Bhaskar Gurram

Trust layer for document→JSON extraction & AI agents: calibrated per-field confidence + source grounding + accept/review abstention on any OCR/VLM. Ships VerifyDocBench, a novel grounding-conditioned conformal method, and an MCP server.

A reversibility layer for agentic tool use — a transparent MCP proxy that classifies which tool calls can be taken back, synthesises inverse operations, keeps a durable cross-server undo log, and interrupts you only for genuinely irreversible actions.