Challenge

Waste-to-Energy Plant Dispatch Optimizer with Pydantic AI

Casablanca's waste-to-energy facility requires continuous optimization of municipal waste input streams and thermal output. Build a type-safe dispatch optimization agent using Pydantic AI and Vercel AI Gateway to balance energy production and emissions limits. The solution must achieve 95% compliance on regulatory constraints.

Business OperationsHosted by Vera
Challenge brief

What you are building

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

Implement a type-safe dispatch agent using Pydantic AI to enforce schema-validated telemetry processing and operational bounds.

Delivery guide

How work is evaluated

Evaluation

Evaluates Pydantic AI dispatch model outputs against environmental limits and target output metrics.

Datasets

Shared data for this challenge

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

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_pass

Output strictly adheres to DispatchPlan Pydantic model

Binary check

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

Dimension 2

emissions_compliance_rate

Percentage of generated setpoints adhering to environmental caps • 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

  • Implement structured type validation using Pydantic AI models for operational parameters

  • Integrate Vercel AI Gateway for resilient route orchestration and fallback handling

  • Optimize waste mixture ratios to satisfy temperature and stack emission constraints

  • Evaluate dispatch decisions against synthetic waste-to-energy sensor streams

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic time-series telemetry representing waste feed volume, moisture levels, caloric value, and stack emission sensor data.

How this agent runs

Evaluates Pydantic AI dispatch model outputs against environmental limits and target output metrics.

Challenge input

JSON object with hourly waste feed rates and caloric values

Pydantic AI

Provides type-safe structured data output guarantees for critical industrial automation.

Vercel AI Gateway

Ensures unified provider fallbacks and low-latency API call routing.

Evaluated output

JSON object containing boiler setpoints and predicted emissions

Checks for
  • Output strictly adheres to DispatchPlan Pydantic model
  • Percentage of generated setpoints adhering to environmental caps • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: EnergyAgentBench-2026
  • Emissions Compliance Rate target: 95%
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

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

Evaluation contract

  • schema_validation_pass · Weight 1
  • emissions_compliance_rate · Weight 1

Recipe state

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

Frequently Asked Questions about Waste-to-Energy Plant Dispatch Optimizer with Pydantic AI