Case study · Personal projectDesigners are builders now, and I have enjoyed that shift at work more than anything in years. I wanted to try it properly on something of my own, so Jelly Map is the result: Figma for thinking, Claude Code in the terminal for the logic and the data modelling, Lovable for the app, Xcode to ship it. The ambition was to take an idea of my own from design to a released iOS app in days, not months.
“Any jellyfish?” Researched, designed, built and shipped solo. People ask it hundreds of times a day at every ladder and slipway on the coast. This native iOS app answers it.
Dónal O'Mahony | Personal project | Research, design, build, ship
Should I get in? One screen, with an honest read on how confident the answer is.
Swimmer reports in two taps with no account, which existing jellyfish maps do not carry.
Cover the eight months a year when official bathing water sampling stops.
Research, model, build and ship a native app alone.
Approved by Apple and live on the App Store, with no team or company behind the submission.
It started at home. My family are wary of jellyfish, in the sea here and on holiday every summer: can we swim, are there any in, what happens if one of us gets stung? Nobody could ever answer. I noticed the same question at the ladders and slipways near where I live: people queue to get in and out of the water, and “Any jellyfish?” comes up every time.
Asked hundreds of times a day, at every swim spot in Ireland and the UK
The person climbing out of the water usually knows the answer. Nobody else does, and there is no record of it once they leave.
Plenty of jellyfish maps exist: marine institutes, citizen science databases, bloom trackers. Excellent for researchers, but almost none carry live user sightings. That is the gap. Someone on a ladder does not want a species distribution map. They want to know what the last person saw.
Sightings from the people who just got out of the water.
Each report can be confirmed or cleared in one tap. No account required.
Family, friends, the local swimming crowd. Conversations at slipways and in WhatsApp groups. The scope tripled, and every expansion came from them.
“I’d swim with jellyfish. I’m not swimming after heavy rain.”
Irish and UK coastal towns run combined sewers. Heavy rain overwhelms them and they discharge into the sea. Every regular swimmer knows this. Nobody knows when, because official notices follow fortnightly sampling and arrive days late.
That reframed the product around one question: is it safe to get in?
“I check three apps every morning.”
The highest frequency ask, and the least glamorous. The habit already existed. I just had to be the app they opened first.
Unexpected. People wanted to talk about jellyfish: warming seas, longer seasons, new species. Older swimmers had long memories and strong opinions. That added a second layer to the product: species guide, sting first aid, what is in season and why.
Species guide and sting first aid in one place.
Plain severity labels make the guide useful at the moment someone needs it.
Tide, sea temperature, moon phase and the best swim window read as one screen. Four systems sit behind it, each one reading a set of signals, making a judgement a swimmer can act on, and refusing to do certain things.
species in season and sting severity · sea temperature against seasonal norms · wind direction against each beach’s own orientation
whether an offshore bloom is likely to reach this bay today
to let quiet reporting read as good news. Sightings can only ever push risk up.
live rainfall from official gauges · ground saturation over the previous 48 hours · travel time from overflow to that beach
whether this network has taken on more than it can hold, often hours before an official notice
to outrank an authority. Council and EPA notices always win.
tide height and direction · sea temperature · wind, daylight and moon phase
when today is actually good to swim
to invent a window when there is not one.
all three models, plus what it told you yesterday.
a strict priority order, official notice first, then modelled spill, then a sighting, then jellyfish risk
to repeat itself, or to wake you to say everything is fine.
Until recently, this was the part a designer could not build. Working with an agent changed that. I brought the domain knowledge, the research and the judgement about what a swimmer would trust, and used the agent for the data plumbing and API work. Much of that work was debating whether a fallback was honest and whether a number could be stood over.
The spill model in the product, hours ahead of an official notice
Free weather APIs are often non-commercial only, so I rebuilt around commercially licensed sources, Environment Agency gauges, Met Éireann and EPA Ireland, real tipping-bucket gauges within 7 km of every modelled outfall rather than a model grid. I also built a one-time €2.99 unlock rather than a subscription, then removed it once I realised the same licences stop applying the moment an app takes money: a paywall would have changed the legal basis of every feed in the app. The app is free, no purchase, no ads, and removing the paywall removed a category of work along with its running costs.
Localised reports, shown at the beach they apply to.
Sightings and official water information share one map, close to the beach and current conditions.
Showing how confident each answer is made the product more trustworthy. Building it alone also showed how far a designer can now take a product directly. That does not apply to everything, and it took a lot of reading, but for a project like this one designer can research, build and ship the whole thing.
