Presentation: Platform Teams Enabling AI - MCP/Multi-Agentic Tools Across Linkedin
LinkedIn built platform abstractions for multi-agent AI. Here's how they orchestrated coding, testing, and observation agents at scale.
Why it matters
LinkedIn is moving beyond fragmented AI implementations by building internal platform tooling (MCP-based) for orchestration and safe agent deployment. This signals how large enterprises are standardizing agent infrastructure as a competitive execution layer.
The key facts
11 to knowLinkedIn built real-world coding agents, observation agents, and UI testing agents
Platform abstraction approach for orchestration, structured context, and tooling
MCP (Model Context Protocol) used as safety/tooling framework
Speakers: Karthik Ramgopal and Prince Valluri (LinkedIn engineering)
Focus on moving beyond fragmented implementations to standardized multi-agentic execution model
LinkedIn built platform abstractions for AI agent orchestration
MCP (Model Context Protocol) tooling standardized across agents
Real production agents: coding, observation, and UI testing
Focus on structured context and safe tooling for multi-agent systems
Architectural pattern moves from fragmented implementations to unified execution model
Presented by engineering leaders Karthik Ramgopal and Prince Valluri
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: LinkedIn’s Karthik Ramgopal and Prince Valluri discuss leveraging AI as a new execution model for large-scale engineering. They explain how to move beyond fragmented implementations by building platform abstractions for orchestration, structured context, and safe tooling like MCP. They share…