TAI Event Drop: Beyond Vector Databases [12 June]

Structured Retrieval and Graph-Native AI Systems

📅 Date: 12 June 2026

⏰ Time: 6:00 PM - 9:00 PM JST

📍 Location: Tokyo, Hongo

🔗 Register: https://luma.com/qbmw0kh8 (copy-paste if not working)

Intro

This event explores advanced retrieval architectures that ground AI systems using relational databases, graph structures, and ontologies rather than relying exclusively on vector embeddings. Across two technical sessions, Adam Gibson (Cofounder, Kompile) will examine how to build AI agents capable of reasoning over complex, structured environments and dynamically retrieving information through tool-mediated patterns.

We will learn practical context engineering approaches for managing mutable operational state, executing graph-native retrieval, and developing enterprise knowledge platforms with greater precision and control than traditional RAG pipelines.

Agenda

We’ll go from fundamental structured retrieval paradigms to advanced graph-native architectures. Part 1 introduces the limitations of vector-based RAG in dynamic environments and establishes a foundation in relational grounding, keyword-based entity resolution, and context assembly. Part 2 builds directly upon this foundation by scaling these concepts to enterprise knowledge graphs and ontologies, demonstrating how hierarchical data structures enable advanced agentic reasoning and dynamic information exploration. This chronological progression ensures a logical escalation in architectural complexity for the technical audience.

Details

As AI systems scale, vector-centric RAG architectures often struggle with highly structured data, complex relationships, and rapidly changing operational state. In this session, we will explore practical alternatives utilizing relational databases, ontologies, and tool-mediated retrieval.

We are joined by Adam Gibson (Cofounder of Kompile, O’Reilly Author) for a comprehensive two-part technical session:

Part 1: RAG Without Vector Databases: Structured Context Engineering for AI Agents

This session covers production architectures that ground AI agents entirely through structured retrieval techniques, demonstrating how relational data and tool-mediated expansion can outperform traditional RAG pipelines. It addresses context assembly under strict token constraints and strategies for managing mutable application state.

Part 2: Graph-Native AI Systems: Ontologies, Knowledge Graphs, and Retrieval Beyond Embeddings

This talk examines how AI systems can directly leverage enterprise graph structures and ontologies rather than flattening relational data into embedding spaces. Topics include graph RAG architectures, subgraph exploration for LLM agents, and structured context compression.

Supporters

Special thanks to our supporters: Foundry Labs and DEEPCORE.

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.

Organizers

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.

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.