AI å ę äøē¼ŗ失ēäøå±ļ¼äøäøęļ¼äøä» ä» ęÆē¶ę
Source: Data Eng Weekly
Join The Great Data Debate to get answers to questions the data & AI industry is so curious about right now:
Where does context materialize in practice?
Semantic layers, ontologies, context graphs - what should data teams build in 2026?
Who owns context as meaning evolves?
Where should that context live: in the warehouse, inside agents, or in a dedicated context layer?
Why Data Engineers Must Think in Graphs, Not Just Tables
If you have been following the āSystems of Recordā debate on tech Twitter, you likely saw the clash between the āAgents kill SaaSā camp and the āLong live the Databaseā camp. But for data engineers, the reality is more nuancedāand far more interesting.
As we move from dashboards to autonomous agents, we are hitting a wall. It turns out that knowing the state (what happened) is not the same as knowing the reasoning (why it happened).
Drawing on recent insights from Foundation Capital, Jamin Ball (Altimeter), OpenAIās internal engineering team, and the TrustGraph manifesto, this post explores the emergence of the Context Graph. This missing architectural layer will likely redefine how we build data platforms in the agentic era.
The Problem: State Machines vs. Decision Traces
For the past decade, our role as data engineers has been to centralize data in the warehouse (or Lakehouse). We built ETL pipelines to move data from Salesforce, NetSuite, and Zendesk into a āSingle Source of Truth.ā
However, traditional Systems of Record (SoR) effectively act as āstate machines.ā They record the final output: the organization closed a deal, applied a discount, and escalated a ticket. But they fail to capture the decision traces.
As Foundation Capital notes, the reasoning behind a decisionāthe Slack threads, the cross-system synthesis, the VPās verbal override of a policyāis rarely captured in the database. A CRM might show a ā20% discount,ā but it wonāt tell an AI agent why that exception was granted (e.g., āCustomer represents a strategic entry into the APAC marketā).
Without these traces, agents fly blind. They have the rules (āDo not give discounts >10%ā), but they lack historical context on when and why they were violated.
The Solution: The Truth Registry and the Context Graph
To address this, we observe a bifurcation in the modern data stack, as illustrated by the Hybrid Agentic Architecture (see Figure 1 below).
This architecture consists of two distinct but integrated planes:
1. The Warehouse as the āTruth Registry.ā
Jamin Ball argues that systems of record arenāt dying; they are becoming āboring, rock-solid sources of truthā. In an agentic world, the warehouse must evolve into a āTruth Registryā that encodes semantic contracts.
Agents are fragile. If an agent hallucinates the definition of āChurn,ā it can automate disastrous decisions. Therefore, we must clean and canonize data before the agent sees it. In the architecture above, the flow is from Raw (Variant) to Silver (Extracted) to Gold (Canonical Model).
Engineering Takeaway: You cannot feed agents raw JSON blobs. Extracting variant columns into typed, named columns in the Silver layer is critical. It transforms āavailable dataā into āgoverned data,ā preventing agents from guessing schemas at runtime.
2. The Context Graph as the āReasoning Layer.ā
While the warehouse handles facts, the Context Graph handles relationships. TrustGraph defines a context graph as a ātriples-representation of data (Subject ā Predicate ā Object) optimized for AIā.
Why a graph? Because structure is information. When you feed an LLM structured data (like RDF or Cypher), the structure itself encodes meaning. This allows agents to traverse relationships that SQL joins struggle to representāstitching together a userās support ticket, their billing status, and their web activity into a single, queryable context.
Case Study: Inside OpenAIās Data Agent
OpenAI recently reported that standard metadata was insufficient for their internal data agent. They had to build a custom āContext Layerā that closely resembles the architecture above.
Their agent failed when it relied solely on table schemas. To fix this, they added:
Human Annotations: Curated descriptions of what tables actually mean (e.g., āThis table excludes logged-out usersā).
Code Enrichment: They used āCodexā to crawl their own codebase, understanding data lineage not just by metadata, but by reading the pipelines that produced the data.
This confirms a major trend: The metadata is the model. Providing agents with a semantic ontology (machine-readable definitions of terms) is just as important as the data itself.
The āFront Doorā is Moving
The implications for the industry are massive. Historically, if you owned the System of Record (like Salesforce), you owned the āFront Doorā (the UI).
But as agents take over workflows, the UI is unbundling from the data. Jamin Ball compares this to the travel industry: GDS systems (Sabre, Amadeus) remained the backend source of truth, but Online Travel Agencies (Expedia, Booking) captured the front doorāand the value.
In our new stack, the Agents become the OTAs. They are the new interface. The Warehouse/Lakehouse becomes the GDSāthe invisible, essential infrastructure layer.
What This Means for Data Engineers
Stop Hoarding State, Start capturing Traces: We need to instrument our systems to emit ādecision tracesā on every run. If an agent (or human) makes a decision, record the inputs and the logic used, not just the result.
The Rise of the āGoldā Layer: Your dbt models are no longer just for dashboards. They are the safety rails for autonomous agents. Strict typing, āGoldā tables, and canonical definitions are non-negotiable.
Graph Literacy: You donāt need to be a Neo4j expert, but understanding the basics of triples (Subject-Predicate-Object) and ontologies is becoming a core DE skill.
Extract Your Semi-Structured/Unstructured Data:Ā As shown in the architecture diagram, leaving data in unstructured blobs is a liability. Agents need explicit structure to reason safely.
As agents grow more capable, the infrastructure beneath them must evolve. The Context Graph offers a powerful new foundationānot just for smarter agents, but for more transparent, explainable, and aligned systems. Itās time for data teams to build not just pipelines, but reasoning engines.
References
https://x.com/KirkMarple/status/2003944353342149021
https://x.com/KirkMarple/status/2005443843848856047
https://foundationcapital.com/context-graphs-ais-trillion-dollar-opportunity/
