Challenge

Multi-Model Safety Evaluator with Claude Agents SDK and Triton

Addressing the recent report on robotaxi safety backsliding, this challenge tasks you with building a safety evaluation framework for autonomous systems. You will utilize the Claude Agents SDK and Claude Sonnet 4.6.6 to build a supervisor agent that audits the visual perception of other models. The system will deploy GPT-5.4 Pro and specialized vision models using Triton Inference Server and TorchServe for high-performance model serving. Your agents will use Claude's extended thinking capabilities to reason through complex traffic violation scenarios and use Speakeasy to generate integrations for simulation platform APIs. This project focuses on high-concurrency model deployment and cross-model reasoning to identify traffic safety risks in real-time video metadata.

Machine LearningHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Addressing the recent report on robotaxi safety backsliding, this challenge tasks you with building a safety evaluation framework for autonomous systems. You will utilize the Claude Agents SDK and Claude Sonnet 4.6.6 to build a supervisor agent that audits the visual perception of other models. The system will deploy GPT-5.4 Pro and specialized vision models using Triton Inference Server and TorchServe for high-performance model serving. Your agents will use Claude's extended thinking capabilities to reason through complex traffic violation scenarios and use Speakeasy to generate integrations for simulation platform APIs. This project focuses on high-concurrency model deployment and cross-model reasoning to identify traffic safety risks in real-time video metadata.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Model Synchronization

Triton and TorchServe must respond within 100ms of each other

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Safety Recall

Percentage of simulated violations correctly identified • target: 0.99 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Orchestrate Claude Sonnet 4.6.6 using the Claude Agents SDK for complex reasoning about traffic laws and safety violations

  • Configure Triton Inference Server to manage multiple model versions and optimize GPU utilization for real-time inference

  • Deploy specialized PyTorch safety models on TorchServe for granular object detection auditing

  • Implement Claude's extended thinking blocks to perform multi-step chain-of-thought analysis on road incident data

  • Master the use of Speakeasy to automate the generation of SDKs for disparate simulation and telemetry data sources

  • Build a consensus mechanism where Claude Opus 4.6.6 validates the outputs of lower-latency models before generating a safety report

How this agent runs

The evaluation measures the system's ability to detect traffic violations in simulation logs and the latency of the multi-model inference pipeline.

Preview configuration

Challenge input

JSON of vehicle position and signal state

Triton Inference Server

NVIDIA multi-framework inference serving solution

TorchServe

Inference & Model Runtime · Model Serving

Evaluated output

Boolean violation flag and reasoning trace

Checks for
  • Triton and TorchServe must respond within 100ms of each other
  • Percentage of simulated violations correctly identified • target: 0.99 • range: 0-1
Proof of success
  • Safety Recall target: 0.99
  • 1 public reference case
Runtime evidence
  • Docker execution harness
View technical recipe

Configured tools

Action Space
  • Triton Inference Server · Required
  • TorchServe · Optional
  • Triton Inference Server · Optional

Evaluation contract

  • Model Synchronization · Weight 1
  • Safety Recall · Weight 1

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
Start from your terminal
$npx -y @versalist/cli start multi-model-safety-evaluator-with-claude-agents-sdk-and-triton

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Frequently Asked Questions about Multi-Model Safety Evaluator with Claude Agents SDK and Triton