Daimon Hackathon · PyMC Labs · Sat, Oct 10, 2026 · 307 W 38th St, NYC
Three tracks. Built with Daimon.
Analyse a company's data, publish a data story, or land a pull request in the PyMC libraries — using Daimon. Every participant gets $25 in Daimon credit.
- 3Tracks
- 4–6Per Team
- $25Daimon Credit
- 1Judge
Presented by
The Brief
The three tracks and who does what on a team of four to six.
- Objective
- Tracks
- Roles
Pick a track. Build it with Daimon. Submit before the deadline.
Analyse a fictional company's data warehouse, publish a data story from public sources, or land a pull request in the PyMC libraries. Every participant gets $25 in Daimon credit.
Pick a track, then ideate freely within it.
Each track has its own deliverable. Pick one, then decide what your team will build within it.
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.
For analysts and modelers.
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.
For writers and researchers.
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.
For engineers and PyMC contributors.
Not sure which? Track 01 has a dataset ready for you. Track 02 needs you to find your own. Track 03 needs someone comfortable with the PyMC codebase.
Everyone has a job. Non-technical people aren't support.
Driver
Runs Daimon and owns the repo or notebook.
Analyst
Decides what to ask Daimon and checks the numbers that come back.
Writer
Writes the post, the PR description, and the submission write-up.
Reviewer
Reviews the work before it is submitted, as the judge would.
Teams are four to six people. Roles are a suggestion, not a requirement. One person running Daimon with three people deciding what to ask it works well.
The Build
The six steps, the tool, and the walkthroughs.
- Steps
- Stack
- How-to
A clear pipeline from track to submission.
- 00Pick
Choose a track and form a team.
Join the hackathon channel on the Decision AI Discord to find teammates. Register on Devpost with your track.
- 01Set Up
Add Daimon to your server.
Add it in Discord or Slack. Hackathon participants get $25 in credit. You can also run the open-source version with your own API keys.
- 02Frame
Write down what you are building.
One paragraph: the question you are answering, the post you are writing, or the feature you are adding. This becomes the description in your submission.
- 03Build
Build it with Daimon.
Run the analysis, write the code, or draft the post in the Daimon thread. Check the output before you use it.
- 04Finish
Finish the deliverable for your track.
A notebook with charts, a published post, or an open pull request.
- 05Submit
Submit on Devpost.
Your track, the repo or notebook link, the deliverable, and a written description of what you built.
Work in one thread — Daimon keeps the context of the conversation, so the whole team can see and build on what it has done.
Tools that power every team.
Daimon runs in Discord and Slack. Add it to your server before the event.
DAIMON
Your fifth teammateData science agent from PyMC Labs. Writes and runs code, fits Bayesian models with PyMC, posts charts and runnable notebooks in the thread. Free to add. Hackathon participants get $25 in credit.
PYMC OPEN-SOURCE STACK
Optional · Special Prize- PyMC
Probabilistic reasoning + Bayesian modeling.
github.com/pymc-devs → - PyMC-Marketing
Media mix modeling + budget optimization.
github.com/pymc-labs/pymc-marketing → - Decision Hub
15,420+ validated agent skills. Chat with it to see what already exists before you build.
hub.decision.ai → - Decision Lab
Harness for agentic data science.
github.com/pymc-labs/decision-lab →
Before you start building, check Decision Hub for agent skills that already do what you need.
Get up to speed before the day.
The Day
October 10 in New York. Doors at 11, out by 4. The timetable, the rules, and where to register.
- Schedule
- Rules
- Register
One afternoon, doors at 11.
- When
- Saturday, October 10, 2026 · 11:00 AM – 4:00 PM EDT
- Where
- 307 West 38th Street, New York, NY
The timetable is provisional. The submission deadline will be confirmed with the challenge requirements — join the Discord to hear first.
Doors open · Coffee · Team formation
Daimon introduction · Track reveal
Build sprint begins
Submissions close on Devpost — no extensions (provisional)
Lunch · Science fair — judges walk the room
Judges deliberate · Three finalists selected
Finalists announced · Demos — three teams, five minutes each
Awards · Closing remarks
Doors close
Eight rules. No exceptions.
- R01
Daimon is the required tool. The managed version or a self-hosted open-source install both count.
- R02
Teams of 4–6. No solo submissions. One track per team, named in your submission.
- R03
Track 01 submits an analysis of the provided dataset: findings, models, and charts.
- R04
Track 02 submits a published blog post that links back to PyMC Labs. Public data sources only. No scraping.
- R05
Track 03 submits a pull request to a PyMC library. A merged PR wins the track.
- R06
Every finding must include the code and data that produced it.
- R07
One Devpost entry per team: track, repo or notebook, the post or PR link, and a written description.
- R08
Submit on Devpost by the deadline, planned for 1:30 PM — no extensions.
Three steps to lock your spot.
- 02
REGISTER YOUR TEAM
Two registrations — Devpost for your submission, the form so prizes reach the right team.
Team verification form: Verify team ↗ - 03
JOIN THE DISCORD
Team formation, questions, and announcements are in the hackathon channel on the Decision AI Discord.
The Prize
How judging works, the prizes, and the FAQ.
- Judging
- Prizes
- FAQ
Five criteria. 25 points maximum.
- 01
It works
Runs on the data. Outputs are not hardcoded.
5 PTS - 02
Daimon did the work
The analysis or code was produced in the Daimon thread.
5 PTS - 03
Matches your description
Judged against what you said you would build in Step 02.
5 PTS - 04
Someone can use it
A reader can follow the post, run the notebook, or review the PR without help.
5 PTS - 05
Explainable
Every finding has a reason a reader can check.
5 PTS
Minimum 15 points to qualify for prizes. Each criterion is scored 0–5: 5 fully demonstrated, 3 partially, 0 absent. All criteria weigh equally. Judges walk the science fair after submissions close and review Devpost at the same time. Ties break on criterion 4, then criterion 1.
Prizes to be announced.
The prize pool is being finalized and will be posted here once confirmed.
Everyone gets: $25 in Daimon credit.
Track 03: a merged pull request wins the track.
Common questions.
I'm not technical — can I compete?
Yes. Tracks 01 and 02 do not require code. Daimon writes and runs it; you decide what to ask and check the results. Track 03 requires someone who can work in the PyMC codebase.
Do I need my own API key?
No. Every participant gets $25 in Daimon credit. If you prefer, the open-source version of Daimon runs on your own API keys.
Can I scrape websites for Track 02?
No. Scrapers get IP-blocked and the data is unreliable. Use downloadable datasets, SEC filings, government data portals, and public APIs.
What must I submit?
Your Devpost entry must include: track selection, a GitHub repo or notebook link, the artifact for your track (charts, the published post, or the pull request), and a written description of what you built. All items required — partial submissions are not accepted.
How are finalists picked?
Science-fair scores plus the Devpost review give each team a score out of 25. Judges deliberate, then the top three demo live, five minutes each. Minimum 15 of 25 to qualify for prizes.
Still have a question?
Ask in the hackathon channel on the Decision AI Discord. Registration is open on both Devpost and Partiful.