Signal Roads

Agent Foundations
for Marketers

An AI agent in an editor you control, put to work on real marketing tasks. No code or terminal experience needed. Works with Claude, Gemini, or Codex.

8 lessons · ~1.6 hrs

Start the course

Subscribe to get new lessons and courses as they land.

Prerequisites None. You don’t need to code or to have used a terminal before. A laptop and access to one AI coding tool (Claude, Gemini, or Codex) is enough.

What changes for you

This course teaches two things. Handing an agent whole pieces of marketing work on your own files, instead of asking a chat for answers and assembling the rest yourself. And building a workspace that compounds: your context and standards live as files that load themselves, improve with every task, and move with you to whichever model comes next.

  • Hand the agent whole pieces of work, a landing page, a launch email, a research pass, and get finished work back instead of text to assemble
  • Get first drafts that sound like your company, because the agent reads your positioning, voice, and rules before every task
  • Put your whole stack in reach, connector or not, so work crosses your analytics, CMS, and email platform without you ferrying data between tabs
  • Run it on real work without fear, with an undo button under every change and a permission gate in front of anything you could not take back
  • Leave with a workspace that compounds: standards that apply themselves, and memory that lives in files you own, portable to whichever model wins next

Curriculum

Part 1 · Understand

  1. 1What is an AI agent? A marketer's guideThe shift that makes agents click, before any setup8 min
  2. 2How to pick and set up an AI coding toolPick your editor and agent, set it up, and run your first task15 min

Part 2 · Build

  1. 3How to build a landing page from an AI promptOne prompt becomes a real page in your browser, nothing plugged in12 min
  2. 4AI context file: make an agent sound like your brandThe file that turns generic output into your voice and your calls12 min
  3. 5Connect an AI agent to your data: MCP and API keysMCP and API keys, scoped read-only first so nothing breaks14 min

Part 3 · Systematize

  1. 6AI models and credits: how to optimize usageMatch the model to the job and stop wasting credits on cheap work11 min
  2. 7Git and GitHub, explained for non-codersThe undo button, the online home, and going live10 min
  3. 8AI agent skills: turn workflows into systemsFrom one-off tasks to reusable skills you write yourself12 min
Nicolaas Spijker

I'm Nico. I run real client work through an agent in my editor every day, and I write about it in the Build Log. This course is the how-to version: the same workflows, set up so you can run them yourself.

Get the rest as I write them.

All eight lessons are drafted. I keep refining them in the open, no set schedule, just when they're good.