Insights from a closed-door roundtable on AI agent safety and governance, chaired by Bruce Schneier and hosted by FireCompass founder Bikash Barai. Participant comments are kept anonymous by agreement. The most useful thing about this roundtable was that nobody pretended to have the answer. A room of senior security leaders spent an hour on AI… Read More »AI Agents Are Doing Real Work. Governing Them Is the Unsolved Problem
Early January, I published a deep dive into why we ripped out JSON-RPC and rewrote our Model Context Protocol (MCP) server using gRPC for our internal AI initiatives. The idea was simple: if you are building enterprise-grade agents, you cannot rely on the “guesswork” of dynamic JSON payloads. You need the strict guarantees of Protobufs.… Read More »Before Google Cloud Backed gRPC for MCP, FireCompass Built It for Our AI Agents
SEBI’s May 5, 2026, circular (HO/13/19/12(1)2026-ITD-1_CIMGI/10873/2026) is addressed to every category of regulated entity in the Indian securities market — exchanges, depositories, brokers, mutual funds, custodians, credit rating agencies, merchant bankers, portfolio managers, investment advisors, and more. Over 10,000 entities. The subject: AI-driven vulnerability detection tools like “Claude Mythos” and the new risk dimensions they… Read More »SEBI AI Guidelines: What 10k+ Financial Entities Must Do
Many objections to belief-state planning are framed as concerns about scalability. In practice, they are concerned about visibility. Systems that avoid explicit belief do not eliminate uncertainty; they merely conceal it. This concealment can appear efficient, but it comes at a cost that is paid later often at the point where decisions matter most. This… Read More »Combinatorial Belief States Are the Cost of Explicit Uncertainty
FireCompass Research has published a new IEEE TecRxiv paper examining a technical weakness increasingly visible in autonomous cybersecurity systems built around large language models. The work, Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability, was authored by two members of the FireCompass research team, including FireCompass co-founder and Head of Research, Arnab Chattopadhayay. … Read More »(IEEE) Belief-State Engines: Solving Uncertainty in Autonomous Security Systems