Social MediaDeep Research
Build an agentic tool that conducts deep web and social media research on a person for a given goal: hiring, sales or due diligence. Free scraping credits courtesy of Apify.
RESEARCH / IDENTITY / EVIDENCE
Agents 0.0.7 present
One night. Three topics. The sun is the deadline.
The briefing
A gathering of vampire builders with their token-sucking agents. The sun is the deadline.
You get from dusk till dawn to bring an AI agent to life. When the sun rises, the code dies. No extensions, no mercy.
Solo or in a team of up to three, you’ll pick one of three topics, plan at sunset, build through the night, and demo your creation to a jury and a live audience on Friday morning. Then we hand out prizes and toast with Bloody Marys, alcoholic and virgin, at noon.
Three case files
Come with a preference, not a finished answer. You can change direction when the briefs land.
Build an agentic tool that conducts deep web and social media research on a person for a given goal: hiring, sales or due diligence. Free scraping credits courtesy of Apify.
RESEARCH / IDENTITY / EVIDENCEImplement an end-to-end scenario with agent discovery, financial transactions, payments, wallets and dispute resolution.
DISCOVERY / PAYMENTS / TRUSTBuild an agent that can build itself. It must recognize a missing capability, create it, test it, install it and use it again later. Give it eyes, hands or a voice with ElevenLabs. Its capabilities may evolve, but its authority may not. By dawn, show a creature that learned to do things it could not do at dusk.
CREATE / TEST / INSTALL / EVOLVEWhat wins
Every judge scores the same five criteria from 0 to 5 using whole numbers.
Does the project complete its stated scenario, from input to useful output?
Does it address a clear problem and deliver a meaningful result for its intended user?
Are the technical choices appropriate, with evidence that the solution behaves reliably?
Does the project introduce a useful new approach or a thoughtful combination of existing ideas?
Has the team checked its results and clearly identified what works, what is simulated and what remains incomplete?
Shared scoring guide
Missing or unsupported.
Major gaps prevent demonstrating the criterion.
Some credible work, but substantial gaps.
Clearly demonstrated at a realistic overnight-hackathon standard.
Convincing evidence, with only minor gaps.
Particularly strong evidence and execution for the available time.
Formula: Total = Σ (criterion score ÷ 5 × criterion weight).
A project receiving 3 on every criterion scores 60/100. Judges include a short evidence-based explanation for each score.
For end-to-end functionality, a 3 means one complete core scenario works, even if it is narrow. A 5 means it works convincingly across several relevant examples and handles an important failure case.
Minimum complete scenario
A research goal and subject go in; a useful report with traceable sources comes out. The demo distinguishes supported findings from uncertainty.
An agent completes a transaction scenario with a visible outcome. A sandbox transaction counts; a simulated payment must be labelled.
The agent identifies a missing capability, creates it, tests it, installs it and successfully reuses it. The demo shows the new ability and confirms that no new authority was granted.
What is at stake
For participants
Free credits and tokens are planned. Providers and details will be confirmed soon.
Sunset to noon
Food keeps landing. Coffee never stops. The entire build fits into one night.
Check in, meet your team and claim a nest.
Rules, topics, mentors and the last useful daylight.
Plan the build, divide the work and eat something warm.
The night is yours. Mentors stay close through the evening.
Food lands. The barista and coffee keep going.
Submit the codebase and a two-minute demo video.
Prepare your story while the jury reviews every project.
Show what survived to the jury and the room.
Topic winners and the overall champion are announced.
One final toast, alcoholic and virgin, then daylight.
Already in the lair
Pack this
Find your crew
Arrive at 16:00 for check-in and team setup.
Who is it for? AI builders, AI-curious developers, product people who ship, and anyone who wants to spend one night finding out what agents can really do. You don’t need to be a pro. Places are limited, so register early.
The lair
Metro + tramNádraží Holešovice on line C, then one tram stop to Ortenovo náměstí and a 9-minute walk.
From the centreTake tram 1, 12 or 25 to Maniny, then walk about 5 minutes.
Car + bikePublic parking is available nearby. Public transport or a bike is the safer option.
OvernightThe building stays open for registered hackers. Showers are available.
Previous Prague meetups
Live demos, practical questions and the conversations around them. The hackathon is the same community, with more time to build.



Making the night possible
Space, tools, coffee and late-night fuel from the people making this hackathon possible.
The fine print
Teams keep their IP. Open-sourcing is encouraged and may sweeten your case for the overall prize.
Presentations and the award ceremony will be recorded and might be streamed publicly. Recordings may be published on our Discord. By participating, you’re OK with appearing in them.
Be kind, inclusive and professional. Harassment, discrimination and unsafe behaviour are not welcome. Contact an organizer immediately if you need help.
FAQ
The common programme and demos are in English. In your team, it’s up to you.
The overnight hackathon is for participants aged 18 and over.
The building remains open overnight. You can step out and return, but coordinate with your team and be back for the 07:14 submission.
Email agents007@etnetera.cz or ask the community on Discord.
Registration on Luma
Thursday, October 8 at 16:00 · Etnetera, Prague 7 · Places limited
Register