The InfoQ Podcast Platform Engineering for AI: Scaling Agents and MCP at LinkedIn
30 snips
Dec 10, 2025 Karthik Ramgopal, LinkedIn's platform engineering lead, and Prince Valluri, an engineer focused on developer experience, dive into the world of AI agents. They discuss LinkedIn's unified agent platform, designed to enhance security and scalability. The duo explains the difference between foreground and background agents, and how these tools reduce developer toil. They also highlight the Model Context Protocol (MCP) as crucial for standardizing interactions across systems. Practical insights on improving developer experience and effective agent orchestration round out this compelling discussion.
AI Snips
Chapters
Transcript
Episode notes
Use Spec-Driven Developer Intent
- Express developer intent as a structured spec that defines tasks, tools, and acceptance criteria.
- Use specs as a contract so agents plan deterministically and reviewers understand expected outcomes.
Leverage Past PRs For Agent Judgement
- LinkedIn leverages historical PRs and human feedback as data to judge mergeability and suggest reviewer comments.
- Agents use past PR examples to improve quality and predict required changes.
Foreground Versus Background Agents
- Distinguish foreground (IDE) agents from background orchestration agents and use each where they fit.
- Foreground agents support active developer control; background agents run long-running, unsupervised tasks like refactors or observability.