Agentic Paved Roads: Shifting Security Left to the Machine That Thinks
Prahathess Rengasamy
fwd:cloudsec North America 2026 · Day 1
In an era where artificial intelligence agents are increasingly writing, shipping, and deploying code to production infrastructure, traditional security paradigms are proving insufficient. Prahathess Rengasamy's talk, "Agentic Paved Roads: Shifting Security Left to the Machine That Thinks," addresses this critical challenge head-on. The presentation highlights a fundamental shift in the software development lifecycle (SDLC), where agents are becoming the primary builders, and even non-technical personnel are leveraging large language models (LLMs) to create applications and data pipelines.
AI review
Rengasamy identifies a real and underappreciated problem — non-technical builders using LLM agents to ship infrastructure, bypassing every security gate security teams spent years building — and proposes a coherent architectural response. The MCP-as-security-API concept is sensible and the demo grounds it in something concrete. But the talk stops short of being genuinely novel research: it's a well-packaged engineering pattern, not a new discovery, and the hard questions (adversarial prompt injection defeating your MCP context, agent hallucination of policy compliance, trust boundaries…