--- title: "Correlic (@correlic) | Hashnode" description: "Kernel-level security observability for AI coding agents. Read the latest articles by Correlic on Hashnode." url: "https://hashnode.com/@correlic" --- @correlic # Correlic @correlic · Joined March 2026 Kernel-level security observability for AI coding agents [Website](https://correlic.com/) ### [Your AI Agent Got Poisoned Through a Tool Description. Here's Why Only the Kernel Saw It Coming.](https://correlic.hashnode.dev/your-ai-agent-got-poisoned-through-a-tool-description-here-s-why-only-the-kernel-saw-it-coming?utm_source=hashnode&utm_medium=feed) MCP tool poisoning hides attacker instructions in tool metadata — invisible to you, fully visible to the model. We built kernel-level eBPF monitoring that catches it where app-layer defenses can't. 13 min read · [correlic.hashnode.dev](https://correlic.hashnode.dev/your-ai-agent-got-poisoned-through-a-tool-description-here-s-why-only-the-kernel-saw-it-coming?utm_source=hashnode&utm_medium=feed) [Apr 20](https://hashnode.com/posts/your-ai-agent-got-poisoned-through-a-tool-description-here-s-why-only-the-kernel-saw-it-coming/69e69479c9501dd01034b697) ### [I Built an AI System to Investigate AI Agents. Here's What I Learned About Making It Not Lie.](https://correlic.hashnode.dev/i-built-an-ai-system-to-investigate-ai-agents-here-s-what-i-learned-about-making-it-not-lie?utm_source=hashnode&utm_medium=feed) \*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 14 min read · [correlic.hashnode.dev](https://correlic.hashnode.dev/i-built-an-ai-system-to-investigate-ai-agents-here-s-what-i-learned-about-making-it-not-lie?utm_source=hashnode&utm_medium=feed) [Apr 11](https://hashnode.com/posts/i-built-an-ai-system-to-investigate-ai-agents-here-s-what-i-learned-about-making-it-not-lie/69da9a2dc8e5007ddbdae95b) ### [\[Part 2\] Building Correlic: Your AI Agent Made 70 System Calls Per Second. Here's How I Taught My System Which Ones Matter.](https://correlic.hashnode.dev/part-2-building-correlic-your-ai-agent-made-70-system-calls-per-second-here-s-how-i-taught-my-system-which-ones-matter?utm_source=hashnode&utm_medium=feed) Four failed attempts at teaching a machine what matters — and the baseline system that finally got it right. 15 min read · [correlic.hashnode.dev](https://correlic.hashnode.dev/part-2-building-correlic-your-ai-agent-made-70-system-calls-per-second-here-s-how-i-taught-my-system-which-ones-matter?utm_source=hashnode&utm_medium=feed) [Apr 9](https://hashnode.com/posts/part-2-building-correlic-your-ai-agent-made-70-system-calls-per-second-here-s-how-i-taught-my-system-which-ones-matter/69d7d80ffa7251682ecee170) ### [\[Part 1\] Building Correlic: Capturing Every Action Your AI Agent Tries to Hide](https://correlic.hashnode.dev/part-1-building-correlic-capturing-every-action-your-ai-agent-tries-to-hide?utm_source=hashnode&utm_medium=feed) Four failed attempts, one kernel breakthrough, and the real cost of making AI agents transparent 19 min read · [correlic.hashnode.dev](https://correlic.hashnode.dev/part-1-building-correlic-capturing-every-action-your-ai-agent-tries-to-hide?utm_source=hashnode&utm_medium=feed) [Apr 4](https://hashnode.com/posts/part-1-building-correlic-capturing-every-action-your-ai-agent-tries-to-hide/69d055ade466e2b762b86353) ### [Do You Actually Know What Your AI Coding Agent Did in the Last Hour?](https://correlic.hashnode.dev/do-you-actually-know-what-your-ai-coding-agent-did-in-the-last-hour?utm_source=hashnode&utm_medium=feed) ~/.ssh/id\_ed25519 was read 47 seconds ago. Not by you. 7 min read · [correlic.hashnode.dev](https://correlic.hashnode.dev/do-you-actually-know-what-your-ai-coding-agent-did-in-the-last-hour?utm_source=hashnode&utm_medium=feed) [Mar 31](https://hashnode.com/posts/do-you-actually-know-what-your-ai-coding-agent-did-in-the-last-hour/69cc587be4688e4edd5b0f26)