You can do anything you want, just not all at once. Having a good scope helps you clarify what's in the project, what's out of the project, and what it's worth to you when it's complete. The situation of the scope - where you find yourself, the direction you're facing, the destination that has your focus - these are best clarified using the Jobs-To-Be-Done formula. The Buyer’s Real ReasonJobs To Be Done is a strategy framework for understanding why people buy, use, switch, or abandon products. The core idea is that people don’t buy products. They “hire” products to make progress in a specific situation. By applying this framework to AI agents (whom you "hire" to accomplish something) you can identify what, specifically, transitions you from an initial state to a goal state, and why it matters. The basic formula goes like this (replace words in CAPS) - When I am SITUATION, I want to PROGRESS, so I can OUTCOME. 🤖 Managing Multiple AI agentsIf you can define the Job To Be Done for each agent (and subagent) you will move beyond random chaos, and into structured management. Managing AI agents is going to be a valuable skillset in an AI-powered future. My professional advice: hire a couple of agents to do regular tasks for you. Gain some experience. Practice. Fail. Learn. Grow. Ask yourself this one question: what is the job to be done? Here are some JTBD situations that can help inform your scope:
In an era of infinite intelligence, clarity of thinking becomes more valuable.
|
|
Weekly newsletter highlighting the latest AI news, with short video tutorials and copy/paste prompts you can use to improve your skills as an AI operator. As artificial intelligence moves from optional to operational, technical specialists no longer have the advantage. It is those who can supervise and coach AI to improve that will thrive in an AI-augmented future.
🏆 "Kimi K3 is the best performing model on http://nextjs.org/evals, ahead of Fable, reaching a comparable success rate in less time. This is the first time that an open model is ahead of all proprietary ones for this comprehensive web engineering benchmark." - Guillermo Rauch Hello Reader, The conventional wisdom has been: open-source models are 3-6 months behind frontier models. If you wanted best-in-class reasoning, you had to pay for your tokens through a Frontier model. You could pay...
🎭 "It prepares you vastly better for the future to think of models as cartoon characters of arbitrary and growing intelligence living in the cloud than it does to think of them as software or tools." - roon Hello Reader, There's been lots of releases in July 2026. First, Anthropic said after Fable 5 was (re)-released, it would go onto the API, and paid subscribers could only use it via API or usage credits (making it pay-as-you-go, instead of all-you-can-eat) after 7 July. Then, OpenAI...
⚖️ "Companies need to turn their workflows, domain knowledge, and accumulated judgment into AI systems that improve with each use. The companies that build this early will have an advantage that is hard to replicate, regardless of any new individual model capability." - Satya Nadella, CEO of Microsoft Hello Reader, The years I spent as a marketing automation strategist taught me to see the work move through a workflow, end-to-end. I find myself using those skills more frequently, as I hatch...