At a glance
- Did you know
- A policy engine checks each tool call against what this agent, user and data may do.
- Rule of thumb
- Deny by default for side-effecting tools; log every decision.
- Watch out
- Over-strict policies stall agents; policy store becomes a hot path.
Its settings in ScaleMySystems
What you can change on it in the lab, and what each number does.
- Concurrency (slots)
- Calls it can work on at once (per instance when autoscaling). Needed slots ≈ calls per second × seconds each takes. Extra calls wait in the queue, then are rejected.
- Queue capacity
- Calls allowed to wait for a free slot. A bigger queue absorbs bursts but adds waiting time; 0 rejects straight away.
- vCPU
- CPU cores available. Needed ≈ calls per second × CPU per request ÷ 1000. Above about 90% busy it slows down and may crash.
- CPU per request (ms)
- CPU time each call burns. Part of what the component is; make the code cheaper to lower it.
- Latency (p50) (ms)
- Typical time one call takes here, before any calls it makes itself. Slots are held for this long.
- Latency (p99) (ms)
- The slowest 1% of calls. Callers must set their timeout above this or they cut off healthy calls.
- Timeout to dependencies (ms)
- How long it waits for each call it makes before giving up. Set it above the dependency’s p99 but low enough that a dead dependency does not hold every slot.
- Error rate
- Share of calls that fail on their own (bugs, declines, flaky tools). An agent that calls it on every step multiplies this.
- Quota (req/min)
- Calls allowed per minute (an API key or provider limit). Calls over it get 429s. Needed = calls per second × 60, with headroom.
Problems that start with it
- Policy check on every tool call Every tool call is authorised by a policy engine with 8 slots and 30 ms per check.
- Policy service on the chat path Every chat checks a data-access policy service with 8 slots and 40 ms per check.
- Multi-tenant RAG: the permission filter Each customer may only see its own documents, so every retrieval passes a document-ACL filter after hybrid search. The filter has 2 slots and takes about 60 ms; questions arrive at 60 a second.
- Coding agent platform: the model provider goes down A coding agent platform: each task is a loop of model calls, tool calls, code runs in a sandbox and checkpoints, minutes long. Twenty seconds in, the model provider has an outage for 30 seconds. Every step that needs the model fails, and with it the whole task: two in three tasks are lost.
Full lesson coming soon
Lessons are being added one component at a time: how it works, its settings, a live exercise to break and fix it, interview questions and a short check. See the Circuit breaker lesson for what one looks like.