From handing off one task — to setting up help that runs itself.
An agent is a handoff that repeats
Design one agent for your week
Your own agent recipe card
Quick catch-up, whether or not you've done the first two guides.
Copilot, ChatGPT, Claude, Gemini, Grok — or your company picked for you. Either way, you're set.
Spotting the repetitive, draining, blank-page tasks and letting AI take the first pass.
Take a handoff you already do — and set it up so you barely have to ask twice.
Forget the sci-fi. Strip away the buzzword and an "agent" is something simple: instead of asking AI to do a task once, you set it up so it does that task again and again — with less and less input from you.
You ask once. You get one answer. You start over next time.
You save the instructions so you're not retyping them every time.
One request triggers several steps — draft, check, format — in a row.
It knows your context, runs the steps, and only checks in when it needs you.
Whether you build it in Copilot, a custom GPT, a Claude Project, or a Gemini Gem — every agent, at any level, comes down to these three.
"Turn my meeting notes into a summary and action items." One clear, repeatable task.
Who you are, your format, your tone, your rules. Set once, so you never re-explain.
You paste something in, say a keyword, or (more advanced) it kicks off on a schedule.
Think of one handoff you already do. Say it out loud as a "job." Got it? You've done the hardest part.
Same three ingredients, very different tools. Start wherever you are — you can always climb.
Built into tools you already have. No coding, ready in about ten minutes. Match it to your ecosystem.
Why it's the right start: you set the instructions, upload a few files, and it remembers your context every time. That's a real agent.
For agents that touch multiple apps and run real business workflows. A visual canvas, but a real learning curve.
Why here: these link an agent to your email, CRM, files, and databases — with governance controls. At work, only connect what your organization approves.
Code-first, for engineering teams building custom, production-grade agents.
Worth knowing: even here, the idea's the same — job, context, tools. You're just writing it instead of clicking it.
Which tier fits you today — not where you think you "should" be? Most people start at Tier 1. That's exactly right.
Which of these would you actually set up? Pick one — that's your candidate for the exercise below.
An agent does more on its own — so the guardrails from Part 2 matter even more here.
The more steps it runs, the more you check the output before anything goes out.
At work, only connect an agent to data and systems your organization approves.
Run it with you watching a few times before you trust it to run on its own.
Whatever you build, know how to pause or turn it off. You're always in control.
Fill in the three ingredients for one agent you'd actually use. Then hit Print to save it — it won't save on its own.
Read your recipe card back to yourself. Missing an ingredient? That's the gap to fill before you build. Bonus: text it to one person — saying it out loud makes it real.
Not ten. One. Set it up, run it a few times supervised, and see how it feels.
Tell one person the agent you're building this week. That's your check-in — have them ask you next week if it's running.