Uploaded May 2026 | Updated November 2026, 1 day ago
Talk by Payal Singh
socallinuxexpo.org/scale/23x/presentations/postgres-ai-control-plane-building-rag-mcp-workflows-inside-database
As AI systems become more complex, developers are discovering that the database, not the model, is the real foundation of reliable AI. In this talk, I'll explore how Postgres can function as a full AI application server and control plane by combining Retrieval-Augmented Generation (RAG) with the Model Context Protocol (MCP).
We’ll walk through a real implementation: ingest pipelines, vector search, metadata ranking, caching, provenance tracking, and LLM tool-calling, with Postgres acting as the system of record and the control plane. Then we’ll expose those capabilities over MCP so LLMs can safely query, transform, and orchestrate data.
The result is an end-to-end AI system where RAG, tools, transforms, logs, and automation are anchored in Postgres, providing a single, reliable foundation for AI applications
Talk by Payal Singh
socallinuxexpo.org/scale/23x/presentations/postgres-ai-control-plane-building-rag-mcp-workflows-inside-database
As AI systems become more complex, developers are discovering that the database, not the model, is the real foundation of reliable AI. In this talk, I'll explore how Postgres can function as a full AI application server and control plane by combining Retrieval-Augmented Generation (RAG) with the Model Context Protocol (MCP).
We’ll walk through a real implementation: ingest pipelines, vector search, metadata ranking, caching, provenance tracking, and LLM tool-calling, with Postgres acting as the system of record and the control plane. Then we’ll expose those capabilities over MCP so LLMs can safely query, transform, and orchestrate data.
The result is an end-to-end AI system where RAG, tools, transforms, logs, and automation are anchored in Postgres, providing a single, reliable foundation for AI applications










