Skip to main content
Back to challenges
Challenge

Build Agentic Coding Workspaces on Nostr with Pydantic AI and Qwen 3

Leverage the new Buzz open source collaboration protocol to build a decentralized agentic workspace where agents and humans interact. Using Pydantic AI, you will create a specialized coding agent that monitors collaborative threads, validates structured task definitions, and executes code updates within a Daytona-managed sandbox environment. This system ensures that every interaction is type-safe and validated before execution, providing a robust interface for cross-platform agent collaboration.

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.

Build an agentic coding assistant using Pydantic AI that integrates with the Buzz protocol for decentralized developer collaboration.

Delivery guide

How work is evaluated

Evaluation

Validation of agentic task execution and structured protocol communication.

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

SchemaValidation

Strict Pydantic field checks

Binary check

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

Dimension 2

ResponseLatency

End-to-end processing time • target: 1500 • range: 0-5000

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 for building type-safe agent interactions with strict validation

  • Implement complex workflows connecting Qwen 3 reasoning outputs to the Buzz Nostr workspace

  • Design autonomous agent-to-human workflows using VAPI for real-time voice updates

  • Orchestrate deployment and UI scaffolding for agent workspaces using Vercel v0

  • Integrate Helicone for advanced observability and policy enforcement on agent traffic

  • Build a multi-turn planning loop that survives inter-process communication failures

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

Validation of agentic task execution and structured protocol communication.

Challenge input

Natural language request

Pydantic AI

Typed Python agent framework.

Vercel v0

AI app and interface builder.

Qwen 3

Policy Serving in the agent workflow.

Evaluated output

Validated Pydantic model

Evaluation checks
  • Strict Pydantic field checks
  • End-to-end processing time • target: 1500 • range: 0-5000
Configured evaluation evidence
  • ResponseLatency target: 1500
  • 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

Action Space
  • Pydantic AI · Required
  • Vercel v0 · Optional
Policy Serving
  • Qwen 3 · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • SchemaValidation · Weight 1
  • ResponseLatency · Weight 1

Metrics

  • ResponseLatency · Target 1500

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Natural language request

    Output: Validated Pydantic model

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build Agentic Coding Workspaces on Nostr with Pydantic AI and Qwen 3