Boundary Forge

Boundary Forge is a model-agnostic AI safety pipeline that helps enterprises deploy LLMs with measurable confidence. Instead of relying on manual red-teaming or hoping a system prompt is enough, Boundary Forge automatically attacks a model, identifies where it behaves unsafely or inconsistently, and converts those discovered failures into runtime guardrails. For this hackathon, we demonstrated Boundary Forge using Qwen 2.5-72B on AMD Developer Cloud with AMD MI300X. Qwen powered the adversarial red-team workflow and was also the model under test, allowing the system to expose real behavioral failure boundaries such as jailbreak attempts, policy drift, unsafe financial guidance, KYC bypass, fraud patterns, coercion signals, asset concealment, and inconsistent refusals. The pipeline works in five stages: generate adversarial probes, run high-throughput model inference, mathematically detect boundary failures, compile those failures into semantic safety rules, and enforce them through middleware before risky prompts reach the LLM. This creates a practical enterprise safety layer that can block, flag, or ask for clarification in real time. The important point is that Boundary Forge is not tied to one model. Qwen 2.5-72B was used to demonstrate the system, but the architecture can benchmark and harden other open-source or proprietary models as well. The goal is to improve models exactly where they fail and make model evaluation repeatable across different deployments. In our AMD Cloud production run with Qwen 2.5-72B, Boundary Forge generated 1,009 unique adversarial probes, fired 4,036 total inferences, discovered 25 boundary failures, and compiled 15 semantic safety rules. The middleware intercepted 68% of known attacks and reduced the effective failure rate from 2.48% to 0.79%. Boundary Forge turns AI safety into an automated engineering workflow: attack, measure, learn, protect, and benchmark again.

Agronomist

Resume Compact

Resume Compact, the HR Resume Analyzer, is an intelligent, end-to-end recruitment automation platform designed to streamline candidate screening and evaluation by combining modern document processing, artificial intelligence, and web technologies to eliminate manual resume review bottlenecks and provide data-driven hiring insights to recruitment teams. Key technical features include seamless fallback PDF processing with transition from native text extraction to OCR when needed, LangChain structured output using StructuredPrompt and Pydantic to ensure JSON-compliant responses, strict schema enforcement that validates all outputs against Pydantic models and rejects malformed responses, detailed and context-rich prompt engineering to guide the LLM toward accurate structured analysis, async HTTP using httpx for efficient non-blocking calls to the LLM API, robust exception handling with informative HTTP status codes and error messages, and comprehensive audit logging with timestamps, file IDs, and LLM raw responses stored for compliance and debugging. The system reduces recruitment cycle time by 60-80%, eliminates subjective bias in initial screening, allows HR teams to focus on relationship-building rather than document review, and, by standardizing candidate data into structured JSON, enables downstream analytics, reporting, and integration with ATS (Applicant Tracking Systems).

Swarm

Swarm est une architecture multi-agents avancée conçue pour automatiser les workflows techniques critiques, de l'analyse de code à la génération d'infrastructure. En exploitant la puissance et la bande passante mémoire de l'AMD Developer Cloud, cet 'essaim' d'agents synchronisés analyse les dépôts de code pour générer instantanément des configurations conteneurisées (Docker), des scripts de déploiement et une documentation technique complète, accélérant radicalement le cycle de livraison logiciel. En d'autres termes, Swarm transforme des problèmes complexes en tâches modulaires gérées par des agents spécialisés, orchestrés pour atteindre un objectif commun : l'automatisation intelligente du développement logiciel. Imaginez une équipe de développeurs virtuels, chacun expert dans un domaine précis, travaillant en parfaite harmonie grâce à une communication et une coordination optimisées. C'est l'essence de Swarm. Cet outil permet aux équipes de se concentrer sur l'innovation plutôt que sur les tâches manuelles et répétitives, réduisant drastiquement les délais de mise sur le marché et améliorant la qualité du code.

TempoGraph: Local Multimodal Video Analysis

TempoGraph is a fully-local, privacy-preserving multimodal video analysis system that turns raw video files into rich structured outputs — entities, behaviors, transcripts, timelines, and interactive knowledge graphs — without sending a single frame to the cloud. Stage 1 — Frame Selection: Motion-aware sampling with static, moving, and auto camera modes. For moving cameras it estimates homography to separate object motion from camera movement, then identifies keyframes where motion peaks exceed a configurable sigma threshold. Stage 1.5 — Audio Transcription: Whisper.cpp running on Vulkan transcribes the full audio track to millisecond-accurate segments. Stage 2 — YOLO Detection: YOLO26 runs on 2nd GPU over every sampled frame, outputting normalized bounding boxes, class names, track IDs, and confidence scores. Stage 3 — Depth Estimation: Depth Anything V2 via HuggingFace Transformers adds per-detection mean depth to every bounding box, giving 3D spatial context to 2D detections. Stage 4 — Frame Scoring: Picks which frames the VLM actually sees. In keyframes mode, only motion-peak frames are forwarded. In scored mode, FrameScorer ranks all YOLO-scanned frames using a weighted combination of motion delta, new YOLO class appearances, tracked object churn, and IoU drop between frames — then fills the VLM budget with the highest-signal frames. Keyframes are always pinned in first regardless of mode. Stage 5 — VLM Captioning: Qwen3.5-VL-9B served by a custom llama.cpp build compiled for AMD ROCm/HIP, running on an AMD RX 9070 XT with a 100k-token context window. Frames are chunked and sent to the model alongside YOLO-derived annotations. Each chunk's summary seeds the next prompt for narrative continuity across the video. Stage 6 — Aggregation: A final text-only LLM call synthesizes all per-chunk captions and the audio transcript into a structured JSON with entities, visual events, audio events, and multimodal correlations linking what was said to what was seen.