AI native marketing | Live workshop: Workflow redesign: Automate experiment ideas generation from research
Map a marketing workflow, then build it to run on AI.
In 1.5 hours, build a workflow that turns research data into test ideas: a set of Claude Code skills and one command that runs them, saved to your own GitHub repo.
- Map any marketing workflow and mark where AI runs and where a human stays
- Turn each AI step into a reusable Claude Code skill
- Chain your skills with one command so the workflow runs end to end
- Leave with a GitHub repo containing your skills and the command that runs the workflow end to end
- Rebuild any other workflow the same way after the session
Workshop date: Wednesday, 12 August 2026 | 11 AM CT / 4 PM UTC | 1.5 hours
Trusted by marketers at
Meet your instructors:
Award-winning experimentation lead. Optimized 50+ brands including Bol, Vodafone, eBay, RTL, Rabobank and Online Dialogue. Taught 25k+ students.
Two things stop marketers from delegating to AI: workflows built for humans, and outputs they cannot trust.
Most teams have added AI steps to processes that were never designed for it. Speed goes up. The structure stays broken.
The second gap is output trust. Generic-sounding copy, hallucinated stats, and brand voice that drifts on every run drag marketers back into execution. This is a workflow architecture problem.
This workshop covers both. You leave with a working workflow you built yourself, a GitHub repo of Claude Code skills and a command that runs it end to end, plus the judgment to know where AI should run without you and where a human check is non-negotiable.
📅 Wednesday, 12 August 2026 | 11 AM CT / 4 PM UTC | 1.5 hours
Part 01: Map the workflow and find where it stalls
Before you build anything, you map the workflow honestly: every step, who owns it, which tool does the work, and where it stalls or waits. The messy version is the useful one.
- How to map a workflow as steps, owners, and tools
- Where work stalls, waits, or gets handed off with no clear quality bar
- Outcome: An honest map of the workflow you are about to build
Part 02: Decide what AI runs and what stays human
You draw the line on every step: which ones AI can own end to end, which a human has to keep, and what each AI step must produce before the next one runs.
- How to decide which steps AI owns and which stay human
- What each AI step must output before the next step can trust it
- Outcome: A redesigned workflow with AI and human steps marked
Part 03: Turn each AI step into a Claude Code skill
You build the AI steps as skill files in Claude Code, one per step, each saving its own output so you can see exactly where a run went wrong.
- How to write a Claude Code skill that mirrors how you do the step
- Why each step saves its own output file before the next one runs
- Outcome: Working skill files for the AI steps in your workflow
Part 04: Chain the skills into a research-to-test-ideas workflow
You chain your skills with a single command so raw research data goes in and test ideas come out, running end to end without babysitting each step.
- How one command chains skills into a workflow that runs end to end
- How to turn messy research inputs into testable ideas
- Outcome: A research-to-test-ideas workflow that runs on one command
Part 05: Ship it to GitHub and repeat it for any workflow
You push the finished workflow to a GitHub repo you own, then learn the pattern well enough to rebuild any other workflow the same way after the session.
- How to store and version a working workflow in your own repo
- The repeatable pattern for rebuilding any workflow as AI plus skills
- Outcome: Your skills, command, and workflow live in a GitHub repo, plus a method you can reuse
What you need to make the most of the workshop?
- A free Miro account
- A free GitHub account
- Pro account on Claude preferable (alternatively: Codex)
- CXL will provide access to any additional tools needed for the session
THIS TRAINING IS PART OF THE AI NATIVE MARKETER SUBSCRIPTION:
Become the AI native marketer who ships the work of three.
Every two weeks, CXL helps you build one AI native workflow you can actually use at work. You only prep what matches your level, then build live with a top 1% operator.
AI ASSISTED
AI makes you faster at tasks you already did. The work itself has not changed.
You can tell because: you use AI for drafts and research, then hand off exactly as before.
AI INTEGRATED
You have rebuilt whole workflows around AI and ship work that used to need a specialist.
You can tell because: you no longer wait on a designer, a writer, or an analyst for your core work.
AI NATIVE
You build systems other people run and cover scope that used to take two or three people.
You can tell because: your team runs on workflows you designed.
There are 3 types of marketers. Which one are you?
Learning AI is a second job for most marketers. Join this program. 2hrs per week. CXL does the heavy lifting.
Here’s why marketers choose CXL
Need some more convincing?
Listen to this agency owner explain why he trains his team at CXL