Polyrific AI Hackathon, Gen 0


Our inaugural Polyrific AI Hackathon will invite both internal team members and outside engineers with a passion for AI to compete for cash prizes based on their AI hacking/engineering skills.

The challenge areas cover a range of enterprise problem areas that are presently top of mind for our enterprise clients:

Registration deadline

Wednesday, September 13




Monday, October 2

  • Contestant intros and round one solution presentation
  • Round one scoring
  • Round 2 challenge reveal


Tuesday, October 3

  • Hacking


Wednesday, October 4

  • Hacking


Thursday, October 5

  • Round 2 solution presentations
  • Final scoring based on adapted solutions


Friday, October 6

  • Awards


  • 500 USD for winners of each challenge area ($3,000 total prize money).
  • 500 for the most “private” solution. This means that it is likely a private model and does not depend on a 3rd party API.
  • Additional 1,000 USD for best overall solution.

Challenge Areas

  1. Chat with Data or Documents - Build the most insightful LLM-powered solution for a business use case that can accept one or many documents, one or many datasets, and potentially other inputs, and then initiate an accurate chat session involving the data. Judging criteria include accuracy, utility, cost to operate, and data privacy.
  2. PII Redaction - Develop a solution using LLM or other techniques to automatically identify, redact, and then restore PII. Success is measured by redaction/restoration accuracy. PII info will have to be restored to the text generated by LLM with the highest accuracy, ideally 100%.
    1. Base judging criteria:
      1. The solution should be able to identify and flag PII including full names, birth dates, social security numbers, credit card numbers, etc.
      2. The solution should remove the PII from the input text that is to be sent through a language model.
      3. The solution should then receive text from a language model after processing and re-insert the text into the correct place so that the PII is once again visible.
  3. LLM-Accelerated Coding - Use LLM to generate code from requirements and docs. Looking for high agency -- can read requirements and create code / read API docs from URL and create code. In this sense, coding begins with a tech lead producing prompts and pointing the agent to a Jira or API doc URL. Assess code quality, functionality, and development time savings.
    1. Base judging criteria:
      1. The solution can create a working code based on the user prompt.
      2. The solution can create quality code with property abstraction, organization, and documentation (in either readme or inline comment).
      3. The solution can retrieve information from external documentation to get the latest/updated solution.
    2. Hackathon Challenge:
      1. The solution can ask for clarification on the prompt and/or the external documentation.
  4. Classification - Build classifiers for datasets that are retrieved from any Open Dataset providers. Judged on accuracy, efficiency, and operational costs. Private ANNs or SLMs will be highly valued here.
    1. Base judging criteria:
      1. The solution accepts labeled data for training purposes.
      2. The solution accepts a CSV of emails (format to be provided) and can properly classify them into various categories.
        • Labeled training data will be provided on day 1 of the hackathon so be sure that you have made a method for quickly ingesting training data for your ANN, etc.
        • Image classification is possible in the wildcard round.
  5. Anomaly Detection - Detect anomalies in datasets and document sets that are retrieved from any Open Dataset providers. Prioritize performance, cost, and privacy.
    1. Base judging criteria:
      1. Accuracy: Correctly identified anomalies vs. false positives.
      2. Insightfulness: Can the solution provide useful insights from the detected anomalies?
      3. Performance: What’s the processing time? Can it handle scalability when dataset increases?
      4. Cost: What’s the amount of computational resource to get the optimum solution?
  6. Evolutionary Algorithm - Optimization challenges like scheduling, cloud spending, logistics, and resource allocation.
    1. Base judging criteria:
      1. The solution can access AWS, GCP, and Azure “retail” APIs that provide SKUs and pricing:
      2. The solution can accept a resource configuration (JSON/XML) and compute the most economical multi-cloud arrangement. For example, if database instances are less expensive on AWS for a given day, app services are less expensive on Azure, and serverless functions are less expensive on GCP, then the evolutionary algorithm should recommend the least expensive resources. The lowest cost is the fitness metric.
      3. The solution should make the recommendation for the lowest cost configuration in a readable report. It does not need to be “pretty”, just readable.

Contestants can start developing solutions that meet the base judging criteria immediately using any resource that they see fit but should be aware we will release surprise requirements the day of the hackathon that they will need to adapt to. This format allows for preliminary work while testing adaptability during the event itself.


  • Participant Eligibility
    • Participants from all backgrounds, genders, and geographies are welcome.
    • Participants must be at least 18 years old to enter.
    • All Polyrific employees are also welcome to participate.
    • There is no country restriction but you must be eligible to receive prizes (in case you win) and you are responsible for paying any taxes on the prize winnings.
  • Registration
    • Participations can register to the event from August 28, 2023 to September 13, 2023.
    • All participants must register themself or their team within the registration period via the registration form.
    • All participants must state the challenge area that they wan to build their solution.
    • One participant can select more than one challenge area, but they must provide a solution for each of challenge area that they participate in.
  • Developing Solution
    • All participants can start developing their solution after they get confirmation on their registration.
    • All participants can continue developing their solution up to September 30, 2023.
    • Participants are allowed to use third party services to support their solutions.
    • Participants can use their existing project so long as they can prove that it is their work.
  • Code Submission
    • Submission Platform & Deadline: All participants must submit their code via GitHub by September 30, 2023, to be included in the final session. Participants who fail to do so will be disqualified.
    • Intellectual Property: All submitted codes and solutions remain as the intellectual property of the participants. However, by participating, participants grant the organizing committee a non-exclusive right to use, display, and build upon said code and solutions.
    • Original Work & Documentation: All of the submitted code must be original and produced by participants. Any use of open-source libraries is permitted but must be clearly stated. A README file with setup and running instructions must be provided.
    • Functional Prototype: All submitted code must be a working prototype. If specific setups are needed, highlight them in the README.
    • Sensitive Data: Avoid committing secrets or sensitive data. Instead, use placeholders and a guide on setting them up in your documentation.
    • Integrity & Licensing: Any code with malicious intent will result in disqualification.
  • Solution Presentations
    • Time Limit: Each time will be given a strict time limit of 30 minutes for their presentation, demo, and Q&A. Going over the allotted time may result in penalty points.
    • Contents & Structure: Presentations should cover:
      • Problem Statement: Clearly outline the problem you addressed.
      • Solution: Describe your solution and why it's impactful or innovative.
      • Technical Details: Briefly touch upon the technologies used and any challenges overcome.
      • Demo: If possible, show a brief demonstration of your solution in action.
    • Equipment: The organizing committee will provide a projector and sound system. Teams are expected to bring their own laptops or devices and any necessary adapters.
  • Code of Conduct
    • Respect and Inclusivity: All participants, regardless of background or identity, should be treated with respect. Discrimination or harassment in any form will not be tolerated.
    • Collaboration and Integrity: Emphasize teamwork, learning, and fair play. Cheating, sabotage, or misrepresentation of one's work will result in disqualification.
    • Open Source and Acknowledgment: Support and acknowledge open sources. Give credit to tools, libraries, and any work upon which you build.
    • Maintain a Positive Environment: Foster a supportive atmosphere. While constructive feedback is welcome, negative or derogatory comments are not.
    • Adherence to Rules: Follow all event rules and guidelines. Decisions by the organizing committee and judges are final. Uphold the spirit of the competition at all times.