Your agents lack context. Here's how to fix "You're absolutely right." 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). Dennis Pilarinos, CEO of Unblocked, gave this talk at LeadDev London (LDX3). 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. Access isn't understanding. A context engine is what closes that gap. See how Unblocked delivers it to your agents. Open source tools. A few OSS tools Unblocked has built to help teams understand the value of a context engine and start building their own: * 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: 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: 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. Stay in the loop. Emerging techniques for building with AI at scale and how software development is changing from the Unblocked team.

Stop Babysitting AI Agents: Build a Context Engine. Brandon Walsenuk from Unblocked discusses the critical need for context engines to empower AI agents, moving beyond simple data access to true understanding and autonomous operation. In the rapidly evolving world of AI, the challenge of managing autonomous agents has become a significant hurdle for many teams. Brandon Walsenuk, from Unblocked, recently addressed this issue at AI Engineer Europe, highlighting the critical need to move beyond simply providing agents with access to data and towards building robust context engines. His presentation, titled "Stop babysitting your agents: building a context engine for mergeable code," outlined the common pitfalls and offered a path forward for creating more effective and independent AI systems. Visual TL;DR. AI Agents Need Context leads to Babysitting AI Agents. Babysitting AI Agents leads to Data Access Isn't Enough. Data Access Isn't Enough instead Build a Context Engine. Build a Context Engine leads to Empower Autonomous Operation. Build a Context Engine leads to Mergeable Code. Empower Autonomous Operation leads to True Understanding. True Understanding leads to Future Applications. * AI Agents Need Context: current AI agents lack understanding, requiring constant human oversight * Babysitting AI Agents: continuous human intervention is needed for zero-context agents * Data Access Isn't Enough: providing data is not the same as providing true understanding * Build a Context Engine: a robust system to provide agents with essential background knowledge * Empower Autonomous Operation: enables AI agents to function independently and effectively * Mergeable Code: context engines facilitate seamless integration of AI-generated code * True Understanding: agents can grasp nuances and make informed decisions * Future Applications: context engines unlock advanced AI capabilities and autonomy Visual TL;DR The problem: context is king, not just access. Walsenuk began by drawing a parallel between human onboarding in a company and the current state of AI agents. Just as new hires initially lack context and require guidance, newly spawned AI agents often begin with a "zero context" state. This necessitates continuous human oversight and intervention, a process Walsenuk refers to as 'babysitting.' He argued that the core issue is not a lack of intelligence in these agents, but a deficit in understanding the broader context in which they operate. He debunked several myths surrounding the creation of effective AI agent context. First, he stated that a 'naive RAG over my docs is a context engine' is a misconception. While Retrieval Augmented Generation (RAG) can provide access to data, it often fails to deliver true understanding or reasoning capabilities, leading to agents that simply stop looking once they find a superficial match, rather than exhaustively searching for the correct solution. Secondly, the idea that 'if I just connect enough MCPs, I'm done' is also flawed. Simply connecting multiple tools or data sources does not guarantee the agent will understand or correctly reason across them. Finally, he addressed the myth that 'a bigger context window will solve this.' While larger context windows can be beneficial, they don't inherently provide the necessary reasoning capabilities or solve the fundamental problem of understanding nuanced relationships within the data. The solution: building a true Context Engine. Walsenuk emphasized that a proper context engine is essential for unlocking the full potential of AI agents. Such an engine should possess several key attributes: * Unified System Context: It must merge signals from all relevant sources before delivery to the agent. * Targeted Retrieval: It needs to retrieve only the information agents need based on the data graph. * Conflict Resolution: Recency and authority signals should resolve contradictions in the data. * Token Optimization: It should render compressed context to create relevant responses within prompt windows. * Data Governance: Permissions and policies must be enforced automatically across systems. * Personalized Relevance: Context should be scoped to the user, team, and work history. He illustrated these points with a demonstration of Unblocked's 'Social Graph Builder,' an open-source tool that analyzes historical pull request data to map team collaboration and identify subject matter experts. This tool, Walsenuk explained, provides a foundational component for building a sophisticated context engine. The demo showcased how such an engine can ingest data from various sources, understand individual roles and relationships within an organization, and provide agents with the precise, contextual information they need to perform tasks autonomously and effectively. Hard lessons and Future Applications. Walsenuk shared three hard lessons learned from their experience building context engines: * Optimized for Access, Not Understanding: Simply wiring more tools didn't help agents understand tasks better. * Hid Conflicts Instead of Surfacing Them: When sources disagreed, the system often picked one truth and ignored the conflict, leading to errors. * Cached Answers Instead of Computing Them: Reusing stale answers, even if they once seemed correct, broke the system as code and requirements evolved. He concluded by stressing that AI-generated code should feel as if it were written by a seasoned team member. This requires a context engine that can reliably provide the right information at the right time, enabling agents to operate with autonomy and intelligence, ultimately freeing up human engineers to focus on more complex, strategic tasks. (C) 2026 StartupHub.ai. All rights reserved. Do not enter, scrape, copy, reproduce, or republish this article in whole or in part. Use as input to AI training, fine-tuning, retrieval-augmented generation, or any machine-learning system is prohibited without written license. Substantially-similar derivative works will be pursued to the fullest extent of applicable copyright, database, and computer-misuse laws. See our terms.