One hackathon / Six challenges

Build a working idea.

Mandatory individual qualification, teams of one to four, executable projects and two-round judging. Registration & Qualification: Oct 1 – Nov 6, 2026. Project Submission & Finalist Qualification: Nov 15 – Nov 22, 2026. Grand Finale: Nov 28, 2026.

Project submission is open

Registration and qualification intake are closed. Qualified teams can submit their working projects. Submission deadline: November 22, 2026 — end of day. The exact cutoff timezone has not yet been confirmed by organizers.

Choose one challenge

Challenge 01 · Beginner-friendly

Smart Login Guardian

Recognize suspicious synthetic login attempts and explain the risk signals.

Focus: Contextual security · behavioral checks

Minimum prototype: Executable login-event classifier with explained decisions, invalid-input handling and tests.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Full submission requirements → · Mandatory qualification →
Smart Login Guardian: conceptual architecture Login events to behavioral checks to risk decision, branching into allow or flag. Conceptual only; no live login enforcement. 01 Login events 02 Behavior checks 03 Risk decision Allow Flag
Conceptual architecture

Login Events → Behavioral Checks → Risk Decision → Allow / Flag

Challenge 02 · Beginner-friendly

Find the Anomaly

Identify unusual synthetic measurements against a documented baseline.

Focus: Feature preparation · anomaly detection

Minimum prototype: Offline detector with separate training/test inputs, declared thresholds and repeatable tests.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Full submission requirements → · Mandatory qualification →
Find the Anomaly: conceptual architecture Synthetic logs to feature extraction to anomaly detector, branching into normal or anomalous results. No measured detection results. 01 Synthetic logs 02 Extract features 03 Anomaly detector Normal Anomalous
Conceptual architecture

Synthetic Logs → Feature Extraction → Anomaly Detector → Results

Challenge 03 · Beginner-friendly

API Traffic Watch

Spot unusual synthetic request traffic without affecting a real API.

Focus: Traffic monitoring · spike detection

Minimum prototype: Executable window summarizer with deduplicated requests, spike flags and a readable output.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Full submission requirements → · Mandatory qualification →
API Traffic Watch: conceptual architecture API requests to traffic monitor to spike detection to a conceptual dashboard. No real traffic or dashboard metrics. 01 API requests 02 Traffic monitor 03 Spike detection 04 Dashboard
Conceptual architecture

API Requests → Traffic Monitor → Spike Detection → Dashboard

Challenge 04 · Beginner-friendly

Explain My Security Alert

Turn a structured synthetic alert into a grounded, understandable explanation.

Focus: Language processing · safe recommendations

Minimum prototype: Executable alert explainer that reports signals, proposed action and uncertainty; rules are welcome.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Full submission requirements → · Mandatory qualification →
Explain My Security Alert: conceptual architecture Security alert to AI explanation processing to a human-readable explanation and safety guidance. Recommendations only, not enforcement. 01 Security alert 02 AI explanation 03 Explanation 04 Safety guidance
Conceptual architecture

Security Alert → AI Explanation → Safety Guidance

Challenge 05 · Beginner-friendly

Predict the Outage

Use synthetic system signals to identify early warning patterns.

Focus: Time-series analysis · risk prediction

Minimum prototype: Offline warning prototype with a chronological split, declared prediction horizon/threshold and repeatable tests.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Full submission requirements → · Mandatory qualification →
Predict the Outage: conceptual architecture System metrics including CPU, latency and errors to pattern analysis to risk prediction to an early warning. No actual prediction or proprietary algorithm. 01 System metrics 02 Pattern analysis 03 Risk prediction 04 Early warning
Conceptual architecture

System Metrics → Pattern Analysis → Risk Prediction → Warning

Challenge 06 · Beginner–intermediate

AI for Everyday Life

Build a practical, intelligent solution to a meaningful everyday human problem.

Focus: AI / ML / GenAI · intelligent automation

Minimum prototype: Working MVP, functional prototype or proof of concept with meaningful intelligent behavior, demonstrable output and basic evaluation.

Any language or framework. Standalone implementations are accepted after mandatory AeglysAI qualification. Include an offline entrypoint, setup/input/output documentation, normal/edge/invalid-input tests and known limitations.

