Skip to main content
Back to challenges
Challenge

Autonomous Hardware Research Agent with Pydantic AI

Design an autonomous research agent using Pydantic AI that monitors the humanoid robot market, focusing on companies like Unitree. The agent will orchestrate specialized tasks to synthesize market reports and prepare executive summaries for investment analysis. By leveraging structured Pydantic schemas, you will ensure the integrity of the data collected from dynamic web sources and API interactions. The agent will interact with a virtual sandbox to validate market claims and simulate supply chain impacts based on recent chip industry developments.

Special Purpose AgentsHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Orchestrate an autonomous research team using Pydantic AI to validate humanoid robotics market data and supply chain trends.

Delivery guide

How work is evaluated

Evaluation

Verify agent logic accuracy and schema compliance through automated test suites.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

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

Schema Validation

Ensure output matches the defined Pydantic class

Binary check

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

Dimension 2

Accuracy

Correctness of extracted market data • target: 0.95 • 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

  • Master Pydantic AI dependency injection for flexible agent state management

  • Implement structured schema validation for complex JSON data streams

  • Deploy E2B sandboxes to execute code and verify claims independently

  • Optimize agent throughput using Vercel AI Gateway model switching

  • Build Synthflow interfaces for real-time voice-based operational updates

  • Design Replit Agent workflows for iterative deployment of the agentic service

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

Verify agent logic accuracy and schema compliance through automated test suites.

Challenge input

JSON Query

E2B

Cloud sandboxes for AI agents.

Pydantic AI

Typed Python agent framework.

Vercel AI Gateway

Unified gateway for AI providers.

Evaluated output

Validated Pydantic Model

Evaluation checks
  • Ensure output matches the defined Pydantic class
  • Correctness of extracted market data • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Environment
  • E2B · Optional
Action Space
  • Pydantic AI · Required
  • E2B · Optional
Policy Serving
  • Vercel AI Gateway · Optional
Orchestration
  • Pydantic AI · Required
  • Vercel AI Gateway · Optional

Evaluation contract

  • Schema Validation · Weight 1
  • Accuracy · Weight 1

Metrics

  • Accuracy · Target 0.95

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON Query

    Output: Validated Pydantic Model

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Autonomous Hardware Research Agent with Pydantic AI