🤝 Top Collaborators
🤓 Latest Submissions
AGENTGUARD AI
AI agents increasingly perform actions through tools, such as booking appointments or updating records. A convincing response does not guarantee that the agent selected the correct action. A request to cancel an appointment could trigger a patient-record update instead. Developers need a clear way to identify and investigate this mismatch before deploying an agent. AgentGuard AI explores this problem through a focused reliability-testing prototype. Its central idea is to compare the action expected from a user's request with the action taken by an agent, then present the difference in a dashboard that supports investigation and correction. The demonstration focuses on a healthcare appointment assistant using synthetic scenarios. In the main example, the user asks, “Cancel my appointment tomorrow.” The expected tool is cancel_appointment, while the demonstrated failure is an update_patient call. This makes an otherwise technical routing error understandable at a glance. The target users are developers, QA teams, and AI integrators building agents for business workflows. In the prototype dashboard, users can review test scenarios, inspect expected and actual tool selections, and examine failure details. The interface also demonstrates the intended progression from identifying a failure to reviewing a fix and rerunning the affected scenario. The project's creative focus is the relationship between user intent and tool action. It brings the request, expected behavior, observed behavior, and failure context into one investigation flow. This is designed to reduce the effort needed to understand what went wrong and what should be checked after a change. The current submission demonstrates this approach through a dashboard and example test data. Full end-to-end execution, automated evidence collection, and verified fix-and-retest automation remain development goals. IBM Bob supports the development of AgentGuard AI as a coding assistant.
27 Sep 2026
WAYLO
Millions of people with visual impairments rely on canes, guide dogs, or other people to understand what's happening around them, but none of these give real-time, on-demand answers to questions like "What's in front of me?" or "Where is my phone?" WAYLO is built to fill that gap. WAYLO is a privacy-first, edge-AI voice companion for visually impaired people. It combines on-device computer vision, natural speech recognition, contextual AI reasoning, and text-to-speech into a single real-time loop: the user speaks a question, WAYLO analyzes the current camera view, detects relevant objects and text, and answers aloud in plain, concise language all without needing to send raw video to the cloud. Instead of narrating everything the camera sees, WAYLO focuses on what actually matters: nearby objects, obstacles directly ahead, requested items, and readable text like signs or labels. It can describe a scene, locate a specific object, read text out loud, and warn about obstacles in the user's path, while honestly saying "I don't see that" rather than guessing. By processing vision locally instead of streaming footage to remote servers, WAYLO reduces latency, works with less dependence on connectivity, and keeps the user's surroundings private by default making assistive AI faster, safer, and more trustworthy for the people who need it most.
16 Sep 2026
