Grammarly Says Wiz MCP Cut Security Triage Time by Nearly 90%

Summary

Grammarly says a workflow combining Wiz MCP, LLMs, and internal tools reduced tier-1 security ticket investigation time from 30–45 minutes to a maximum of four minutes. The company says it later expanded automation to other security tasks.

Key points

Grammarly began with tier-1 incident triage as a focused use case for Wiz MCP and AI-assisted workflows.
The described workflow uses Jira ticket details, Wiz context, LLMs, and tools connected to internal knowledge and communications systems.
Grammarly reports that ticket investigation time fell from 30–45 minutes to a maximum of four minutes, an efficiency improvement of nearly 90%.
The company says it expanded the workflows to threat hunting, detection engineering, and threat-intelligence knowledge building.
Grammarly recommends starting with focused tasks, refining prompts using organizational data, and keeping people involved in reviewing AI outputs.

Article Details

Topic: Grammarly’s use of the Wiz MCP Server and AI workflows to automate security triage and other security operations

People

Giles DouglasGrammarly’s Chief Information Security Officer; described the need to scale security processes and automate repeatable work.Igor TarpanGrammarly’s Security Engineer; described how Wiz MCP workflows support triage and reduce manual work.Thijn BukkemsGrammarly’s Threat Hunting Lead; discussed the development and gradual expansion of AI workflows.

Vendors

WizThis vision first led Grammarly to adopt Wiz, which transformed the company’s approach to cloud visibility, vulnerability detection, and secure-by-design workflows. But as operations expanded through acquisitions,

Products

Claude DesktopThe team began using tools like Claude Desktop and the Wiz MCP servers with custom prompt templates to automate repeatable standard processes. With these prompts, a typical triage flow begins with a Jira ticket, which Jirato automate repeatable standard processes. With these prompts, a typical triage flow begins with a Jira ticket, which automatically retrieves issue details and analyzes the context using Wiz. The next step in LangGraphnext step in their orchestration involved integrating the Wiz MCP into an AI agented workflow via the LangGraph framework, combined with other tools that access the internal knowledge base and communication systems,Wiz MCP serverGrammarly’s journey with the Wiz MCP Server shows how targeted automation can deliver outsized impact—cutting response times, boosting efficiency, and freeing teams to focus on high-value work. By starting small,