0:00 / 0:00

AI Dev 26 x SF | Brandon Waselnuk: Building the Context Engine AI Agents Need

Name: AI Dev 26 x SF | Brandon Waselnuk: Building the Context Engine AI Agents Need
Uploaded: 2026-06-16T14:56:30.093Z
Duration: 25 min 25 s
Channel: DeepLearning.AI
Description: Brandon Waselnuk from Unblocked discusses building a context engine that provides AI agents with organizational knowledge from distributed sources. The video covers practical engineering challenges such as reasoning over inconsistent systems, permission management, and personalized results beyond basic RAG.

DeepLearning.AI16 June 2026Watch on YouTube

Description

Every AI coding tool can generate code. Very few can generate the right code for your organization, because they're missing context. They don't know why your team chose Redis over DynamoDB, what the team decided in a Slack thread from two months ago about the auth migration, or which architectural patterns your principal engineers actually enforce in review. Brandon Waselnuk from Unblocked shares a practitioner's guide to building a context engine: the reasoning layer that continuously synthesizes organizational knowledge across disparate sources into unified, queryable understanding. Brandon walked through the problems you actually have to solve — reasoning across systems that don't agree with each other, searching globally before you can reason, maintaining identity-scoped permissions so every user and agent only sees what they should, and personalizing results based on who's asking and what they're working on. These are the engineering challenges that make naive RAG fall short, drawn from real lessons building this at scale. Learn more about Unblocked: https://tinyurl.com/4hmu89np

What you'll learn

You understand why AI coding tools without context fail to generate the right code for your organization
You learn how to build a context engine that synthesizes knowledge from scattered sources into queryable insights
You see how to reason across systems that do not agree with each other
You learn to apply identity-scoped permissions so users and agents only see what they should
You discover how to personalize results based on who is asking and what they are working on

Frequently asked questions

Why does naive RAG fall short for organizational context?

Naive RAG falls short because you need to search globally before you can reason, and real organizational context lives across systems that do not agree with each other. Reasoning over that requires a context engine as an intermediate layer.

Which engineering challenges come with building a context engine?

The main challenges are reasoning across inconsistent systems, searching globally before reasoning, managing identity-scoped permissions so every user and agent only sees what they should, and personalizing results based on who is asking.

What exactly is a context engine?

A context engine is the reasoning layer that continuously synthesizes organizational knowledge from various sources into unified, queryable understanding. It forms the basis AI agents use to generate the right code for your organization.

Topics

ai-agents rag context-engines practical-applications enterprise-ai