Culpepper UX
← PRODUCT BUILDS CASE STUDY — 03

Content Playbook Engine

Over the years I’ve seen teams let their A/B test results languish in spreadsheets no one ever revisits, missing opportunities to turn raw data into content strategy. That’s why I built the Content Playbook Engine — it takes a team's messy experiment history, standardizes it, runs the synthesis and hands them a working playbook on their own infrastructure.

01

The Engine

CONTENT PLAYBOOK — PRODUCT
02

The hard part wasn't using AI. It was knowing where to stop it.

Anyone can feed data to a model and get confident-sounding output. The real design work was deciding what the AI should never be allowed to do. Four rules made the tool trustworthy:

RULE 01

Code makes the calls. The model writes the prose.

Anything a stakeholder reads as a judgment — did this test win or lose, is this stage healthy — is computed from the numbers, in code, the same way every time. If the model re-decided those calls on every run, the same data could tell a different story on Tuesday than it did on Monday. That's not a tool; that's a mood.

RULE 02

Report behavior, never attitude.

The tool says what users did — clicked, converted, dropped off. It never claims what they felt. "Shorter copy won here" is evidence. "Users have commitment anxiety" is a guess wearing a lab coat. Humans can make that inference; the tool doesn't make it for them.

RULE 03

Losses are findings.

A stage where three variants failed in a row isn't a gap in the playbook — it's one of its most useful pages. "Stop adding urgency messaging here" saves as much money as any winning headline.

RULE 04

Show what you can't resolve.

When two tests genuinely contradicted each other, the tool named the conflict instead of averaging it into a fake answer. A playbook that only ever produces tidy wins is lying, and experienced PMs can smell it. The honesty is what makes the rest believable.

These four rules are content design. Not the copy on the buttons — the rules governing what the system is allowed to say. That's what writing for AI actually means.

03

The hard part of every engagement

The hardest part of every engagement isn't the AI. It's the human judgment upstream: figuring out which column in a messy tracker is the real verdict, which tests are actually about content, and what the team's funnel stages really are. The model does the mechanical work. I make the calls that keep the output honest.

See Content Playbook as a consulting engagement → Inside the Care.com internal build →
← Samuel Sauntr Next: Sauntr →