Skip to main content
Back to challenges
Challenge

Real-Time EV Subsidy Compliance Streaming Agent with Vercel AI SDK

Automating incentive eligibility under national clean energy initiatives requires high-throughput stream processing of telematics and compliance documentation. Build a streaming analytics agent using the Vercel AI SDK in Next.js to stream real-time battery usage validation and claim compliance results for EV manufacturers.

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.

Build a streaming Next.js dashboard application powered by Vercel AI SDK to stream live EV subsidy compliance checks.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming output validity and PLI subsidy calculation accuracy.

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

pli_threshold_check

Ensures claims with <50% domestic addition are rejected.

Binary check

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

Dimension 2

streaming_first_token_latency_ms

Latency in milliseconds before first response token. • target: 400 • range: 0-1500

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

  • Leverage Vercel AI SDK `streamText` and `generateObject` for real-time streaming interfaces.

  • Integrate tool calling with streaming JSON payloads in TypeScript/Next.js.

  • Implement PLI (Production Linked Incentive) scheme rule validators for clean energy logistics.

Resources and assets

Reference links and supporting material

Dataset notes

EV vehicle telemetry logs, manufacturing component sourcing breakdowns, and PLI incentive rules.

Challenge setup

Evaluates streaming output validity and PLI subsidy calculation accuracy.

Challenge input

JSON containing vin_number, domestic_value_addition_pct, and total_ex_factory_cost_inr.

AI SDK

TypeScript streaming AI SDK with React and Next.js integration

Evaluated output

JSON containing claim_approved, calculated_incentive_inr, and audit_summary.

Evaluation checks
  • Ensures claims with <50% domestic addition are rejected.
  • Latency in milliseconds before first response token. • target: 400 • range: 0-1500
Configured evaluation evidence
  • Benchmark: Streaming AI Reactivity Benchmark
  • Streaming First Token Latency Ms target: 400
  • 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
  • Aim · Optional
  • Retell AI · Optional
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • pli_threshold_check · Weight 1
  • streaming_first_token_latency_ms · Weight 1

Metrics

  • streaming_first_token_latency_ms · Target 400

Benchmarks

  • Streaming AI Reactivity Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing vin_number, domestic_value_addition_pct, and total_ex_factory_cost_inr.

    Output: JSON containing claim_approved, calculated_incentive_inr, and audit_summary.

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · agent_framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Real-Time EV Subsidy Compliance Streaming Agent with Vercel AI SDK