STARTS MAY 12TH · BI-WEEKLY · LIVE
WTFÂ ISÂ THE
A bi-weekly live series for AI leaders and builders. One burning question per episode, an open AMA floor, and guests who've actually built context infrastructure.
FROM ONTOLOGY TO CONTEXT LAYER: WHAT ACTUALLY CHANGED WITH AI?
Both ontologies and context layers are trying to solve the same problem: give AI an understanding of what business concepts actually mean. Ontologies were the original attempt to encode the meaning human organizations run on. Jessica Talisman has been building ontologies since before LLMs existed. She joins Austin to give her honest take.
Bring your questions.
We'll bring answers.
...or more questions
Context is having a moment. Every new startup, and legacy business, is now a context company. The LangChain CEO called context engineering the defining skill for AI. Even MIT published a piece on context being the single biggest reason for AI failures.
And in all of this noise, you're still left with real questions nobody's answering. This series is built to work through your questions, with guests who actually know what they're talking about.
Why do my AI agents keep getting enterprise data wrong?
WTF IS THEÂ
CONTEXTÂ LAYER
How do I give AI the context that lives in my people's heads?
WTF IS THEÂ
CONTEXTÂ LAYER
How can I make sure our organizational context stays our own?
WTF IS THEÂ
CONTEXTÂ LAYER
How do I actually know if my context layer is working?
WTF IS THEÂ
CONTEXTÂ LAYER
Who should own the context layer?
WTF IS THEÂ
CONTEXTÂ LAYER
What does an AI team look like when it owns the context layer?
WTF IS THEÂ
CONTEXTÂ LAYER
Is context engineering a real discipline?
WTF IS THEÂ
CONTEXTÂ LAYER
How do you know when your context layer is good enough to ship an agent?
WTF IS THEÂ
CONTEXTÂ LAYER
Does every company need one, or is this only for large enterprises?
WTF IS THEÂ
CONTEXTÂ LAYER
Why do my AI agents keep getting enterprise data wrong?
WTF IS THEÂ
CONTEXTÂ LAYER
How do I give AI the context that lives in my people's heads?
WTF IS THEÂ
CONTEXTÂ LAYER
How can I make sure our organizational context stays our own?
WTF IS THEÂ
CONTEXTÂ LAYER
How do I actually know if my context layer is working?
WTF IS THEÂ
CONTEXTÂ LAYER
Who should own the context layer?
WTF IS THEÂ
CONTEXTÂ LAYER
What does an AI team look like when it owns the context layer?
WTF IS THEÂ
CONTEXTÂ LAYER
Is context engineering a real discipline?
WTF IS THEÂ
CONTEXTÂ LAYER
How do you know when your context layer is good enough to ship an agent?
WTF IS THEÂ
CONTEXTÂ LAYER
Does every company need one, or is this only for large enterprises?
WTF IS THEÂ
CONTEXTÂ LAYER
What are your burning questions about the context layer?
UPCOMING SESSIONS
Register for any session below. Can't make the live session?
Register anyway — on-demand access goes out within 24 hours.
Both ontologies and context layers are trying to solve the same problem: give AI an understanding of what business concepts actually mean. Ontologies were the original attempt to encode the meaning human organizations run on. Whether the context layer is a new name for the same job, or whether AI changed something fundamental about how it gets done. Jessica Talisman has been building ontologies since before LLMs existed. She joins Austin to give her honest take.
QUESTIONS WE'LL TACKLE:
- Ontologies have existed for thirty years. Why did its enterprise adoption stall?
- When AI can generate an ontology, what does the human still have to own?
- What can an ontology give an AI agent that a semantic layer cannot?
- Is the context layer a genuine evolution of ontology, or a rebrand?
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?
Late last year, Jaya Gupta called the context graph AI's next trillion-dollar opportunity: the reasoning behind a company's decisions that systems of record never stored. The post set off a wave of debate across the field. What it left unsettled is whether a strong graph is enough alone, or whether reliable AI needs the context layer around it, the wider system that governs how those decisions get used. Jaya joins Austin to work through what a context graph must hold and where it stops.
QUESTIONS WE'LL TACKLE:
- How much of the reasoning behind a decision can actually be captured as data?
- How does a context graph stay accurate when the enterprise changes?
- What happens when an agent faces a decision the context graph has never seen?
- What keeps two agents using the same context graph from contradicting each other?
Missed a live session?
Every episode is on-demand.
Watch the full conversation or read the recap.