Bringing genetic predictions to life

BabyPeek offered expecting parents predictions about their baby's traits, from eye color to hair texture, using the blood sample already collected for a clinical screening test.

I designed the experience to help parents picture their baby while understanding that every prediction was a probability. The product also had to give people a reason to discover it, pay for it, and share the experience.

Every trait result opens with a sentence a parent can repeat out loud, on a card colored as the trait itself. The probability sits underneath it, and it shows the full spread rather than only the winning answer. Green or hazel at 70%, blue at 25%, brown at 5%, with each bar colored as the eye color it stands for.

That was the honesty mechanism. Naming the alternatives and their weight is what stops a confident headline from becoming a promise.

Every screen carries an Other factorssection, which is the part I argued hardest for. Eye color admits that babies' eyes often change from blue to brown in the first two years. Hair texture lists products, hormones, humidity, and ethnicity, each with its own drawing. It is where the product volunteers what it cannot know, inside the experience rather than in a disclaimer nobody reads.

The science sits behind progressive disclosure. Open “How it works” and you get eumelanin and pheomelanin, or a drawing of how a follicle's shape decides whether a strand curls. Closed, the screen is a warm sentence and a number.

I combined behavioral analysis with 20 interviews across purchasers and non-purchasers who had reached the information page. I wanted to understand why people acted or stopped after showing initial interest.

I synthesized six composite personas and shared the findings with product, marketing, and engineering leaders before feature work. Each persona pointed to a different opportunity or a limit to what we could change.

The funnel showed where to act: 45% of patients opened the BabyPeek information page, and 4.5% purchased at $99. The persona signals helped explain what we could try. I combined those signals with funnel location and feasibility to frame three growth hypotheses.

The Frugal Shopper wanted BabyPeek but could not justify the price. The Adventurist already recommended it to others. Share to unlock connected those signals: parents could earn free access by posting about BabyPeek, helping others discover it.

Legal did not approve unconditional free access alongside a clinical test, so access had to be earned. Buying remained available for people who were not ready to announce their pregnancy publicly.

Users understood the exchange but struggled to complete it. They did not know what to post, got lost in the promo code process, and missed verification below the fold.

I brought posting, verification, and unlocking into the first screen, applied the promo code automatically, and provided sample captions and images as optional help.

The Advice Seeker showed that a partner influenced the decision. I explored ways to make anticipation and participation part of BabyPeek's value, while keeping the science clear for people who needed more evidence before buying.

Our PM proposed an online guessing game that used parents' traits before revealing the baby's prediction. I wireframed it to show the problem: the sequence implied that parents' answers produced the prediction. It actually came from the baby's DNA. We agreed to shelve that version.

I kept the shared reveal and changed the mechanism. I asked coworkers to invite me to baby showers, attended a few, and observed what people played. I then designed three printable games where friends and family could participate without suggesting their guesses generated the genetic prediction.

Peek-a-Boo is the one I'm proudest of. Players rank how likely each eye color is, then guess the percentage chance of curly hair or cilantro aversion. Scoring gives five points for an exact match, three if you land within 5%, one if you land within 10%.

That is probability calibration as a party game. To play it well you have to think in distributions and accept that a confident answer can still be wrong, which is exactly what this product needed people to understand. Nobody sits through that explanation. They will play it at a baby shower.

The page copy does the same job in one line, reaching for something people already reason about correctly:

The three hypotheses were where we started, not where we stopped. Over the following year I shipped most of the option space: lifecycle marketing, influencer collaborations, checkout experiments, science clarification, customer reviews, shareable trait results, the reveal moments above, and a price test across $149, $99, $29, and $9.99.

Two things we chose not to build: a physical keepsake book, too expensive to produce for the return, and partner participation. The shipped landing page is the clearest record of everything else.

BabyPeek's conversion rate increased by 75%, but it missed its standalone revenue target. My read was that conversion improvements alone could not overcome the limited audience and price needed to make it a meaningful revenue line.

The team repositioned BabyPeek as a reason for patients to ask their doctor for UNITY, the clinical screening test it accompanied. Its value shifted from direct consumer sales to supporting adoption of the clinical product. The lesson was to evaluate whether experiments strengthened the business model, alongside whether they improved the funnel.

Legal constraints produce better design problems

The inducement restriction that stopped us handing BabyPeek out for free forced a mechanism that was simultaneously compliant, viral, and respectful of the user. It was a better answer than the one we were prevented from giving.

The honest version of a feature is usually still a good feature

The guessing game didn't need to be killed. It needed the part that misrepresented the science removed. Getting to that took wireframes rather than argument, and the result kept what my PM was right about.

What I would do differently

Research gave us signals about price, trust, and shared experience. I should have tested which motivations were strong enough to drive action before scaling a campaign. Interest in sharing with family did not mean people were ready to announce a pregnancy publicly. I would use smaller tests to separate those motivations before committing to a larger launch.