Unblocked Engineer Peter Werry Demonstrates Relational Context Engine: Addressing RAG Limitations in Structured Engineering Data
AI Engineer conference video selection. Peter Werry from Unblocked argues that traditional RAG (vector similarity search) fails to handle engineering data queries with temporal or structural attributes. He proposes building a 'Relational Context Engine' that converts natural language into database queries, ensuring reliability through schema discovery, identity resolution, query planning, and validation retries. The workshop demonstrates building this engine over a GitHub repository, suitable for readers focused on AI engineering implementation.
In a video published on October 11, 2026, for the AI Engineer conference, Peter Werry from Unblocked demonstrated a technical architecture called the 'Relational Context Engine,' designed to address the limitations of traditional Retrieval-Augmented Generation (RAG) when handling structured engineering data. Werry pointed out that when users ask questions with temporal or structural constraints, such as 'PRs I merged last week,' RAG systems relying solely on vector similarity search often return results that are semantically relevant but temporally incorrect or structurally mismatched.
Werry's core thesis is that RAG is only half of retrieval; the other half is turning natural language into a real database query. In this mode, the model does not answer the question directly but writes the query. His workshop walked through six stacked Pull Requests, demonstrating how to transform a stubbed query playground into a working engine over a GitHub repository.
To ensure query reliability, Werry proposed four key components: Schema Discovery (sampling documents and merging them into a tree structure using procedural code rather than model inference for types), Identity Resolution (mapping users to GitHub logins via fuzzy matching), Query Planning (passing the schema, forcing a tool call for name extraction, and including the current date), and Validation & Retries (deny-by-default strategy, using an operator allow list to prevent JavaScript execution on the server, and falling back to full-text search when exact match fails).