Three challenges. Pick one.
Each challenge is judged on its own rubric. Teams can pick one or more challenges and freely add or drop until the Sun 15:00 submission deadline. The Lovable tool track below is an optional add-on; opt in on your team page.
Next-level personalization in loan comparison
How can AI optimise and time transactional messages — application status updates, offers, reminders — so they adapt in real time to different customer behaviours and needs, maximising conversion and customer experience without message fatigue? The right message, at the right time, in the right channel, to the right customer. You get a real dataset (anonymised messages + emails + conversions) and ship a Dockerised solution + a short doc explaining your thinking..
Agentic GraphRAG for accounting regulatory research
Naïve RAG breaks on regulatory text — chunking cuts clauses in half, cosine ignores recency + authority, inter-document references aren't followed, and multi-hop questions get one-hop answers. The challenge: give retrieval a structure to walk.
Engineering Aiven's Infra Economics
Aiven ships an 18-month, ~4M cost-line dataset from production: 4 clouds, 18 SKU families, 6 geo buckets, 6 service categories. Anonymised, structurally identical to what they use internally.
Optional prize tracks any team can stack on top of their main challenge. Opt in from your team page.
Honorable mentionBest use of Lovable in your build wins it. Every participant gets 200 Lovable credits regardless.
Credit details + redemption →