What I Built During the Lovable Hackathon was a weekend challenge to turn an idea into a working product. I built Spark, an Applied AI Idea Generator, to help organisations find the right first AI build. Here is what I learned.
What I Built During the Lovable Hackathon
What can you actually build with AI in one weekend? Not a brainstorm, and not a slide deck. I wanted something another person could open, use and understand. I applied for Season 4 of the SheBuilds Lovable Hackathon, and I was thrilled to be accepted.
SheBuilds is a global community of women building with AI. Lovable is an AI app-building platform where you describe what you want in plain language, review what it builds and keep refining through conversation. My concentrated build happened over Saturday and Sunday morning here in Ireland.
The problem behind Spark
When I speak to business leaders, comms teams or public servants, they understand the AI examples and leave with pages of notes. But one question stays hard: what should we build first? People can name a broad area like marketing, HR or finance. Turning that into one clear, bounded AI job is the struggle.
How Spark works
You pick the part of your organisation that needs help, then name the job like a new digital hire, such as Proposal Pro or Inbox Assistant. You describe in a few plain sentences what that role would do. Spark turns it into a one-page plan with five stages:
- Starts: what triggers the work
- Reads: what information the AI needs
- Works: what the AI actually does
- Approve: what a person must review and authorise
- Lands: where the finished work goes
That structure stops the idea becoming “we need an AI agent that does everything.” Spark also asks for your time and hourly rate to estimate the value of time returned. I am careful here: it is an estimate based on your inputs, not a promise of savings. There is also a voice support feature if you get stuck.
What I learned about vibe coding
Vibe coding can dramatically shorten the distance between an idea and a working first version. But it does not remove product thinking. I still had to decide who Spark was for, which questions it should ask, what the output should contain and what claims it should not make.
When building gets faster, it is tempting to add too many features or mistake a working screen for a validated business. A hackathon product still needs user testing, accessibility checks, security review and evidence that it solves the problem.
I did not just explain applied AI this weekend. I built a tool that helps other people find their own applied AI opportunity. So ask yourself: which repetitive job would you most like to take off your desk?
If you want to build your AI literacy and skills, I can help
📚 Grab AI Playbook on Amazon, the perfect podcast companion.
📰 Subscribe to Human in the Loop, my LinkedIn Newsletter
🎓 Take the CPD Accredited AI Playbook Diploma
📞 Book a call at digitaltraining.ie
Key Statistics
– SheBuilds Season 4 was an application-based, three-day virtual event.
– The event ran from the 15th to the 17th of October.
– Spark’s one-page plan follows five stages: Starts, Reads, Works, Approve and Lands.
– The concentrated build happened over Saturday and Sunday morning in Ireland.
– By Sunday morning, Spark was a working product with a new name, a clearer visual identity and a short user guide.
About the Podcast Host
AI and Communications Specialist | Author | Podcaster | International Speaker
Joanne Sweeney is a recognised leader in digital marketing and digital transformation, specialising in the practical application of AI to enhance communication strategies. The founder of Digital Training Institute, Joanne, empowers leaders and communications professionals to leverage AI responsibly and effectively, ensuring transparency, trust, and tangible results.
She completed the Harvard Kennedy School Executive Programme in AI and Public Policy this summer before launching her fourth book AI Playbook, in September. Joanne has also published two editions of Public Sector Marketing Pro, which were preceded by her first title, Social Media Under Investigation Law Enforcement and the Social Web.
Her books have become go-to resources for governments, public sector and policing agencies, as well as marketing and communications professionals, all navigating the challenges of the changing Internet.
Joanne is the host of the AI SIX Podcast, a daily six-minute podcast that provides actionable insights, expert interviews, and practical advice to help professionals navigate the new world of work.



















