AI-Powered Event Discovery for Buenos Aires
A conversational event discovery product that turned Buenos Aires' fragmented event scene into one searchable assistant for finding, saving, and sharing plans.
What changed
Launched a working event discovery product with 800+ events and 190+ venues pulled into one searchable experience instead of forcing users to jump between sources.
- Proof type
- Selected experiment
- Client
- Personal Project
- Service
- AI Product Build
- Best fit
- Teams exploring AI assistants, RAG search, or data-heavy discovery products that need grounded answers.
- Track
- AI Systems
- Role
- Solo Product & AI Systems Builder
- Timeline
- Ongoing product build, 2025 to present
- Team
- Solo build
Why it mattered
Buenos Aires has a thriving nightlife and cultural scene, but event information is scattered across incompatible platforms: Instagram stories, Facebook events, Eventbrite, Passline, venue websites, and WhatsApp groups. There's no single source of truth, making it nearly impossible to discover what's happening tonight.
Constraints
- Event data was fragmented across multiple sources with inconsistent formats.
- The assistant needed to answer vibe-based queries without drifting away from real event data.
Built with
// What Was Happening
Buenos Aires has a thriving nightlife and cultural scene, but event information is scattered across incompatible platforms: Instagram stories, Facebook events, Eventbrite, Passline, venue websites, and WhatsApp groups. There's no single source of truth, making it nearly impossible to discover what's happening tonight.
Traditional search doesn't work for events. Users want to ask questions like 'romantic jazz spots in Palermo' or 'underground techno this weekend' - queries that require understanding intent, vibes, and context rather than just keyword matching.
// What I Built
Built a conversational assistant that lets users ask for events in plain language instead of hunting across Instagram, ticketing sites, and venue feeds.
Created an ingestion and enrichment pipeline that pulls events from multiple sources, matches venues, cleans descriptions, and keeps the catalog usable.
Combined semantic search with structured filters so the product can handle intent-heavy queries like mood, neighborhood, or time window instead of just keywords.
Built the admin and data-quality tooling needed to keep the product grounded in real event data rather than turning into an unreliable AI demo.
// What Changed
Launched a working event discovery product with 800+ events and 190+ venues pulled into one searchable experience instead of forcing users to jump between sources.
Proved a repeatable pattern for AI-assisted discovery over messy local data: ingest it, clean it, enrich it, embed it, and answer with grounded results.
The product is now a live example of how I build AI systems that need reliable retrieval, admin tooling, and a usable front end, not just a chat box.
Need this kind of workflow cleaned up?
If your business is still relying on copy-paste, fragmented tools, or one person’s memory, bring the workflow and we’ll scope the first fix.