Lesson 5 of 7

6 min read

Design your first agent (no code)

Time to make it real. You can design a genuinely useful agent in fifteen minutes with nothing but plain writing. Here is the recipe.

By David Silva

The mistake almost everyone makes is starting too big. A great first agent does one small job well. Resist the urge to build an everything-assistant on day one. Follow these four steps and you will have something worth running.

Step 1: Pick one job

Choose a single task from Lesson 2 that you actually want off your plate this week. One job, one clear finish line. "Send me a 5-bullet morning news digest" is a first agent. "Run my life" is not.

Step 2: Write the instructions

Instructions are just plain writing, the same way you would brief a new assistant. Cover four things: what the goal is, how you want it done, what you never want it to do, and when it should stop and ask you.

Example

A real instruction block

"Every morning at 7am, read these three sources and send me the five most important new items as short bullets. Keep it neutral and skip anything older than a day. Never include opinion pieces. If a source is down, tell me instead of guessing."

Step 3: Set the guardrails

Guardrails are the limits that let you trust the agent. Decide them now, not after something goes wrong.

  • What is it allowed to do on its own, and what needs your approval first?
  • What is the spending limit, if it can spend anything at all?
  • Which tools and accounts can it touch, and which are off-limits?
  • How will it reach you, and how often is too often?

Step 4: Choose a model and define success

For a first agent, start with the default model your platform offers. It is almost certainly good enough, and switching later is easy. More important is defining success in one sentence, so you can tell whether the agent is actually helping.

That is a complete design: one job, clear instructions, sensible guardrails, a model, and a definition of success. It fits on an index card, and it is more than enough to launch. In the next lesson we connect your agent to the outside world, which is where guardrails earn their keep.

Key takeaways

  • Start with one small job that has a clear finish line.
  • Write instructions like a brief: goal, how, never, and when to ask.
  • Set guardrails for actions, spending, tools, and contact before launch.
  • Use the default model to start, and write a one-sentence definition of success.

Get the next lesson in your inbox

Up next: Connect your agent to the world, safely. Join the free course and we'll send new lessons and practical ways to put agents to work.

Common questions

A short, clear paragraph or two beats a page of vague rules. Be specific about the goal and the hard limits, and leave the rest to the agent. You can always tighten the instructions once you see how it behaves.