Snyk's LangGraph support agent handled 60k queries with 85% ticket-free resolution
LangChain · x · 2026-10-09
Snyk shares how it built Snyk Assist, a customer-facing conversational agent on LangChain + LangGraph with observability in LangSmith. Key numbers: 60k queries handled, 500+ customer accounts served, 85%+ of sessions resolved without a support ticket, and 250+ cases auto-detected and escalated. Design pillars: solving a real customer pain point, treating trust and access control as core requirements (the agent stays within user permissions), and one LangGraph runtime powering multiple surfaces with LangSmith evals to catch regressions.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23