A one-day hackathon built around Daimon, the data science agent from PyMC Labs. Saturday, October 10, 2026, 11:00 AM – 4:00 PM at 307 West 38th Street, New York. Part of #AIWeekNY by Pulse NYC.

Pick a track, form a team of 4–6, and build it with Daimon. Every participant gets $25 in Daimon credit.

Track 01 · Data Analysis

A fictional company's data warehouse: realistic tables plus call recordings. Use Daimon and the PyMC libraries to analyse it, build predictive models, and present the results.

Track 02 · Data Journalism

Gather public data — SEC filings, government datasets, open APIs — analyse it with Daimon, and publish a blog post about what you found, with a link back to PyMC Labs. Use downloadable sources; scraping is unreliable.

Track 03 · Benchmarks & Features

Dig into the PyMC libraries and their code and data-analysis benchmark. Find a feature to add or an evaluation to improve, build it with Daimon, and open a pull request. A merged PR wins the track.

Tracks 01 and 02 do not require code. Daimon writes and runs it; you decide what to ask and check the results. Track 03 needs someone comfortable with the PyMC codebase.

Schedule

11:00–11:30 AM · Doors open · Registration · Team formation · Coffee

11:30 AM–12:00 PM · Briefing: AI for data science · Unveiling Daimon's new capabilities · Track reveal

12:00–1:30 PM · Building session

1:30 PM · Submissions close on Devpost — no extensions

1:30–2:30 PM · Lunch (pizza provided) · Judges preview — science fair

2:30–3:30 PM · Demos · Results · Closing notes · Networking

4:00 PM · Event concludes

Full brief, rules, and FAQ: https://oct-hackathon-landing.pages.dev/

Requirements

What to Build

One deliverable per team, decided by your track:

Track 01 · Data Analysis — an analysis of the provided dataset: findings, models, and charts, in a notebook or repo.

Track 02 · Data Journalism — a published blog post that links back to PyMC Labs. Public data sources only. No scraping.

Track 03 · Benchmarks & Features — a pull request to a PyMC library. A merged PR wins the track.

Daimon is the required tool. The managed version or a self-hosted open-source install both count. Every finding must include the code and data that produced it.

What to Submit

One Devpost entry per team. All items are required — partial submissions are not accepted.

- Track selection (01, 02, or 03)

- GitHub repo or notebook link

- The deliverable for your track: the charts and notebook, the published post, or the pull request

- A written description of what you built. This is what judges score you against, so say what question you answered, what post you wrote, or what feature you added.

Deadline: Saturday, October 10, 2026, 1:30 PM Eastern. No extensions.

Hackathon Sponsors

Prizes

1 non-cash prize

Placeholder prize

1 winner

Placeholder breakdown

Judges

Dr. Luca Fiaschi
Partner at PyMC Labs

Dr. Christian Luhmann
Chief Operating Officer

James Pooley
Principal Data Scientist

Judging Criteria

Novelty
How original is the question, approach, or result? What does the project add beyond an obvious first attempt?
Technical depth
How much care and skill went into the method, implementation, and validation?
Concrete use case
Does the project solve a clear problem for a real audience, and does the result help that audience act?
Communication
Can someone outside the team understand the problem, the work, and the result?
Reproducibility
Can someone else inspect the evidence and follow the steps behind the result?

Build Multiplayer Data Science Agents · PyMC Labs