Skip to main content
Back to challenges
Challenge

Process Flow Measurement Telemetry Validation Agent with Pydantic AI

Industrial process flowmeters frequently experience multiphase flow distortion or aeration bursts that corrupt volumetric flow totals. Construct a type-safe telemetry validation agent using Pydantic AI to validate raw sensor telemetry streams and output structured flow corrections. Achieve 99.5% schema validation pass rate with precise invalid packet handling.

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.

Implement a Pydantic AI agent with explicit schema types to parse flowmeter telemetry streams, catch sensor noise, and calculate adjusted flow totals.

Delivery guide

How work is evaluated

Evaluation

Evaluates Pydantic AI type safety, validation pass rates, and flow calculation precision.

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

strict_pydantic_validation

Ensures the response passes Pydantic model validation without exceptions.

Binary check

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

Dimension 2

schema_pass_rate

Percentage of agent outputs adhering exactly to output target schema. • target: 0.995 • 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

  • Define Pydantic schemas for Coriolis and Electromagnetic flowmeter telemetry packages

  • Build a Pydantic AI agent with type-safe tool dependencies and validation functions

  • Filter out invalid aeration spikes and compute accurate mass/volumetric flow totals

Resources and assets

Reference links and supporting material

Dataset notes

Coriolis flowmeter time-series data streams containing clean operational segments mixed with entrained gas aeration bursts.

Challenge setup

Evaluates Pydantic AI type safety, validation pass rates, and flow calculation precision.

Challenge input

JSON containing raw_flow_records list with density, volumetric_flow, and pressure

Pydantic AI

Type-safe agent framework with structured validation

Evaluated output

Validated JSON object conforming to ProcessFlowSummary schema

Evaluation checks
  • Ensures the response passes Pydantic model validation without exceptions.
  • Percentage of agent outputs adhering exactly to output target schema. • target: 0.995 • range: 0-1
Configured evaluation evidence
  • Benchmark: Structured Industrial Telemetry Validation
  • Schema Pass Rate target: 99.5%
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • Pydantic AI · Required
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • strict_pydantic_validation · Weight 1
  • schema_pass_rate · Weight 1

Metrics

  • schema_pass_rate · Target 0.995

Benchmarks

  • Structured Industrial Telemetry Validation
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing raw_flow_records list with density, volumetric_flow, and pressure

    Output: Validated JSON object conforming to ProcessFlowSummary schema

    Execution harness: Python

Evaluation tools

  • Pydantic AI · framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Process Flow Measurement Telemetry Validation Agent with Pydantic AI