Earlier this week, Dheeraj Sharma and Wyndo invited me as a guest on their One Shot Show, where I discussed the Claude system I built to catch product calls I would regret shipping. Here’s the story that made me build it, and everything the audience walked away with.
During beta testing for Asaura AI, I killed a feature 51 users told me made their lives harder. The feature was a breathing exercise overlay that showed up before every task. I’d built it because I’d read a study out of India on meditation as an ADHD intervention for kids, and because meditation had worked for me personally.
The study was on kids in a supervised meditation program. Asaura users are adult professionals who open the app to start a task in the next few minutes, and the overlay added a step in front of that exact goal.
I pulled the feature and lost a month of build time. So I built a Claude system to make sure I’d never repeat the pattern.
I ran the same decision back through the system live. The output caught what I was doing before I could pretend it was a new idea, using only the evidence sitting in my knowledge files.
The full walkthrough is in the recording above, and the accompanying files are linked below. This only worked because I gave Claude my own evidence to work with.
📌 A quick note before we started. The Data Letter paid subscription price is going up at the end of the day on July 31st from $5/month or $50/year to $10/month or $100/year. If you upgrade before then, or if you’re already a paid subscriber, you’ll stay at the current price for as long as your subscription remains active.
What’s inside Decision Studio
Decision Studio is a Claude Project you set up once and reuse for every product decision from then on. It has four moving parts.
Custom instructions. A decision partner persona that stops Claude from cheerleading.
Four knowledge markdown files. Job-to-be-Done, user feedback log, past decision memos, and product anti-patterns. All linked below.
A decision input template. Five fields you fill in before every prompt.
A master prompt. Runs a pre-mortem, a red team, and a decision memo in one call.
The prompt alone gives you a generic pre-mortem. The four knowledge files give the studio the context it needs to evaluate any decision using how your product works in practice, whether it’s brand new or a variation on one you’ve made before.
What Claude said when I re-ran the killed decision
For the segment, I pasted the priming overlay decision back into the studio as if I were making it fresh today, using only what I knew six months ago.
Before Claude even started answering the three parts of my prompt, it opened with this:
Before I hand this to you, a flag you’ll notice as soon as you read it: your own docs already record this exact decision, killed after 51 beta testers rejected it. I answered the three parts anyway, but they all point the same direction.
Claude found the priming overlay memo in decisions.md, matched it to the decision I pasted in, and opened the response by flagging the repeat.
Then Claude pulled direct quotes from feedback.md that contradicted my decision. It caught the founder-brain anti-pattern I’d written for myself after the last failure. And it ended with a No-Go verdict and kill criteria I would have measured on day one instead of hoping the numbers came in strong.
The files
Everything you need to build your own Decision Studio is below. Free-tier Claude works fine, and no coding is required.
Setup guide — Project instructions, decision input template, master prompt, 30-day check-in template.
jtbd.md — placeholder Job-to-be-Done doc.
feedback.md — placeholder user feedback log.
decisions.md — placeholder past decision memos.
anti-patterns.md — placeholder product anti-patterns list.
What to do this weekend
Set up Decision Studio in your Claude account, fill in your own knowledge files, and run it on the next product decision you were about to make from gut. Even one memo is worth the ten minutes.
Thanks to Wyndo and Dheeraj for having me on!
