4d ago · 13 min read · MCP tool poisoning is the attack you can't see in your UI. We built the defense you can see in your kernel. In Part 3, I covered how we taught Correlic's AI investigation layer to analyze security inc
Join discussionApr 16 · 12 min read · AI agents are moving beyond demos and into real production use. In production, you need sessions that last through infrastructure changes, code that stays secure, and controls that your platform team
Join discussion
Apr 16 · 5 min read · TL;DR MCP is becoming the interface between AI agents and infrastructure data. Datadog shipped an MCP Server connecting dashboards to AI agents. Qualys flagged MCP servers as the new shadow IT risk.
Join discussion
Apr 16 · 4 min read · For years, observability has demanded a compromise. Deep visibility required invasive instrumentation SDKs embedded in every service, sidecars consuming resources, and agents constantly polling. The c
Join discussion
Apr 11 · 14 min read · *From raw incident timelines to confident, evidence-grounded analysis — the engineering decisions behind Correlic's AI investigation layer.* In [Part 2](https://correlic.hashnode.dev/your-ai-agent-mad
Join discussionApr 10 · 7 min read · April 2026 · Tracenyx Security Team On March 31, 2026, engineers across the world woke up to a serious supply chain attack. Two versions of Axios — the JavaScript HTTP client with over 100 million we
Join discussion
Apr 9 · 11 min read · TL;DR CUDA graphs shipped in 2018 but only became critical infrastructure in the past two years, driven by LLM inference demands and framework automation. They also create an observability blind spot
Join discussion
