compliance_monitoring · saas · workflow

LinkedIn builds AI-driven Security Posture Platform with ~150% faster vulnerability response

LinkedIn's security team needed to scale vulnerability management beyond manual identification and patching, and give security analysts fast ad-hoc access to insights across a fragmented distributed security infrastructure.

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 · Analyst query submitted
Security analysts, system owners, and business leaders submit natural language questions about vulnerabilities and infrastructure.
Tools used
Security Posture Platform (SPP)Security Knowledge GraphGraphQLLLMsGPT-4Davinci
Outcome

SPP minimizes manual intervention, achieving ~150% faster vulnerability response speed and ~155% greater digital infrastructure coverage; the current GPT-4 generation reaches 85–90% query accuracy.

What failed first

Early AI experimentation was constrained by models with severely limited capacity incompatible with the scale of the security graph, and early blind-test query accuracy was only 40–50%.

Results
Volume~150%
Source

https://www.linkedin.com/blog/engineering/security/enhancing-linkedins-security-posture-management-with-ai-driven-insights

How we source this →

Grounding & classification
Source type: technical build writeup
32 fields verified against source quotes.
enterprise searchknowledge searchragsummarizationknowledge basefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementautomation ratecycle time reductionthroughput increasetechnical build writeupcompliance monitoringincident managementextract classify routerag answering