Hooligan

A Telegram sidekick that turns a craving and travel mode into evidence-backed nearby places, then checks in after the visit.

Hooligan product dashboard with verified planning loop

Small planning decisions make people bounce between maps, notes, recommendation apps, saved posts, and group chats just to answer what to do next.

Inside the experience

What someone can actually do

  1. Natural-language craving and travel-mode clarification
  2. Explicit location sharing
  3. Evidence-backed nearby venue discovery
  4. Walk and drive route ranking
  5. Venue verdict memory and consented check-ins

How the idea took shape

Hooligan clarifies the craving and travel mode, requests an explicit location share only when needed, returns nearby OpenStreetMap venues with walking-route evidence, remembers the verdict, and sends a consented check-in around the planned visit.

The best surface for lightweight planning may be the conversation people already use, not another app they have to remember to open.
Explore how it was built +

I designed the Telegram product loop, built the location and venue-discovery flow, connected route evidence, and made memory plus visit-timed follow-ups explicit and reversible.

  • TypeScript
  • Node.js
  • Telegram Bot API
  • OpenStreetMap
  • HeiGIT
  • SQLite

Where it could go next

Ambient usefulness only works when people can understand what the agent knows, why it needs location, and whether a follow-up will happen.

More work