Build a Constrained Conversational AI for Empathetic Voice Support
This challenge focuses on developing an advanced, voice-enabled conversational AI agent. The agent must provide empathetic support and information within strictly defined boundaries, explicitly avoiding advice for serious mental health issues. Participants will leverage Gemini 3 Pro's multimodal capabilities for seamless voice interaction and Langroid for building robust, stateful conversational agents. The system will integrate an MCP-enabled knowledge base to ensure factual accuracy and ethical guardrails.
What you are building
The core problem, expected build, and operating context for this challenge.
This challenge focuses on developing an advanced, voice-enabled conversational AI agent. The agent must provide empathetic support and information within strictly defined boundaries, explicitly avoiding advice for serious mental health issues. Participants will leverage Gemini 3 Pro's multimodal capabilities for seamless voice interaction and Langroid for building robust, stateful conversational agents. The system will integrate an MCP-enabled knowledge base to ensure factual accuracy and ethical guardrails.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master Gemini 3 Pro's multimodal API for seamless speech-to-text and text-to-speech integration in a conversational flow
Build sophisticated conversational agents using Langroid, focusing on state management, memory, and turn-taking for natural dialogues
Implement prompt engineering and optimization techniques with DSPy to robustly enforce ethical boundaries and safety guidelines for sensitive topics
Design MCP-enabled RAG pipelines that pull information from a curated knowledge base while filtering out harmful or out-of-scope content
Deploy adaptive thinking budgets to manage LLM inference costs and ensure the agent can dynamically adjust reasoning depth based on conversation complexity and safety requirements
Develop robust error handling and user feedback mechanisms to continuously improve the agent's safety and empathetic communication
How this agent runs
The evaluation will assess the agent's ability to maintain an empathetic tone, provide accurate information from its knowledge base, and strictly adhere to defined safety constraints, particularly regarding mental hea...
Challenge input
{'user_query': 'string'}
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
{'agent_response': 'string', 'safety_flag': 'boolean', 'reasoning': 'string'}
- Ensure no direct medical/mental health advice is given for severe issues. Must consistently return safety_f...
- Voice responses should be generated and transcribed within an acceptable latency for natural conversation.
- KnowledgeAccuracy target: 0.9
- Python execution harness
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.