeSpeak).

​Speaker: Kerry Champion

​Kerry Champion has 10+ years of experience with real-world use of ML and AI and 20+ years leading Silicon Valley technology teams. His current focus is on Enterprise applications of AI.

​Recent projects include:

• ​Supported an established SaaS Fintech as it added initial Gen AI features and made AI tools central to its software development process.

• ​Advised a launch team building an AI-native startup that brings modern customer service tools to a traditional vertical industry.

• ​Provided training for a multi-industry multinational as it builds a new center of excellence for AI deployments.

​​Organizers

​Ilya Kulyatin is an entrepreneur with work and academic experience in the US, Netherlands, Singapore, UK, and Japan. He holds a BA in Economics, an MA in Finance, and an MSc in Machine Learning. He's a 3x founder, now helping Japan grow the local AI ecosystem through a not-for-profit community, Tokyo AI (TAI), while building an AI-native system integrator and solutions provider, Foundry Labs株式会社.

​​​Supporters

​Foundry Labs K.K. is a Tokyo-based AI systems integrator and solutions provider, delivering end-to-end support for enterprises: from strategy design through implementation, deployment, and operations. They tailor AI to each client’s operational, regulatory, and security requirements, with hands-on experience across finance, government, and industry, and a track record of shipping production systems in secure and regulated environments.

​DEEPCORE is a Tokyo-based AI-focused incubator and venture capital firm, founded in 2017 as a wholly-owned subsidiary of SoftBank Group, backing pre-seed to early-stage AI and deep-tech startups across sectors from healthcare to logistics. It also operates KERNEL, an AI incubation community near the University of Tokyo, where founders, engineers, and researchers connect and co-create ventures.

​About TAI

​Tokyo AI (TAI) is the largest international AI community in Japan, with 5,000+ members mainly based in Tokyo: engineers, researchers, investors, product managers, and corporate innovation leaders. Through 80+ events a year and 300+ speakers spanning startups, enterprises, and academia, TAI connects the people building AI in Japan with the global ecosystem, working to transform Tokyo into a global AI hub.

​​​​Privacy Policy

​We will process your email address for the purposes of event-related communications and ongoing newsletter communications. You may unsubscribe from the newsletter at any time. Further details on how we process personal data are available in our Privacy Policy.