Merge CTO Gil Feig: Why Enterprise AI Agents Need a 'Context Graph' Beyond Live MCP Lookups
At the 2026 AI Engineer World's Fair in San Francisco, Merge Co-founder & CTO Gil Feig argued that connecting MCP servers alone is insufficient for large-scale data queries. He proposed building a 'Context Graph' (company brain) using synced data copies, routers, and summarizers to support semantic search, emphasizing the role of skills and memory in the context layer.
For engineering teams building enterprise-grade AI agents, a common pain point is this: an agent can explain why one customer was upset, but fails when asked 'which customers were upset last year?'—a query requiring cross-dataset analysis. In his talk 'Why Your Company Needs a Context Graph (and How to Build It)' at the 2026 AI Engineer World's Fair, Gil Feig, Co-founder & CTO of Merge, addressed this architectural bottleneck.
Feig explained that simply connecting a few MCP (Model Context Protocol) servers isn't enough because live API lookups cannot perform semantic searches across large datasets. He advocated for a 'Context Graph' or 'company brain' architecture that integrates third-party data, structured context, memories, and skills. Key components include a router, synced and live context, a summarizer, and skills/memory modules that encode how the company defines business concepts like a 'happy customer'.
The presentation also covered four tiers of context, including derived summaries, and provided a decision flowchart for when to use cached versus live data. Feig further emphasized traceability, noting that every answer must track where its data came from, when it was retrieved, and what invalidates it. For readers seeking to enhance their agents' ability to handle complex enterprise data, this session offers a valuable reference on practical architectural patterns.