OG House
The conversation · No. 02

I let AI make our ads for a quarter. Here’s what it couldn’t do

Handing creative to AI, cutting the free trial to three days, and why his first hire was an analyst, not a buyer.

CreativeAI in growthRetention and monetisation

Marcus Webb has run user acquisition for subscription apps since the early days of the App Store, most recently as Head of UA at a top-20 fitness app. We covered three decisions: handing creative to AI, shortening the free trial, and who to hire first.

1. Letting AI make the ads for a quarter

The setup. “Creative was our bottleneck. We needed forty new concepts a month to keep fatigue at bay and we were shipping twelve.”

The call. “For one quarter AI drafted scripts, edits and variations, and humans approved. One rule: every concept had to start from something a real subscriber had said.”

What happened. “Volume tripled and the cost of each concept collapsed. But the two concepts that actually moved trial starts both came from a customer interview a human sat in on. The machine was brilliant at the second idea and useless at the first.”

“AI made us ten times faster at producing ads, and no faster at knowing what to say.”
Steal this. Split creative in two: let AI scale proven concepts, and keep humans finding new ones in real customer language. Measure the two separately.

2. Cutting the free trial from seven days to three

The setup. “Most of our seven-day trials were decided by day two. The other five days mostly gave people time to forget they’d signed up.”

The call. “We tested three days against seven by market. Product worried about trial starts falling; I worried about paying for installs that never had a chance to convert.”

What happened. “Trial starts dipped a little, trial-to-paid rose a lot, and refunds fell. Net, three days won in every market but one, where seven still did better.”

Steal this. Look at when your trials are actually decided. If it’s day two, a seven-day trial is mostly a forgetting window.

3. Hiring an analyst before another buyer

The call. “My first hire when the team grew wasn’t a media buyer. It was an analyst who could tell us which of our numbers to trust. Every buyer after that got better because the numbers did.”

Steal this. If your buyers argue about whose numbers are right, your next hire is an analyst, not a buyer.

What he’d do differently

“Measure concepts and variations separately from day one. We celebrated volume for a month before we noticed the new ideas had dried up.”

If I were starting today. Speed is cheap now. Knowing what your customer actually wants to hear is not.
02
Member of the House · No. 02 Marcus Webb Former Head of UA at a top-20 fitness app. Has run user acquisition for subscription apps since the early days of the App Store. Marcus Webb’s profile