Skip to main content
Back to challenges
Challenge

Industry 4.0 Scaling & Data Capture Quality Workflow with Mastra AI

Scaling Industry 4.0 initiatives fails primarily due to bad factory telemetry capture and schema drift. Create an enterprise TypeScript workflow using Mastra AI that automatically ingests MQTT and OPC UA streams, detects missing fields or schema corruptions, and auto-corrects data payloads before reaching cloud historians.

EngineeringHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Develop a Mastra AI agent workflow in TypeScript to handle edge telemetry data capture validation, repair schema drift, and guarantee data ingestion pipelines.

Delivery guide

How work is evaluated

Evaluation

Evaluates the workflow's ability to repair malformed MQTT payloads and fill missing sensor fields automatically.

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

payload_repair_check

Ensures all non-numeric strings in numeric fields are repaired or imputed.

Binary check

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

Dimension 2

repair_throughput_ms

Execution time per packet repair. • target: 15 • range: 1-100

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

  • Construct stateful data pipeline workflows using Mastra AI in TypeScript

  • Implement automatic schema drift recovery for MQTT payload variations

  • Build memory-backed agents to impute missing factory floor telemetry values

  • Ensure end-to-end data pipeline integrity for factory scale implementations

Resources and assets

Reference links and supporting material

Dataset notes

Raw MQTT telemetry message logs with corrupted fields, missing keys, and timestamp drifts.

Challenge setup

Evaluates the workflow's ability to repair malformed MQTT payloads and fill missing sensor fields automatically.

Challenge input

JSON raw payload with schema anomaly or missing fields.

Mastra AI

Provides robust workflow primitives and state machine handling in TypeScript.

Evaluated output

JSON containing repaired_payload, schema_repaired_flag, and confidence.

Evaluation checks
  • Ensures all non-numeric strings in numeric fields are repaired or imputed.
  • Execution time per packet repair. • target: 15 • range: 1-100
Configured evaluation evidence
  • Benchmark: Industrial Data Quality Benchmark
  • Repair Throughput Ms target: 15
  • 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
  • Mastra AI · Required
Orchestration
  • Mastra AI · Required

Evaluation contract

  • payload_repair_check · Weight 1
  • repair_throughput_ms · Weight 1

Metrics

  • repair_throughput_ms · Target 15

Benchmarks

  • Industrial Data Quality Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON raw payload with schema anomaly or missing fields.

    Output: JSON containing repaired_payload, schema_repaired_flag, and confidence.

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · TypeScript Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Industry 4.0 Scaling & Data Capture Quality Workflow with Mastra AI