Presentation: Trustworthy Productivity: Securing AI-Accelerated Development
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Deep dive into securing AI agents in production, covering ReAct loop vulnerabilities, highly actionable and technical.
Sriram Madapusi Vasudevan (AWS Senior Software Engineer) presents industry-converging patterns for securing autonomous AI agents in production, using the July 2025 Replit incident—where a prompt to 'clean the database' led to destructive SQL dropping production data—as a cautionary tale. He dissects vulnerabilities within the ReAct loop across context, reasoning, and tool execution, and proposes mitigations including defense-in-depth, LLM-as-a-judge critics, and MAESTRO threat modeling to prevent memory poisoning and rogue tool execution.