recruiting · saas · workflow
LinkedIn extends GenAI tech stack to build multi-agent AI systems including Hiring Assistant
LinkedIn's existing GenAI stack supported single-agent, one-off prompt interactions but was not tenable for the complex, long-running multi-agent workflows that members and customers needed across the platform.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Agent definition and registration
Developers annotate a gRPC service schema with metadata and register their agent into a central skill registry via a build plugin.
Tools used
gRPCLangSmithLangGraphLangChainOpenTelemetryMCPA2A
Outcome
LinkedIn extended its GenAI platform with multi-agent orchestration, human-in-the-loop control, and layered observability, and is making Hiring Assistant globally available in English to customers.
Grounding & classification
Source type: technical build writeup
22 fields verified against source quotes.
agentic workflowconversational aimulti agent workflowragknowledge basenamed customerproduction runtime claimedtools describedworkflow describedsoftwaretechnical build writeuprecruitingagentic task executionhuman review queue