Problems / AI systems, medium

Agent: a slow tool and a tight quota

An agent takes 6 steps per task at 15 tasks a second. Every step calls a tool server with 8 slots that takes 300 ms, and the model allows 4,000 requests a minute.

Solve it in the labTake it as a mock interview

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 97%, p99 ≤ 30 s.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 4; 1 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.

The traffic

15 requests a second for 60 seconds: 100% task (reads).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
API gatewayAPI gatewayTraffic enters here.Calls Agent orchestrator.Gateways centralise auth, rate limits and routing so each service does not reimplement them.100000 slots · 600,000 calls/min
Agent orchestratorAgent orchestratorAPI gateway forwards to it.Calls LLM endpoint, Tool server.An agent loops: think, call a tool, read the result, repeat until done.300 slots · 6 steps
Tool serverTool / MCP serverAgent orchestrator calls it.Tools give the model actions such as search or database queries; each call is another round trip.8 slots
LLM endpointLLM endpointAgent orchestrator calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.120 streams · 4,000 calls/min

More ai systems problems