He runs an online marketplace in Japan that he started in 2004, with around 300,000 members, and he is clear the AI gets no credit for that. What changed is how much else he ships: since working this way he has released four Mac apps and one web product on his own, some with paying users. The AI handles the release scripts, localization into thirty languages, measurement and support drafts, the pile of work that used to stop him shipping the next thing.
During a flash sale on his petals.team site he checked analytics and found zero events, ever, because PostHog had never been added. Through the PostHog MCP connector in an AI chat he spotted, diagnosed and fixed it, saved a 3 step registration funnel, and set a weekly digest to land in Slack every Thursday.
The user's agent, nicknamed for its savings habit, cancelled Squarespace, migrated the site to Shopify, and discovered his Apple TV subscription was already free through his Chase Sapphire Reserve, activating that instead of paying.
Added the AI rules and skills to split Terraform PRs into the smallest mergeable units, resulting in cases like 40 PRs with 38 approved and merged immediately.
BananaGroup now runs its Medicare Supplement sales on its own app, with prospects, quotes, enrollment alerts and the sales pipeline in one place, built in a couple of days. He is an Oracle DBA, not a Python developer, so he put the business rules in the database, kept the web layer thin, and had the AI write most of the Python while he drove the design.
Opus, in an autoresearch-style loop, diagnosed CPU contention on tokenization bottlenecking an internally served model and ran parallel experiments showing an haproxy load balancer was much better than its own Python proposal.
This only partly worked. Worth knowing before you try it.
He set up a pipeline he wrote himself. Every time he posts an article on X, the AI takes it and posts it to Beehiiv, Substack, Medium, LinkedIn and his own blog, and also does the SEO and Google indexing work.
At the same accounting firm, staff batch upload client bills and the agent reads each one, decides whether it belongs in payables, receivables, or the cash book, and posts it into AutoCount after a person reviews and amends the lines. The firm has run the setup in production for three months.
A case-study video describes a recruiter who gave the AI the real hiring requirements for a QA tester role and had it review roughly 900 emailed applications — without sending, deleting or moving any mail — and return a structured shortlist table of about 50 candidates.