OwnStory

OwnStory began as a digital memorial platform — a niche product with steady but limited demand. The founder saw a larger opportunity: pivot into a **private digital story platform** for life moments — birthdays, weddings, graduations, travel, new babies, memorials — positioned explicitly against social media (private by default, owned by the user, designed for gifting rather than posting). Each story gets a QR code that attaches to a physical gift, so the digital and physical sides of a keepsake live together. The engineering challenge was building out the AI infrastructure to support that pivot while keeping the platform reliable for existing customers.

I joined the engineering team during this pivot, working alongside the founder/CEO with a lean process between an idea and shipped code. Three months from pivot decision to production launch. AI infrastructure had to be cost-aware from day one because budget ceilings were real and an unbounded LLM bill was a company-level risk.

I contributed to the AI infrastructure behind the pivot, alongside product features including a featured-stories editor, admin user filters, scan-tracking for QR-linked stories, and collaborative storytelling (multiple contributors per story). *(I also contribute to a separate AI platform the same team is building — that work has its own case study.)*

**Cost-aware AI infrastructure from day one.** An unbounded LLM bill was a company-level risk for a small team mid-pivot, so cost controls had to be part of the infrastructure from the start rather than bolted on after a surprise invoice. I worked on the parts of the AI pipeline that needed to stay within that budget envelope while the product itself was still changing shape under a 3-month deadline.

The new private story platform is live in production, with the original memorial product continuing to serve existing customers throughout the pivot — no migration window. AI infrastructure has stayed within budget while supporting real user traffic.

Three months for a pivot of this scope was genuinely tight. The thing I'd reconsider is being more aggressive about feature flags earlier — small teams tend to ship without them because flags feel like infrastructure when features feel urgent. But the moment a regression hits, having flags means the rollback is scoped to the broken thing instead of a full revert. I'd push for treating them as table stakes next time.