Components · Agents

Human approval

A person approves risky actions; the agent waits.

Lesson
Coming soon
Zone
app
Place it
8 cr on the blank canvas, free inside a problem

At a glance

Did you know
Human-in-the-loop review holds risky actions until a person approves them.
Rule of thumb
Ask only for irreversible or costly actions, or reviewers start rubber-stamping.
Watch out
Minutes-long waits; deadline misses; rejected actions.

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

  • Approvals pile up A finance agent asks a human to approve every payment. Five reviewers take about 20 s each; tasks arrive at 0.5 a second.
  • Sandboxes held during approvals A coding-agent platform runs 7 tasks a second with 3 sandbox runs each, about 3.5 s per run, on a provider that allows 100 sandboxes at once. On 30% of runs the sandbox asks a person to approve a command and stays reserved (and billed) while it waits, about 12 s. Times are scaled: a second here stands for a minute.

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.