Generic agents can do anything — which is exactly the problem. Custom agents in containers behind an inference proxy create a production architecture where security is structural, not aspirational.
A high-performance Rust proxy that lets Claude Code, Continue.dev, ZeroClaw, Mistral Vibe — or any AI coding agent — use Snowflake Cortex AI models as their backend. Optional prompt policy enforcement included.
A defense-in-depth security architecture for AI agents and inference workloads — covering network isolation, identity propagation, authorization, data protection, and auditing under the EU AI Act, DORA, and NIS2.
How to exchange OIDC JWT tokens for short-lived Snowflake PATs and use them as Bearer tokens for MCP server authentication — with automatic rotation and cleanup.
How to use Postgres 17 as a transparent encryption proxy so that data stored in Snowflake is always AES-256 encrypted at the column level — with your own key, under your own control.
How to decrypt PGP/GPG-encrypted files directly inside Snowflake using Python UDFs and the pgpy library — no external compute, no middleware, no key in transit.
A step-by-step guide to having Snowflake automatically detect failed login attempts and raise incidents in your SIEM or XDR — no external code required.