Back to challenges
Challenge

Green Hydrogen Feasibility Assessor with Pydantic AI & Edge Impulse

Clean energy planners require type-safe assessment workflows that incorporate edge sensor readings to re-evaluate shelved hydrogen assets. Build a structured feasibility agent using Pydantic AI and Edge Impulse runtime model data to classify operational metrics.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Design a type-safe Pydantic AI workflow connected to Edge Impulse sensor classifications to evaluate green hydrogen plant viability.

Delivery guide

How work is evaluated

Evaluation

Evaluates Pydantic AI validation strictness and feasibility classification precision.

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

type_safety_verification

Ensures returned payload strictly adheres to FeasibilityResult Pydantic class.

Binary check

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

Dimension 2

lcoh_calculation_accuracy

Accuracy of Levelized Cost of Hydrogen estimation. • target: 0.98 • 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

  • Implement type-safe agent schemas with Pydantic AI validation

  • Integrate Edge Impulse inferencing output into agent structured context

  • Evaluate electrolyzer degradation and power cost tipping points

  • Enforce explicit output types for clean energy investment decisions

Resources and assets

Reference links and supporting material

Dataset notes

Levelized Cost of Hydrogen (LCOH) parameters, solar PV tariff curves, electrolyzer health metrics, and Edge Impulse vibration anomaly logs.

How this agent runs

Evaluates Pydantic AI validation strictness and feasibility classification precision.

Challenge input

JSON with power_cost_usd_mwh, electrolyzer_efficiency_pct, and membrane_vibration_edge_state

Pydantic AI

Framework ensuring strict type-safety and Pydantic validation.

Edge Impulse

Provides tinyML vibration and anomaly detection classification.

Evaluated output

JSON with lcoh_usd_kg, recommendation (PROCEED|SHELVE|RENEGOTIATE_POWER), and confidence_score

Checks for
  • Ensures returned payload strictly adheres to FeasibilityResult Pydantic class.
  • Accuracy of Levelized Cost of Hydrogen estimation. • target: 0.98 • range: 0-1
Proof of success
  • Benchmark: CleanEnergy-Econ-Eval
  • Lcoh Calculation Accuracy target: 0.98
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Pydantic AI · Required
  • Edge Impulse · Optional
  • Weights & Biases · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • type_safety_verification · Weight 1
  • lcoh_calculation_accuracy · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Green Hydrogen Feasibility Assessor with Pydantic AI & Edge Impulse