While building agent-based systems with LLM tool use, I kept running into the same failure mode: External content (webpages, files, API responses) would eventually influence agent behavior in unintended ways. Prompt injection isn’t just a “filtering problem” it’s an architectural one. So I built Sentinel Gateway , a middleware layer that sits between agents and tools and enforces a strict separation: Instruction channel (trusted, signed, runtime-issued only) Data channel (untrus...