At #LinkedIn, early AI coding tools created more "babysitting" than productivity.
Discover how they used MCP to build Contextual Playbooks - scaling to 600+ playbooks & 8K active users.
The result❓ ➡️ 20% productivity boost ➡️ Zero drop in system reliability
🔗 Watch Ajay Prakash’s video + transcript 👉 https://www.infoq.com/presentations/linkedin-context-engineering/
Ajay Prakash discusses how LinkedIn overcomes AI agent limitations in large codebases. He explains Contextual Agent Playbooks and Tools - built on Model Context Protocol (MCP) - which serves procedural memory, code search, and runbooks directly to coding agents. Prakash shares architectural details and operational guardrails that deliver a 20% productivity boost with zero loss in reliability.
www.infoq.com
Comments (0)
Sign in to comment or create an account