Use cases
Where OrmAI earns its keep.
The same policy runtime shows up wherever an AI agent touches a real database. Here are the patterns teams reach for most — each with the OrmAI primitives that carry the weight.
Multi-tenant SaaS
Let AI agents query a shared multi-tenant database without ever crossing a tenant boundary. Every query is scoped by tenant_id automatically.
Read the pattern →Customer-support agents
Give a support copilot read access to orders, tickets, and accounts — with PII masked and destructive operations off the table by construction.
Read the pattern →Internal data agents
Let internal tools and Slack bots answer questions from production data with per-principal policies and a tamper-evident audit trail.
Read the pattern →Analytics agents
Point an analytics agent at production with aggregate-only tools, capped scans, and masked identifiers — fast answers, no raw row dumps.
Read the pattern →Agentic writes
Let agents create and update records safely: approved models only, a required reason on every write, row caps, and a full audit trail.
Read the pattern →MCP database tools
Expose your database to Claude and other MCP clients as typed, policy-checked tools instead of a raw SQL endpoint over the Model Context Protocol.
Read the pattern →