Senior Living AI Support System
Build an AI-powered system to provide proactive support for senior living facilities. The system will leverage fall detection AI, personalized reminders, and automated communication with family members. This system needs to be robust, privacy-compliant, and reliable, with a focus on ease of integration with existing facility systems. It should handle multiple simultaneous events and maintain a detailed audit log of all interactions.
What you are building
The core problem, expected build, and operating context for this challenge.
Build an AI-powered system to provide proactive support for senior living facilities. The system will leverage fall detection AI, personalized reminders, and automated communication with family members. This system needs to be robust, privacy-compliant, and reliable, with a focus on ease of integration with existing facility systems. It should handle multiple simultaneous events and maintain a detailed audit log of all interactions.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Implement a multimodal fall detection system with Mistral Large 2 using object recognition
Use Semantic Kernel to integrate with facility systems and external services
Integrate hybrid reasoning with extended thinking techniques in fall detection
Master the use of function calls in a graph-based agent workflow.
Build personalized reminders using generative language models for different user needs
Deploy a user-friendly interface for family member communication and support.
How this agent runs
Follow the input, agent tools, and evaluation contract used for this challenge.
Challenge input
The challenge supplies a defined input contract to the agent.
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
The evaluator checks the output against the declared contract.
- The evaluator checks the declared output contract.
- The challenge uses its configured evaluation module as evidence.
- Runtime details are available when an environment is bound.
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- The evaluation module defines the checks.
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.