rye-agent-ops

Prevent LLM agents from violating PostgreSQL row-level security by directing them to use official Rye SQL helper functions instead of raw queries. This enforces RLS-compliant session setup, team boundaries, and immutable assertion rules.

Assertion lifecycle management for AI agent database workflows ensures agents safely read and write data without corrupting knowledge states. It enforces provenance tracking, separates planned work from future-effective truth, and validates knowledge candidates.

Set up a Rye session context for safe agent data retrieval by configuring RLS-compliant sessions and using official Rye SQL helper functions. This allows agents to retrieve scoped node information while maintaining audit requirements and team boundaries.

Yes, you can use LLM agents to ingest external CRM data into Rye-managed PostgreSQL. The workflow helps agents connect external domain tables to the Rye graph, create validated knowledge candidates, and track table changes via CDC triggers without bypassing access controls.

Yes, writing agent workflows with Rye SQL helpers supports future state scheduling. It enforces the separation of planned work from future-effective truth, allowing agents to safely schedule future deal stage changes while maintaining provenance tracking.

Raw SQL queries cause data leaks in LLM agent PostgreSQL operations because they bypass row-level security policies, assertion lifecycle rules, and audit requirements. Using official Rye SQL helper functions ensures all agent actions are traceable and compliant.