AI solution from team The CheckInTech for AMD Developer Hackathon: ACT II hackathon ...
GlazeSmith is a physics-grounded digital twin for ceramic glaze chemistry: instead of stopping at a prediction on a page, it renders the predicted fired outcome live on a rotatable 3D vase, so a ...
RalfIIA Hybrid Ops Copilot is a production-ready orchestration ecosystem built for IT service providers (PC Doctor / InnerSpark) to automate technical quoting, cross-channel operations, and system ...
first submission. first submissionfirst submissionfirst submissionfirst submissionfirst submissionfirst submissionfirst submissionfirst submissionfirst ...
Quantum dot labs read device states via dispersive or RF measurements, operating much faster than the classification loops meant to track them. When a twin lags behind, drift can go unnoticed until ...
Legal teams, insurance claims adjusters, and law firms spend countless hours manually reading through dense case files, FIRs, and legal notices to extract basic facts. Connecting timelines across ...
Traditional AI agents often waste expensive cloud API tokens on simple tasks or hidden "reasoning" generation, resulting in massive operational costs. Our solution introduces a sophisticated 5-layer ...
Longhand is an auditable AI tax assistant built for US citizens working PAYE jobs in the UK — a group stuck between HMRC and the IRS with no tool that clearly shows its work. The core problem: US ...
Fireworks AI competition agent built as a production-grade, batch-processing Docker container. The image reads task data from /input/tasks.json, routes each task through a confidence-based ...
Window Manager Agent turns window management from a manual chore into a single spoken intent. Press Ctrl+Alt+Space, type what you're about to do — "I want to study," "gaming session" — and an LLM ...
Most agents answer every question the same expensive way, burning the same budget on a trivial lookup as on a hard proof. TokenSentinel doesn't. It treats cost as a first-class objective, matching ...
Capsum is an AI video captioning agent that turns raw video clips into style-aware captions without sacrificing factual accuracy. Feed it any clip, and it returns four genuinely distinct captions ...