# Your agents lack context. Here's how to fix "You're absolutely right."


URL: https://getunblocked.com/blog/your-agents-lack-context/
Published: 2026-06-17T15:00:00Z
Author: Dennis Pilarinos
Categories: Context Engineering, Engineering Insights, Conference Talks

How to build the context engine AI agents need to produce organization-aware, permission-safe, and genuinely useful code. A talk by Unblocked Founder & CEO Dennis Pilarinos from LeadDev London (LDX3).

---
[External Video](https://player.vimeo.com/video/1199249283?dnt=1&app_id=122963 )


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 got decided in a Slack thread last night about the auth migration, or which architectural patterns your principal engineers actually enforce in review.

## Building a context engine

This talk is a practitioner's guide to building a context engine: the reasoning layer that continuously synthesizes organizational knowledge across disparate sources into unified, queryable understanding for humans and agents.

Dennis walks through the problems you actually have to solve:

- Searching globally and exhaustively before you can reason
- Reasoning across systems that don't agree with each other
- Maintaining identity-scoped permissions, so every user and every agent sees only what they should
- 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.

## Slides

Slides from the talk: [view the LDX3 deck (PDF)](https://leaddev.com/wp-content/uploads/2026/06/ldx3-leadership-final.pdf).

Access isn't understanding. A context engine is what closes that gap. See how [Unblocked](https://getunblocked.com) delivers it to your agents.

## Open Source Tools

A few OSS tools we’ve built to help teams understand the value of a context engine and start building their own:

- [Context Engine Simulator](https://github.com/unblocked/context-engine-simulator): a local tool that A/B tests whether pre-gathered organizational context helps AI coding agents complete tasks faster, cheaper, and better. No accounts needed, runs entirely with your preferred agent and optional MCP connectors you and your team use.
- [Engineering social graph](https://getunblocked.com/blog/oss-social-graph-builder/): a CLI tool that builds a weighted collaboration graph from your GitHub PR history. Point it at a repo, and it maps who reviews whose code, detects teams from review patterns, identifies domain experts for every code area, and flags knowledge silos. Then it renders an interactive visualization you can open in a browser.
- [Repo rules agent](https://getunblocked.com/blog/oss-repo-rules-agent/): a CLI tool + skill that turns `CLAUDE.md`, `AGENTS.md`, `.cursorrules`, and ~40 other rules-files scattered around your repo into a queryable index coding agents can consult on demand.