AI Concierge: your night out, on request
Our own product — concept, design, engineering and launch
ZDES Events holds thousands of events and venues. The AI Concierge is a second way to use them: don’t browse — just ask. You describe the night you want in your own words, and the concierge builds a ready-to-go plan from the city’s real events and places, explains every pick and takes you all the way to the door — registration and a pass included.
01
Describe the night you want
No filters, no categories: “a Saturday night plan for two, under 3,000 ₽,” “something with coworkers on Thursday after work.” The concierge picks up the constraints on its own — when, who with, budget, mood. Venues and Web search switch on with one tap, right in the input.
02
A plan, not a list
The answer is a two-to-four-step plan in time order: what, where and why it fits. It streams in like a text message, with event cards underneath. Keep talking — “anything free?”, “can we start earlier?” — and the plan adapts instead of starting over.
03
Agents that read the city
The listings behind the concierge are gathered by AI agents. Every night they work through Telegram channels, venue websites and event listings, follow the links, pull each event out of a post with its date, time and venue, check the city and the organizer, and drop ads and duplicates. So the concierge answers from fresh, checked data — not a stale catalog.
04
A hand-built venue guide
More than 10,000 venues: Moscow’s niche bars, coffee shops, galleries, vintage stores and craft workshops that we collected and checked by hand, plus the venues from the listings. With Venues on, the concierge fills out the plan with places — a bar after the show, coffee before the gallery. Every place gets its own page, and owners can claim it — along with the guests the concierge sends their way.
05
The web, when the listings run thin
With Search on, the concierge checks the web when the listings run thin. Finds show up in a separate “From the web” block with links to the sources; past dates are filtered out and repeat searches are cached — so search stays cheap and never replaces the checked listings.
06
From plan to the door
Each card opens the event page: one-tap registration, a QR pass in your profile and check-in with a scanner at the door. The concierge doesn’t just suggest — it gets you there.
07
It started with being tired
Friday night. Five tabs of listings, three Telegram channels, “so where are we going?” in the group chat — and you end up staying in. That was us, and almost everyone we knew: a city full of things to do, and nothing left in the tank to choose.
The concierge grew out of that fatigue. We studied how people actually decide where to go — in words, not filters — and built an AI that listens. Every night that doesn’t get lost to scrolling is a night actually lived, and that’s what a life is made of.
For years the internet taught us to search and scroll. Now it’s starting to understand what we want — and it won’t be the same again. Here’s how it works, and why the concierge never makes things up:
- 01
The ask
You write the way you’d text a friend: when, who with, budget, mood.
- 02
The planner
A language model pulls out the constraints and turns the ask into search queries.
- 03
Hybrid search
Meaning-based search over a vector index plus exact-word search, fused by rank.
- 10,000+ venues near the events
- The web: only when the listings run thin
- 04
Ranking
Event quality, how soon it is, the city, 18+ — and no repeats from the same series.
- 05
The plan
The answer streams in: 2–4 steps in time order, facts from the listings only.
- Caching and daily caps keep the cost of every ask in check
08
The same concierge, built on your catalog
The concierge isn’t a chatbot bolted onto a website. It’s a layer on top of your catalog that understands the customer’s situation and answers with a ready-made solution drawn from your data. The same architecture works anywhere the choice is huge: ticketing and event platforms, retail and marketplaces, travel, lifestyle perks from banks and developers, loyalty programs. We build the whole product — scenarios and prompts, data-gathering agents, search, the interface, answer quality control and the unit economics of every request.