Agentic SRE Advanced By Samson Tanimawo, PhD Published Jun 27, 2026 5 min read

The Action-Limit Pattern: Capping What an Agent Can Do

Hard caps per run, per service, per minute. The cap dimensions that matter, sensible defaults, and the dashboard that catches caps quietly hitting in production.

Cap dimensions that matter

Action caps need at least three independent dimensions. A single cap value is either too tight for high-volume cases or too loose for high-risk ones.

Sensible defaults to ship with

Defaults are conservative on purpose. Raising a cap when evidence justifies it is cheaper than recovering from a thundering-herd outage.

Watching the caps in production

Cap hits are signal, not noise. Distinguishing the correct hits from the bug hits is what makes the dashboard useful.

What happens when a cap hits

Cap behaviour is part of the agent’s contract. Quiet truncation is the failure mode worse than no cap at all.

Eval cases for caps

Caps need eval cases in both directions. Tight caps that fire on routine traffic are as bad as loose caps that miss runaway runs.