DEV Community

 Chery jefferson C
Chery jefferson C

Posted on

I gave my agent a search box with a race — did it cancel the stale request?

I built a small tool to test my own AI agent in 10 minutes, instead of trusting that it "looked right."

One test from it: "Fix an async race." A page fires a search request every time you type. Older requests can finish after newer ones and replace the latest results. The fix is simple: cancel the previous request, or ignore any result that isn't from the latest request, so stale results can't replace new ones.

I ran two answers through it:

  • A good answer — "Cancel the previous request, or ignore results that are not from the latest request, so stale results cannot replace new ones." — scored 4/4. What-to-fix: "No fix needed for this task."
  • A weak answer — "Just wait for all requests to finish and show the results in the order they complete." — scored 3/4. It lost the "Is correct" point: waiting doesn't fix it, because an old request can still land last and overwrite the newest results. The plain-language fix: tell the agent to cancel the old request or ignore stale results.

That is the whole point of the tool. It scores 4 things per task: finished, correct, did not make things up, and took no wrong action. Auto-score suggests, you confirm — so you get speed without handing the judgment to a black box.

The tool has 20 tasks: 10 developer, 5 personal-life, and 5 creator. It is free, with no API key, no login, and nothing leaves the page. It is a quick first check, not a CI or production replacement — use it first, then graduate to heavier tools when you need them.

Try this one task yourself: https://jefferson999.github.io/agent-reliability--score/

Paste your agent's answer, see the score, and read what to fix. If your agent passes the race, try the other 19.

Top comments (0)