# ClawKeeper, 110 agents inside a deterministic finance hierarchy.

> Case study: ClawKeeper, a 110-agent finance system with deterministic policy engine and Postgres Row Level Security. Production AI at scale.

Canonical: https://alexcinovoj.com/case-studies/clawkeeper

A production AI system for finance ops. Specialized agent roles, policy engine in front, Postgres Row Level Security at the data layer. Every action is auditable.

## Finance teams cannot ship 'agentic' AI on vibes.

Auditability, separation of duties, and approval gates are not optional. Most agent demos collapse the moment a regulator asks who approved what.

## Specialized agents inside a hard policy boundary.

### Role hierarchy

Analyst, controller, auditor, approver. Each agent has scope, tools, and an upstream reviewer.

### Policy engine

Deterministic rules in front of every action with money or PII. The LLM proposes. The policy decides.

### Postgres RLS

Row Level Security enforces tenant isolation and role-level data access at the database, not the app.

### Audit log

Every decision, prompt, tool call, and policy verdict captured. Replayable, exportable.

## Agents finance teams actually trust.

Production deployment with full audit trail. Stack pattern reused across other regulated AI builds. Public source on GitHub.

## Common questions.

## Need agents that survive an audit?

Compliance-constrained agent work runs through Systems Decision Audit at TechTide AI. Architecture notes and code live on alexcinovoj.dev.