Episode 5
How do graph databases and
the context layer fit together?
Emil Eifrem and Prukalpa Sankar agree on the problem: enterprise AI fails when agents can't navigate the relationships that give data meaning. Emil argues graph databases are the foundation — the layer that maps how entities and relationships connect. Prukalpa argues: graph databases store structure, but the context layer carries meaning, governance, and lineage. They join Austin to work toward a shared picture of what enterprise AI actually needs.
Questions we'll tackle:
- What actually counts as a context layer?
- Is a graph database a foundation, a component, or one option among several for the context layer?
- A graph database maps how everything connects. Is that enough for AI to trust the data?
- Graph databases aren't new to enterprise. So why is the context problem still unsolved?
SPEAKERS
CONVERSATION LEADERS
HOST
Director of Data Strategy, Atlan
Former Gartner Director who spent years advising Fortune 500 data leaders on analytics strategy — now Director of Data Strategy at Atlan. He's the person large enterprises call when they can't figure out why their AI keeps getting context wrong.
GUEST
CEO & Co-founder, Neo4j
CEO and Co-founder of Neo4j, the graph database company he started in 2007. He coined the term "property graph" and has spent two decades building the infrastructure that maps how enterprise data connects. He argues graph databases aren't just useful for AI — they're the foundation layer that makes relationships navigable at scale.
GUEST
Co-founder, Atlan
Co-founder of Atlan, the active metadata platform. She has been building context infrastructure since before "context layer" was a phrase anyone used. Her argument: a graph database stores structure, but structure alone isn't context — meaning, governance, and lineage are what make data trustworthy for AI agents.