---
title: "Drexathon recap: what builders made with Drex in one day"
description: "On 14 November, about 150 builders spent a day at Frontier Tower in San Francisco building agents with Drex, NDI and Intern. Here are the tracks, the four winners and what they built."
canonical: "https://www.nace.ai/blog/drexathon-2026-recap"
updated: 2026-11-16
---

# Drexathon recap: what builders made with Drex in one day

> On 14 November, about 150 builders spent a day at Frontier Tower in San Francisco building agents with Drex, NDI and Intern. Here are the tracks, the four winners and what they built.

Blog · Nov 16, 2026 · Nace.AI

**Drex, a small model that decides.** Generally available. Ahead of Jev on the public Decision Index 0.3.1, with about 3B parameters active per token.

- [Explore](https://www.nace.ai/drex)
- [Get started](https://console.nace.ai/?utm_campaign=drex-launch&utm_content=announcement&utm_medium=website&utm_source=nace.ai)

![Builders at their laptops at long tables in a bright, brick-walled hall at Frontier Tower during Drexathon](https://www.nace.ai/images/blog/drexathon-2026-recap/building.webp)

On Saturday, 14 November, we hosted **Drexathon**, our first hackathon, at Frontier Tower in San Francisco, with Adobe EDU as our partner. Teams of one or two spent the day building agents that make decisions with [Drex](https://www.nace.ai/drex), our decision model. They read documents with [Nace Document Intelligence (NDI)](https://www.nace.ai/perception) and ran on [Intern](https://github.com/nace-ai/intern), our open-source agent harness.

## Drexathon in numbers

- **355** people registered on Luma.
- **About 150** builders came on the day.
- **3** tracks, plus a Best Use of Adobe prize open to every team.
- **4 hours** of building, from 11:00 AM to the 3:00 PM submission deadline.
- **More than 45** projects submitted as pull requests to the public [Intern repository](https://github.com/nace-ai/intern/pulls?q=is%3Apr+Drexathon).
- **5 minutes** for each finalist demo.

## How the day ran

| Time     | What                                         |
| -------- | -------------------------------------------- |
| 9:30 AM  | Check-in and breakfast                       |
| 10:00 AM | Welcome and kickoff                          |
| 10:15 AM | Product demos from Nace.AI, rules and judges |
| 11:00 AM | Building starts                              |
| 3:00 PM  | Hard submission deadline                     |
| 3:15 PM  | Finalist demos                               |
| 4:30 PM  | Awards                                       |
| 4:45 PM  | Networking                                   |

Teams built on Intern and submitted their code as pull requests to the Intern repository, so the projects are public.

![A speaker from the Nace.AI team talks at the Frontier Tower podium next to a banner that reads "Execute your workflows with Nace Small Models"](https://www.nace.ai/images/blog/drexathon-2026-recap/kickoff.webp)

## The tracks

**🦖 Apex Predator: Drex vs. the Giants.** Take a task a frontier LLM normally handles, give the decisions to Drex, and prove it's faster, cheaper or more accurate. Teams were judged on measured results and the size of the improvement.

**🧬 Swarm Intelligence.** Build a system where several agents coordinate, compete or negotiate, with Drex making every agent's calls.

**🎨 Wildcard.** The most creative, surprising or delightful use of Drex.

In every track, teams that used NDI to bring real-world documents into their build earned bonus points. Adobe EDU added a **Best Use of Adobe** prize for teams that used Adobe tools in their project or demo.

## The judges

- **Shakh Sailaukan**, Co-founder of Rixt.AI
- **Nischay Dhankhar**, Chief of AI at Nace.AI
- **Mark Illes-Toth**, Senior PM at IBM
- **Kostas Bimpikis**, Professor at Stanford
- **Aidana Daulbayeva**, Product and Strategy at Sierra

## The winners

![Builders, finalists and the Nace.AI team gather on the stage for a group photo at the end of Drexathon](https://www.nace.ai/images/blog/drexathon-2026-recap/group.webp)

### Apex Predator: Drex Vertical Reframe, by team Wukong

Drex Vertical Reframe turns long landscape video into vertical 9:16 shorts. NDI and crowd noise shortlist the moments worth keeping, Drex classifies them, and then Drex decides frame by frame which part of the picture survives the crop. The team turned framing into multiple choice: a numbered grid on each frame, and Drex picks the lines that mark where the action is. In the team's words, every judgment call is a Drex call and everything else is deterministic code. On a 30-minute football match, Drex found all 4 key moments on time, against 1 for Gemini watching the full video. On the same clips, Drex framed each one 4 to 6 times faster and about 20 times cheaper than Gemini, the team reports.

[See the project](https://github.com/nace-ai/intern/pull/48)

### Swarm Intelligence: Drex Poker Arena

Five AI poker players play Texas Hold'em against each other or against you, and every move is a live Drex call. Drex returns a probability for each legal move, and each bot's personality decides what to do with those odds. The Statistician always takes Drex's top move, the Conservative raises only when Drex is more than 60% sure, and the Manipulator asks Drex whether its opponents will fold. After each hand you can see every bot's cards, Drex's probabilities and the reason for each move. In evolution mode, the worst bot goes extinct and the best one spawns a mutated child. NDI reads messy hand-history logs and feeds opponent stats to the bots, and the bot avatars were made with Adobe Firefly. The team reports 368 ms per decision and no illegal moves in its benchmark, against 4 for a rule-based bot.

