Beyond RAG: Build a Relational Context Engine from Scratch
Conference Context
- Date/time: 2026-06-29 · 12:10pm-1:10pm
- Track/room: Workshops Day 1 · Track 7
- Speaker(s): Peter Werry
- Session type/status: workshop · confirmed
- Track: Workshops Day 1
- Room: Track 7
- Session type: workshop
- Status: confirmed
Session Description
In this workshop we'll explore the importance of context engines in modern engineering workflows, and we'll look at why traditional RAG techniques are no longer enough to deliver the context agents need. We'll build a structured query engine that fills the gaps left by RAG, translating natural language into validated database queries over GitHub PR and Issue data. We'll implement schema-aware prompting, identity resolution, query validation, and error-driven retry loops, and you'll walk away with a working query engine for your GitHub repository.
Media Evidence
Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
- Source video:
youtube-5ID22ACI7IM - Slide deck: Dense Slides: Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked — 4 visible slide image(s); 4 HTML recreation(s).
- Additional slide evidence: Slides: Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked, Reconstructed Slides: Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
- Slide-derived themes for
youtube-5ID22ACI7IM: connect, code, logs, docs, tickets, gives, plausible, output.

Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.
Media Signals
youtube-5ID22ACI7IM— 4 slide-derived text signals- Slide-derived themes for
youtube-5ID22ACI7IM: connect, code, logs, docs, tickets, gives, plausible, output. - Evidence links for
youtube-5ID22ACI7IM: youtube 5ID22ACI7IM, youtube 5ID22ACI7IM slides, youtube 5ID22ACI7IM dense slides, youtube 5ID22ACI7IM reconstructed slides
Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Supporting Slides
- youtube 5ID22ACI7IM slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube 5ID22ACI7IM dense slides (4 viable slide images).
- Related slide/OCR pages:
- youtube 5ID22ACI7IM dense slides
- youtube 5ID22ACI7IM reconstructed slides
- youtube 5ID22ACI7IM slides
- Slide-derived terms:
code,context,unblocked,tickets,review,tests,description,rere,planning,architecture,compiles,fails,undlocked,callers,quality,team,comp,improve
Synthesis
Synthesized Breakdown
Beyond RAG: Build a Relational Context Engine from Scratch ## Conference Context - Date/time: 2026-06-29 · 12:10pm-1:10pm - Track/room: Workshops Day 1 · Track 7 - Speaker(s): Peter Werry - Session type/status: workshop · confirmed - Track: Workshops Day 1 - Room: Track 7 - Session type: workshop - Status: confirmed ## Session Description In this workshop we'll explore the importance of context engines in modern engineering workflows, and we'll look at why traditional RAG techniques are no longer enough to deliver the context agents need. We'll build a structured query engine that fills the gaps left by RAG, translating natural language into validated database queries over GitHub PR and Issue data. We'll implement schema-aware prompting, identity resolution, query validation, and error-driven retry loops, and you'll walk away with a working query engine for your GitHub repository. ## Media Evidence Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Speaker And Company Context
- Peter Werry — Founding Engineer at Unblocked.
Topics Covered
Derived Links And Source Material
- youtube 5ID22ACI7IM — related YouTube source page.
- youtube 5ID22ACI7IM slides — slide evidence.
- youtube 5ID22ACI7IM reconstructed slides — slide evidence.
- youtube 5ID22ACI7IM dense slides — slide evidence.
Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.
Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.