Spend Control for Azure AI Foundry Agents
Foundry agents combine Azure models with tool access — and tools spend. The guard enforces the budget on Microsoft's platform.
Why Foundry agents overspend
Azure model token costs at agentic volume.
Tool calls hit paid APIs and services mid-task.
Azure budgets cover Microsoft; the rest is ungoverned.
How it works
Add the guard as a tool. Before any spend, the agent gets APPROVED, BLOCKED, or FLAGGED.
Rules that fit
Per-agent daily ceiling.
Merchant allowlist for paid tools.
Velocity limit on retry loops.
Guard call
from sipi_guard import sipi_guard
decision = sipi_guard(amount=45, merchant="api.vendor.com", category="api")
# APPROVED | BLOCKED | FLAGGEDFoundry for the app; the firewall for the money.
FAQ
Does this replace Azure budgets?
No — keep Azure budgets. The firewall covers every merchant.
Can I cap per agent?
Yes — per-agent rules.
Related
Stop the next $12,400 night.
One API call (or MCP tool) in front of every agent transaction — APPROVED, BLOCKED, or FLAGGED, deterministic, ~5 ms, fully logged.
See plans — from $99/mo Try a live check