[See the project](https://github.com/nace-ai/intern/pull/56)

### Wildcard: Reach

Reach is a Mac desktop assistant that acts for you. You can type to it, talk to it or circle something on your screen. Every request is an Intern session, with Drex Max as System 1 and Qwen3-30B-A3B on DeepInfra as System 2. Drex sizes up each request before it runs, including what kind of task it is and how risky, in about 260 ms. It also decides whether speech it overhears is meant for Reach and routes voice commands. NDI finds evidence in documents and returns cited quotes, grounded to the page.

[See the project](https://github.com/nace-ai/intern/pull/17)

### Best Use of Adobe: Boneify

_Fossil or fiction?_ You upload a document and paste what an AI wrote about it. NDI reads the original and pulls out key facts with citations. Drex then labels every sentence of the AI's text as correct, wrong or made up, with a confidence for each. The receipts appear in the original PDF through the Adobe PDF Embed API: a green box for a correct sentence, a red box for a wrong one. Intern can then rewrite only the flagged sentences, and Boneify checks the rewrite again. On 450 answers from the RAGTruth test set, the team reports that Drex Max scored a higher sentence-level F1 than GPT-6.1 Sol, 0.56 against 0.51. It was also 12.9 times faster and 45 times cheaper.

[See the project](https://github.com/nace-ai/intern/pull/39)

## What else people built

The tracks left a lot of room, and the [other entries](https://github.com/nace-ai/intern/pulls?q=is%3Apr+Drexathon) range widely. Teams built:

- a mock jury of 12 where Drex makes every juror's decision,
- an election simulator where Drex casts every vote,
- a real-time capture-the-flag game where Drex commands every unit against an army run by an LLM,
- a simulated robotics match where Drex makes every robot's call,
- a composer that turns a prompt into music, with Drex making every musical decision,
- an allergen checker that reads food-label photos,
- a pipeline that turns driver-camera crash video into an ER pre-alert,
- a tool that rebuilds torn and shredded pages from a photo,
- an inbound firewall that screens every tool result an agent reads,
- and a CI helper that decides whether a failing test is flaky or real.

![A team presents its project on the main stage during the finalist demos](https://www.nace.ai/images/blog/drexathon-2026-recap/finalist-demo.webp)

## Partners

![The Drexathon table with an Adobe sponsor sign, stickers and snacks](https://www.nace.ai/images/blog/drexathon-2026-recap/adobe-table.webp)

- **[Adobe EDU](https://www.adobe.com/education.html)** partnered with us on the event and sponsored the Best Use of Adobe prize. Winning projects used Adobe Firefly and the Adobe PDF Embed API.
- **[DeepInfra](https://deepinfra.com)** served open models for builders. Reach and Boneify both ran Intern's System 2 model on DeepInfra.

Thanks to Frontier Tower for hosting us, to the judges, and to everyone who came to build.

## What's next

The submitted projects are public in the Intern repository, so you can read the code and run it yourself. If you want to build with Drex, you can [try it for free in the Nace Console](https://console.nace.ai/?utm_campaign=drexathon-recap&utm_content=post&utm_medium=website&utm_source=nace.ai). To hear about the next hackathon, follow our [events page](https://www.nace.ai/events).

## About the product

**Drex is generally available.** Facts in, a probability for every option out. Benchmarks, board games, the playground and the API are on the product page; an API key takes a minute.

- [Get started](https://console.nace.ai/?utm_campaign=drex-launch&utm_content=announcement&utm_medium=website&utm_source=nace.ai)
- [Explore](https://www.nace.ai/drex)
- [Talk to sales](https://www.nace.ai/contact?product=drex&source=blog)

## For agents

- [Drex API guide](https://www.nace.ai/drex.md): the decision model: request shape, question types, benchmarks and deployment, as markdown
- [Decision endpoint](https://console.nace.ai/v1/systemone): POST with model "drex-latest", a state string and typed questions (choice, noul, score); https://console.nace.ai/v1/models lists checkpoints
- [Document endpoints](https://console.nace.ai/v1/documents/{parse|split|classify|extract|ground}): POST a source (a public URL, an uploaded workspace file or a finished parse job) and poll GET https://console.nace.ai/v1/documents/jobs/{id}; the same key and credit as decisions
- [Console](https://console.nace.ai): API keys, the playground, usage and billing; send `Authorization: Bearer $NACE_API_KEY` on every request
- [Console docs](https://console.nace.ai/docs): quickstart, question types, the document routes, errors, limits and pricing
- [Nace Document Intelligence](https://www.nace.ai/perception.md): the Perception series: parse, split, classify, extract and ground any file type with a location on every value
- [Drex for Search](https://www.nace.ai/drex/search.md): Drex for Search: decision-powered retrieval for agents, Drex finds the page, cited search through the CLI, SDKs, MCP and REST, and the public benchmark ranks
- [Industries](https://www.nace.ai/industries.md): Nace by industry: the files Document Intelligence reads and the decisions Drex makes for accounting, banking, mortgage, insurance, legal, healthcare, government, construction, logistics and professional services
- [Developers](https://www.nace.ai/developers.md): The execution layer for agents: Perception, Decision and Search behind one key, the Drex Max frontier, install steps, a scripted agent session and the four deployment boundaries
- [Site index](https://www.nace.ai/llms.txt): every page on nace.ai; append `.md` to any page URL or send `Accept: text/markdown` for the markdown version
