# Snyk Assist Transforms Internal Tool into Essential Customer Support Feature > Discover how Snyk transitioned its internal support tool into a vital customer feature, enhancing service efficiency and addressing critical operational challenges in the AI security landscape. **Source**: langchain.com | **Published**: 2026-10-09 | **Type**: case_study ## Key Facts - Snyk Assist resolved 85% of queries without tickets, enhancing customer satisfaction and reducing costs. - 60,000+ queries handled indicate strong demand for efficient support, reflecting market need for automation. - Internal testing minimized rollout risks, showcasing Snyk's commitment to quality and customer trust. - Single LangGraph runtime across platforms streamlines updates, providing a competitive edge in scalability. - Auto-detection of 250+ cases highlights vulnerabilities in product, informing strategic improvements in documentation. ## Summary \## Summary Snyk, an AI Security Platform, faced challenges in scaling its customer support operations. To address this, they developed Snyk Assist, a conversational agent that provides quick, accurate answers to customer inquiries. Since its launch, Snyk Assist has resolved over 85% of sessions without the need for a support ticket, significantly reducing the workload on the support team. \## Background Snyk is a security platform that helps developers find and fix vulnerabilities in code, open source dependencies, containers, and cloud configurations. Before deploying Snyk Assist, customer inquiries were managed through traditional support channels, which involved reading through extensive documentation and filing tickets, leading to delays and inefficiencies. \## Challenge The primary challenge was the inability of the support team to scale effectively as customer inquiries grew. Each support case required classification and routing, which became increasingly burdensome. Snyk needed a solution that could provide accurate answers while maintaining the security standards expected from their products. \## Solution Snyk Assist was initially developed as an internal tool for the support team, functioning as both a case triage and virtual agent. It was built using LangChain and LangGraph, with observability managed in LangSmith. The agent was designed to understand customer context, perform health checks, and automate ticket creation. In September 2026, Snyk Assist was integrated into the core product, making it accessible to all paying customers. \## Results Since its launch in April 2026, Snyk Assist has handled over 60,000 queries across more than 500 customer accounts. It has resolved over 85% of sessions without generating a support ticket, saving the support team hundreds of hours. Additionally, the agent has auto-detected and escalated over 250 cases directly to the appropriate teams. \## Key Insights Snyk's approach highlights the importance of internal testing before customer rollout, ensuring that any issues are identified early. The use of a single runtime for multiple interfaces simplifies maintenance and scaling. Continuous evaluation and feedback loops are crucial for improving AI performance and user experience. \## Customer Testimonial “The hard part of building agents isn't what the model can do, it's proving the agent actually works. We run every change through evals in LangSmith, and if it doesn't clear the bar, it doesn't ship." — Bailey Millns, AI Engineer, Snyk ## Entities - **Companies**: Snyk - **Products**: Snyk Assist, LangChain, LangGraph, LangSmith - **Technologies**: AI, conversational agent, middleware, PostgreSQL - **People**: Bailey Millns, Jada Ross, Matt Jarvis ## Key Concepts customer support automation, AI in security, internal tooling, scalability, evaluation processes, user permissions, conversational interfaces, feedback loops ## Definitions - **Snyk Assist**: A conversational agent developed by Snyk to help customers find answers and take actions related to security queries. - **LangChain**: A framework used for building conversational agents, known for its community support and robust ecosystem. - **LangGraph**: A runtime that powers multiple surfaces of the Snyk Assist agent. - **LangSmith**: A tool used for observability and evaluation of the Snyk Assist agent's performance. - **middleware**: Software that acts as a bridge between different applications or services, facilitating communication and data management. ## Use Cases - automating customer support queries - checking for known vulnerabilities in packages - raising support tickets - logging feature requests - conducting health checks on user accounts - handling case triage ## Frequently Asked Questions **What is Snyk Assist?** Snyk Assist is a conversational agent designed to help customers quickly find answers to their security-related questions without navigating through extensive documentation. **How does Snyk ensure the accuracy of Snyk Assist?** Snyk employs a rigorous evaluation process using LangSmith to test every change made to the agent, ensuring it meets high standards for accuracy and reliability before being deployed. **What technologies power Snyk Assist?** Snyk Assist is built on LangChain and LangGraph, with observability managed through LangSmith, allowing for a scalable and efficient conversational agent. **How has Snyk Assist impacted customer support?** Since its launch, Snyk Assist has handled over 60,000 queries and resolved more than 85% of sessions without the need for a support ticket, significantly reducing the workload on the support team. **What are the future plans for Snyk Assist?** Snyk aims to continue enhancing Snyk Assist to ensure it remains a valuable tool for customers, integrating it further into the Snyk experience and improving its capabilities based on user feedback. ## Links - [Read on Welcome.AI](https://welcome.ai/content/snyk-assist-transforms-internal-tool-into-essential-customer-support-feature) - [Original source](https://www.langchain.com/blog/how-snyk-turned-an-internal-support-agent-into-a-customer-feature) - [LangChain](https://welcome.ai/company/langchain): Featured company --- Source: Welcome.AI | https://welcome.ai/content/snyk-assist-transforms-internal-tool-into-essential-customer-support-feature