500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn
LinkedIn scales a large internal agent catalog through search, schema lookup, and execution rather than exposing every tool at once. Its playbooks add task-specific operating knowledge.
LinkedIn’s internal system serves more than **1,300 tools** and **600 playbooks** to coding agents. Because performance reportedly degrades beyond 30–40 exposed MCP tools, the catalog sits behind **three meta-tools**: search, schema lookup, and execution.
Use progressive discovery when your tool surface grows. Keep playbooks narrow and composable, load their instructions only when relevant, and let agents propose reviewed updates when real work reveals stale or missing guidance.
LinkedIn’s internal system serves more than **1,300 tools** and **600 playbooks** to coding agents. Because performance reportedly degrades beyond 30–40 exposed MCP tools, the catalog sits behind **three meta-tools**: search, schema lookup, and execution. Use progressive discovery when your tool surface grows. Keep playbooks narrow and composable, load their instructions only when relevant, and let agents propose reviewed updates when real work reveals stale or missing guidance. The reported scale includes **8,000 daily users** inside LinkedIn’s centrally managed environment. Its tool-limit observation is not presented as a controlled benchmark, and smaller teams may not need the authentication, telemetry, and distribution infrastructure described.
This supplies a large internal deployment case for progressive tool and skill discovery: expose a tiny routing surface, retrieve schemas and playbooks only when needed, and maintain guidance through reviewed feedback from real work. It confirms that catalog scale changes harness architecture, while leaving the claimed tool threshold uncontrolled and making the supporting governance infrastructure potentially disproportionate for smaller teams.