AI coding tools promise productivity gains, but many teams aren’t seeing the impact.

The real bottleneck isn’t code generation. It’s context. Understanding why a system was built a certain way, how it evolved, and what trade-offs were made often requires digging through GitHub, Slack, Notion, Confluence, Jira, and other tools.

This talk explores the idea of context engineering: structuring and exposing relevant knowledge so both humans and AI agents can work more effectively. I’ll show how Unblocked creates a contextual layer across your tools, giving AI models like Claude and Cursor access to product decisions, architectural history, and team discussions.

The result is less hallucination, faster iteration, and fewer interruptions. You get AI that understands your system instead of just guessing.

If you’re using AI in production codebases, this is the foundation that makes it work.