{"slug": "how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script", "title": "How I'd Pick the First Task to Hand to an AI Agent (With a 20-Line Scoring Script)", "summary": "A developer published a 20-line Python scoring script for choosing the first task to hand to an AI agent, scoring candidate tasks 1-5 on frequency, time cost, clarity of rules and safety, with a hard rule that any task scoring 1 or 2 on safety is deferred regardless of its total. The framework, illustrated with tasks like sorting email and sending refunds, is packaged into a beginner-oriented ebook for small business owners that includes seven starter agents and a seven-day launch plan. The author cites McKinsey's November 2025 State of AI survey finding that 62% of organizations were experimenting with AI agents while only 23% had scaled them.", "body_md": "AI agents are the big topic this month, but most people I talk to outside tech haven't tried one yet. The most common mistake I see is picking the tool first and the task second.\n\nAs a developer, I'd reverse that. Here's the small framework I use to choose a first task, plus a script you can run.\n\nA chatbot answers when you ask, and then *you* do the work. An agent takes a goal, plans the steps, uses tools (email, calendar, a spreadsheet, a store), does the task, and reports back.\n\nThat difference matters because it changes the risk. An agent can *act*, so a bad choice of task costs more than a bad chatbot answer.\n\nMcKinsey's State of AI survey (Nov 2025) reported that 62% of organizations were experimenting with AI agents, but only 23% had scaled them. Lots of pilots, few things in daily use. A small team that picks one narrow job and makes it reliable can get ahead of that.\n\nList everything you repeat each week. Score each task from 1 to 5 on four things:\n\nAdd the four scores. A high total means a good candidate. One rule overrides the total: if safety is 1 or 2, wait, however high it scores elsewhere.\n\n```\ntasks = [\n    {\"name\": \"Sort and label incoming email\",   \"frequency\": 5, \"time_cost\": 4, \"clear_rules\": 4, \"safety\": 5},\n    {\"name\": \"Answer repeat customer questions\", \"frequency\": 5, \"time_cost\": 4, \"clear_rules\": 4, \"safety\": 3},\n    {\"name\": \"Send refunds\",                     \"frequency\": 3, \"time_cost\": 3, \"clear_rules\": 4, \"safety\": 1},\n    {\"name\": \"Write monthly newsletter draft\",   \"frequency\": 2, \"time_cost\": 4, \"clear_rules\": 3, \"safety\": 4},\n]\n\nMIN_SCORE = 16\nMIN_SAFETY = 3\n\nfor t in tasks:\n    t[\"score\"] = t[\"frequency\"] + t[\"time_cost\"] + t[\"clear_rules\"] + t[\"safety\"]\n    t[\"ready\"] = t[\"score\"] >= MIN_SCORE and t[\"safety\"] >= MIN_SAFETY\n\nfor t in sorted(tasks, key=lambda x: x[\"score\"], reverse=True):\n    flag = \"START HERE\" if t[\"ready\"] else \"wait\"\n    print(f'{t[\"score\"]:>2}  {flag:<10}  {t[\"name\"]}')\n```\n\nOutput:\n\n```\n18  START HERE  Sort and label incoming email\n16  START HERE  Answer repeat customer questions\n13  wait        Write monthly newsletter draft\n11  wait        Send refunds\n```\n\nRefunds never make the list because of the safety rule, even though the task is frequent. That's the point.\n\n```\nmonthly value = (hours saved per week × 4.3 × value of an hour) − tool cost\n```\n\nRecord your baseline *before* you start. Without it you can't tell whether the agent helped.\n\nI'm a developer who works with AI, and I put this into a short beginner-friendly guide for non-technical small business owners: 7 starter agents, a 7-day launch plan, prompt templates, and a launch checklist. It's my first ebook, so I'd really like honest feedback.\n\n[The AI Agent Playbook for Small Business](https://aezad.gumroad.com/l/anksws)\n\nWhat's the first task you'd hand to an agent? Tell me in the comments and I'll tell you how I'd score it.", "url": "https://wpnews.pro/news/how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script", "canonical_source": "https://dev.to/awais_aezad_6c3abb84995ef/how-id-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script-5acb", "published_at": "2026-11-10 07:17:29+00:00", "updated_at": "2026-11-10 07:20:58.011753+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-products"], "entities": ["McKinsey", "Gumroad"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script", "markdown": "https://wpnews.pro/news/how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script.md", "text": "https://wpnews.pro/news/how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script.txt", "jsonld": "https://wpnews.pro/news/how-i-d-pick-the-first-task-to-hand-to-an-ai-agent-with-a-20-line-scoring-script.jsonld"}}