Skip to main content
Back to challenges
Challenge

Build a Multi-Consortium BESS Arbitrage Agent with AI SDK

Managing grid-scale battery revenue across $1.16bn consortium agreements requires precise spot-market arbitrage. Build a TypeScript agent using Vercel AI SDK to forecast hourly electricity prices, schedule battery charge/discharge cycles, and calculate consortium revenue shares.

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.

Deploy Vercel AI SDK tools to model wholesale power market prices and optimize multi-consortium battery dispatch.

Delivery guide

How work is evaluated

Evaluation

Evaluates battery dispatch revenue maximization and accurate consortium yield split.

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

payout_sum_check

Verify consortium payouts equal total daily revenue

Binary check

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

Dimension 2

arbitrage_efficiency

Efficiency ratio of captured price delta • target: 0.96 • range: 0.88-1

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

  • Build dynamic price forecasting tools using Vercel AI SDK generateObject

  • Implement multi-consortium profit-sharing algorithms based on asset capacity contribution

  • Schedule high-efficiency charge cycles during off-peak solar generation windows

  • Output automated financial dispatch reports for ACWA and Engie project entities

Resources and assets

Reference links and supporting material

Dataset notes

Hourly Saudi electricity spot prices, solar irradiance profiles, and consortium partnership agreements.

Challenge setup

Evaluates battery dispatch revenue maximization and accurate consortium yield split.

Challenge input

JSON hourly price curve and battery specs

AI SDK

Vercel TypeScript framework for real-time structured execution

Evaluated output

JSON revenue and schedule profile

Evaluation checks
  • Verify consortium payouts equal total daily revenue
  • Efficiency ratio of captured price delta • target: 0.96 • range: 0.88-1
Configured evaluation evidence
  • Benchmark: EnergyArbitrageBench
  • Arbitrage Efficiency target: 0.96
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

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
  • Vercel AI SDK · Required
  • Retell AI · Optional
  • AutoML (H2O) · Optional
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • payout_sum_check · Weight 1
  • arbitrage_efficiency · Weight 1

Metrics

  • arbitrage_efficiency · Target 0.96

Benchmarks

  • EnergyArbitrageBench
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON hourly price curve and battery specs

    Output: JSON revenue and schedule profile

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Agent SDK

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Multi-Consortium BESS Arbitrage Agent with AI SDK