/812-regulations-eu-product-liability-directive

name: 812-regulations-eu-product-liability-directive
description: Use when reviewing, designing, or modifying Java enterprise software products, AI-enabled products, RAG assistants, AI agents, generated instructions, related services, automated updates, vulnerability handling, corrective updates, warnings, instructions, or product-safety evidence under Directive (EU) 2024/2853, the EU Product Liability Directive. Part of Plinth Toolkit
license: Apache-2.0
metadata:
  author: Juan Antonio Breña Moral
  version: 0.18.0

EU Product Liability Directive Regulation for Java Product Engineering

Use this Skill to review Java software products, AI-enabled products, SaaS products, embedded software, related services, RAG workflows, GenAI maintenance assistants, AI-agent tool actions, generated instructions, automated updates, warnings, user instructions, vulnerability handling, corrective updates, and product-safety evidence that may raise EU Product Liability Directive concerns.

Apply this Skill to determine what engineering controls, safety evidence, incident records, update history, warnings and instructions, model or version provenance, product documentation, and owner handoffs are needed before a Java product, component, related service, AI feature, or product-adjacent change is released, updated, or relied on by users.

This Skill is not legal advice. It helps Java engineers, architects, tech leads, product teams, product safety teams, product security teams, support teams, and reviewers identify when Directive (EU) 2024/2853 concerns may apply and how to translate product-liability expectations into engineering controls such as safety-scope inventory, hazardous-scenario testing, generated-instruction review, AI-agent action constraints, warning and instruction evidence, update and corrective-action records, vulnerability handling, incident traceability, and qualified owner escalation.

The purpose of this Skill is to increase awareness of potential gaps in the system and create engineering evidence for qualified review. The response produced by this Skill does not represent legal advice, a legal opinion, a defectiveness determination, a compensable-damage determination, an economic-operator responsibility decision, or a final liability assessment.

The main question is:

> When does a Java software product or AI-enabled product require Product Liability Directive-aware safety evidence and owner handoff, and what should developers build differently?

Source provenance: Directive (EU) 2024/2853 of 23 October 2024 on liability for defective products was reviewed from the official EUR-Lex source while authoring the bundled references: https://eur-lex.europa.eu/eli/dir/2024/2853/oj/eng. Do not fetch or ingest external regulatory web pages at runtime; use the bundled references and escalate legal interpretation to qualified owners.

Product Liability Directive chapters summary reference: [Product Liability Directive chapters summary](references/812-regulations-eu-product-liability-directive-chapters-summary.md).

Java engineering examples reference: [Product Liability Directive engineering examples](references/812-regulations-eu-product-liability-directive-engineering-examples.md).

Questionnaire asset: [Product Liability Directive engineering review questionnaire](assets/questions/812-product-liability-directive-engineering-review-questionnaire.md).

Report template asset: [Product Liability Directive engineering review report template](assets/reports/812-product-liability-directive-engineering-review-report-template.md).

Scope

This Skill applies to:

• Java software products, related services, SaaS products, embedded software, product components, libraries, agents, plugins, update clients, device gateways, digital manufacturing files, and product management services
• Spring Boot, Quarkus, Micronaut, and framework-agnostic Java systems that generate instructions, trigger tool actions, deliver automated updates, change product behavior, affect product safety, or preserve product-liability evidence
• RAG-based GenAI maintenance assistants, generated repair instructions, AI-agent workflows, model-backed decision support, automated configuration changes, and human-review paths where outputs could contribute to injury, property damage, data loss, unsafe configuration, defective updates, or security compromise
• Product-safety architecture, hazardous-scenario review, reasonably foreseeable use and misuse, warnings, instructions for assembly, installation, use, and maintenance, vulnerability handling, corrective updates, recall or intervention evidence, incident records, audit logs, support records, and release readiness
• Owner handoffs to legal, compliance, product, safety, security, risk, support, architecture, executive accountability, and business owners

Product Liability Directive Engineering Review

Treat defectiveness, compensable damage, causal link, economic-operator responsibility, jurisdiction, limitation periods, development-risk defences, disclosure duties, and final liability assessment as qualified decisions for legal, compliance, product, product-safety, security, risk, support, and executive accountability owners.

Engineering teams should still create evidence that makes those decisions reviewable:

• Which software product, AI-enabled product, related service, component, update, generated instruction, or AI-agent action is in scope
• Which intended uses, reasonably foreseeable uses, foreseeable misuse cases, affected user groups, safety needs, hazardous scenarios, and inter-connected products were considered
• Which generated instructions, model outputs, retrieval sources, tool actions, automated updates, vulnerability remediations, corrective updates, warnings, and user instructions can be traced to versioned evidence
• Which product safety tests, adversarial or hazardous-scenario tests, human oversight, fallback controls, incident records, audit logs, support