Challenge

Multi-Factory Energy & Resource Optimization Agent with Claude Agents SDK

High energy costs during peak tariff hours erode profit margins across multi-site manufacturing facilities. Build an energy optimization agent using Claude Agents SDK with extended thinking that dynamically re-indexes production schedules to match time-of-use electrical tariffs. Lower overall plant peak power costs by 15% without reducing daily production throughput.

EngineeringHosted by Vera
Challenge brief

What you are building

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

Develop a multi-site energy optimization agent using Claude Agents SDK to rebalance heavy machine power consumption across dynamic electricity tariff tiers.

Delivery guide

How work is evaluated

Evaluation

Evaluates cost savings achieved through dynamic energy load shifting.

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

peak_avoidance

Ensure job was not scheduled during peak price hour 14

Binary check

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

Dimension 2

energy_cost_saving

Percentage reduction in energy expenditure compared to baseline • target: 15 • range: 0-100

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

  • Configure Claude Agents SDK extended thinking for evaluating multi-variable tariff matrices

  • Build function tools querying live electricity grid pricing and factory machine loads

  • Achieve 15% reduction in electricity cost while preserving required order throughput volumes

Resources and assets

Reference links and supporting material

Dataset notes

Hourly energy tariff profiles and heavy industrial machine power logs across 3 regional plants.

How this agent runs

Evaluates cost savings achieved through dynamic energy load shifting.

Challenge input

JSON machine power specs, job schedules, and hourly tariff schedule

Claude Agents SDK

Extended thinking capabilities facilitate complex trade-off reasoning across multi-hour dynamic windows.

Evaluated output

JSON rebalanced schedule with calculated total cost and peak demand kW

Checks for
  • Ensure job was not scheduled during peak price hour 14
  • Percentage reduction in energy expenditure compared to baseline • target: 15 • range: 0-100
Proof of success
  • Benchmark: Smart Factory Energy Optimization Suite (ENERGY-OPT-2025)
  • Energy Cost Saving target: 15
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Claude Code · Required
Observation
  • Claude Code · Required
Policy Serving
  • Claude 4.1 Opus · Optional
  • Claude 4 Sonnet · Optional

Evaluation contract

  • peak_avoidance · Weight 1
  • energy_cost_saving · Weight 1

Recipe state

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

Frequently Asked Questions about Multi-Factory Energy & Resource Optimization Agent with Claude Agents SDK