Policy Control For AI Agents - Brane

Policy control for AI agents means enforcing explicit rules when an agent attempts to act. Brane provides policy control by evaluating Python policy functions before and after capability execution. Policies receive a structured PolicyContext and return a structured Decision.

Policy Control Loop

Capability + AgentAction + PolicyContext -> Policy -> Decision

This loop lets teams decide what an agent can do based on:

Agent identity
Principal identity
Tenant
Environment
Capability risk
Input arguments
Output
Runtime metadata
Application-specific policy data

Before Policies

Before policies run before the action executes. Use them to prevent unsafe side effects.

@runtime.before_capability("refund_customer")
def refund_limit(ctx):
    if ctx.arg("amount_usd", 0) > 100:
        return Decision(type="deny", reason="Refund exceeds tenant limit")
    return Decision(type="allow")

After Policies

After policies run after execution and can inspect output. Use them to detect oversized outputs, unexpected schemas, PII, secrets, or policy violations after the capability returns.

@runtime.after_capability("call_model")
def block_secret_leak(ctx):
    if "SECRET_KEY" in str(ctx.output or ""):
        return Decision(type="deny", reason="Possible secret in output")
    return Decision(type="allow")

Policy Control Categories

Category	Example policy
Financial control	Deny refunds above a tenant limit
Data control	Allow only SELECT queries
Tenant control	Block cross-tenant actions
Environment control	Block high-risk capabilities in prod
Tool control	Deny destructive tools without approval
Output control	Deny responses containing secrets or PII