Example areas

  • Education and learning
  • Accessibility
  • Personal productivity
  • Sustainability and food waste
  • Community assistance
  • General wellness
  • Financial literacy
  • Scam awareness

Challenge requirements

  • Define the problem and intended users; any appropriate real-world problem may be proposed.
  • Use any programming language or framework with meaningful AI/ML, GenAI or intelligent automation.
  • Demonstrate working output and provide basic tests or evaluation evidence.
  • Use privacy-safe synthetic or authorized data; document attribution and licensing.
  • Do not make unsupported medical, legal or financial decision claims.

This sixth challenge is a Portal-approved extension; the research COM-003A offering currently defines five tracks. Upstream alignment is pending.

Full submission requirements → · Mandatory qualification →
AI for Everyday Life: conceptual architecture Real-world problem to privacy-safe user input or data to AI or ML processing to a useful outcome. Conceptual only; no measured results or medical, legal or financial decision claims. 01 Everyday problem 02 Input / data 03 AI / ML processing 04 Useful outcome
Conceptual architecture

Real-World Problem → User Input / Data → AI / ML Processing → Useful Outcome

Register for HackathonRegistration Closed

Individual entry and teams

  • Individuals may compete; teams may contain two to four participants, maximum four.
  • Every member, including the leader, must individually complete qualification and be selected.
  • Designate one team leader and obtain a unique team ID from the organizer.
  • No duplicate active team membership; membership changes require organizer approval.
  • Organizers verify rosters in private Google Sheets; roster mappings are never public.

Mandatory qualification and selection →

Final project submission

Every project must be a working MVP, executable prototype or functional proof of concept. A slide deck or documented walkthrough alone is insufficient. Any programming language or framework; standalone implementations are acceptable after mandatory AeglysAI qualification.

  • Team ID
  • Selected challenge
  • Public GitHub source URL and frozen review commit/tag
  • Project README
  • Reproduction/setup instructions
  • Working demonstration video URL — maximum two minutes
  • Explanation of AI/ML or intelligent technique
  • Test or validation evidence
  • Data/model attribution and licensing
  • Known limitations

Narrated screen recordings or silent captioned demonstrations are accepted. Webcam footage is not mandatory. A deployed demo URL is optional. Submit only sanitized evidence; no private participant, credential or patent-related data.

Prepare the final submission →

Two-round judging

Virtual project review and finalist selection: November 15 – November 22, 2026. Exact session times will be announced separately.

Submission deadline: November 22, 2026 — end of day. The exact cutoff timezone has not yet been confirmed by organizers.

Round 1 — technical screening

Review source code, working prototype, required video and reproducibility. Round 1 determines finalist selection.

  • Functionality — 30 points
  • AI/ML or intelligent feature — 25 points
  • Relevance and creativity — 20 points
  • Reproducibility — 15 points
  • Video clarity — 10 points

Round 2 — finalist review

Shortlisted finalists give a five-minute live demonstration over Google Meet followed by five minutes of technical Q&A. Round 2 determines final ranking; do not combine round scores.

  • Live demonstration — 35 points
  • Technical understanding — 25 points
  • Solution quality and safety — 20 points
  • Technical Q&A — 15 points
  • Presentation — 5 points

Proposed capacity: five to ten finalist teams, subject to submission quality and organizer capacity. This is not a guaranteed finalist count. Each rubric totals 100 points; equally weighted, non-conflicted judges score independently and their scores are averaged within each round.

Round 1 ties: functionality, intelligent feature, then reproducibility. Round 2 ties: live demonstration, technical understanding, then solution quality and safety. Remaining ties receive equal additional demonstration/Q&A and independent panel review; unresolved ties receive a shared rank with any capacity decision explained under published rules.

Reviewers disclose conflicts privately and recuse; organizers assign unconflicted replacements. Technical clarification uses equivalent time and scope, is logged privately and cannot permit undisclosed post-deadline feature development. Scores, roster mappings and private comments remain in private Google Sheets/Drive. Judge appointments and results are not confirmed.

Legacy proposal links

The former three-event proposal has been replaced by this single hackathon. These URLs are retained for compatibility; their dates and prizes are not current event announcements.