Skip to main content
Back to challenges
Challenge

ISA/IEC 62443 Compliance Auditor Agent with LlamaIndex RAG

Adopting ISA/IEC 62443 cybersecurity standards across plant networks requires auditing complex control system configurations against extensive compliance documentation. Build a Retrieval-Augmented Generation (RAG) agent using LlamaIndex to query ISA/IEC 62443 standard controls and assess plant firewall configurations. Achieve 90% semantic query precision across regulatory controls.

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 LlamaIndex RAG pipeline indexing ISA/IEC 62443 documentation to evaluate control system security posture and generate audit gap analysis.

Delivery guide

How work is evaluated

Evaluation

Evaluates RAG retrieval accuracy and compliance gap identification against ISA/IEC 62443 standards.

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

clause_citation_accuracy

Ensures the correct ISA/IEC 62443 section is cited in the gap evaluation.

Binary check

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

Dimension 2

semantic_query_precision

Precision of retrieved knowledge nodes relative to ground truth references. • target: 0.9 • 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

  • Index ISA/IEC 62443-3-3 and 62443-4-2 standard requirements into LlamaIndex vector stores

  • Build a query engine capable of retrieving security level (SL) targets and foundational requirements

  • Analyze plant security configuration files against retrieved standard requirements

Resources and assets

Reference links and supporting material

Dataset notes

ISA/IEC 62443 control requirement summaries paired with sample industrial device configuration files.

Challenge setup

Evaluates RAG retrieval accuracy and compliance gap identification against ISA/IEC 62443 standards.

Challenge input

JSON containing query_string, security_level_target, and system_config_text

LlamaIndex

Data framework and RAG architecture

Evaluated output

JSON with answer, cited_clauses array, and compliance_status

Evaluation checks
  • Ensures the correct ISA/IEC 62443 section is cited in the gap evaluation.
  • Precision of retrieved knowledge nodes relative to ground truth references. • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: Regulatory Compliance QA Benchmark
  • Semantic Query Precision target: 0.9
  • 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
  • Llama Index · Required
  • LlamaIndex · Optional
  • Llama 3.2 · Optional

Evaluation contract

  • clause_citation_accuracy · Weight 1
  • semantic_query_precision · Weight 1

Metrics

  • semantic_query_precision · Target 0.9

Benchmarks

  • Regulatory Compliance QA Benchmark
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing query_string, security_level_target, and system_config_text

    Output: JSON with answer, cited_clauses array, and compliance_status

    Execution harness: Python

Evaluation tools

  • LlamaIndex · framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about ISA/IEC 62443 Compliance Auditor Agent with LlamaIndex RAG