Workato CISO shares how AI agents triage ~80% of security alerts in production
adamse · x · 2026-11-17
Workato CISO Hans Gustavson and his security team detailed how they rebuilt security operations with agentic workflows.
- 80% of security alerts are triaged by AI agents; one piece of audit evidence is auto-mapped to 23 compliance frameworks; security reviews run inside Slack
- Cited data: 87% of security leaders flag AI-related vulnerabilities as the fastest-growing cyber risk (WEF); attack speed up 65% from 2024 with the fastest breakout at 27 seconds (CrowdStrike)
- Stack built from Agents, Skills as recipes, Knowledge Bases, event streams, and APIM — a reference architecture enterprise IT teams can adapt
More from coding & agent
- DEF CON talk breaks down 6 data-exfiltration vulnerabilities in AI agents — Kyrannio · 2026-11-17
- Voice agent flagged as spam? Swapping the DID won't help — check pickup latency first — Packet-Exchange-Care · 2026-11-17
- Coding agents burn two-thirds of tokens after the first edit; upfront plans fix it — rseroter · 2026-11-17
- PM running 60+ concurrent Claude Code sessions switches from cmux to t3 — kavirkaycee · 2026-11-17
- OpenAI quietly adds a remote switch controlling how Codex runs agent teams — ryanmerket · 2026-11-17
- Torch Compile underrated: CUDA Graphs + PDL hits 98% of megakernel speed on Llama 1B — simran_s_arora · 2026-11-17