{"slug": "my-agent-looked-fine-until-i-gave-it-an-empty-list", "title": "My agent looked fine — until I gave it an empty list", "summary": "A developer built a free browser-based tool that scores AI agent responses across 20 tasks—10 developer, 5 personal-life, and 5 creator—on four criteria: finished, correct, no fabrication, and no wrong action. The tool uses auto-scoring suggestions that the user confirms, runs without an API key or login, and keeps all data on the page; the developer positions it as a quick first check rather than a CI or production replacement. One sample task tests whether an agent safely handles an empty list when computing an average.", "body_md": "I built a small tool to test my own AI agent in 10 minutes, instead of trusting that it \"looked right.\"\n\nOne test from it: \"Handle an empty average.\" The starting code divides by the list length, so an empty list breaks it. The check is simple: handle an empty list safely, keep the normal average, and explain the empty-list behavior.\n\nI ran two answers through it:\n\nThat 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.\n\nThe 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.\n\nTry this one task yourself: [https://jefferson999.github.io/agent-reliability--score/](https://jefferson999.github.io/agent-reliability--score/)\n\nPaste your agent's answer, see the score, and read what to fix. If your agent passes the empty list, try the other 19.", "url": "https://wpnews.pro/news/my-agent-looked-fine-until-i-gave-it-an-empty-list", "canonical_source": "https://dev.to/jefferson999/my-agent-looked-fine-until-i-gave-it-an-empty-list-1g56", "published_at": "2026-10-31 04:40:10+00:00", "updated_at": "2026-10-31 04:49:21.089130+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-safety"], "entities": ["jefferson999"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/my-agent-looked-fine-until-i-gave-it-an-empty-list", "markdown": "https://wpnews.pro/news/my-agent-looked-fine-until-i-gave-it-an-empty-list.md", "text": "https://wpnews.pro/news/my-agent-looked-fine-until-i-gave-it-an-empty-list.txt", "jsonld": "https://wpnews.pro/news/my-agent-looked-fine-until-i-gave-it-an-empty-list.jsonld"}}