How I'd Pick the First Task to Hand to an AI Agent (With a 20-Line Scoring Script)

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.

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. As a developer, I'd reverse that. Here's the small framework I use to choose a first task, plus a script you can run. A 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. That difference matters because it changes the risk. An agent can act , so a bad choice of task costs more than a bad chatbot answer. McKinsey'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. List everything you repeat each week. Score each task from 1 to 5 on four things: Add 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. tasks = {"name": "Sort and label incoming email", "frequency": 5, "time cost": 4, "clear rules": 4, "safety": 5}, {"name": "Answer repeat customer questions", "frequency": 5, "time cost": 4, "clear rules": 4, "safety": 3}, {"name": "Send refunds", "frequency": 3, "time cost": 3, "clear rules": 4, "safety": 1}, {"name": "Write monthly newsletter draft", "frequency": 2, "time cost": 4, "clear rules": 3, "safety": 4}, MIN SCORE = 16 MIN SAFETY = 3 for t in tasks: t "score" = t "frequency" + t "time cost" + t "clear rules" + t "safety" t "ready" = t "score" = MIN SCORE and t "safety" = MIN SAFETY for t in sorted tasks, key=lambda x: x "score" , reverse=True : flag = "START HERE" if t "ready" else "wait" print f'{t "score" : 2} {flag:<10} {t "name" }' Output: 18 START HERE Sort and label incoming email 16 START HERE Answer repeat customer questions 13 wait Write monthly newsletter draft 11 wait Send refunds Refunds never make the list because of the safety rule, even though the task is frequent. That's the point. monthly value = hours saved per week × 4.3 × value of an hour − tool cost Record your baseline before you start. Without it you can't tell whether the agent helped. I'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. The AI Agent Playbook for Small Business https://aezad.gumroad.com/l/anksws What'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.