Step 2: Normative Requirements Pass (Discussion Section)

DUAL PRINCIPLE EXTRACTION - Ethical Principles Analysis THEORETICAL CONTEXT (Chapter 2.2.2): - Principles are ABSTRACT ethical foundations requiring extensional definition through cases - They function like constitutional principles - open-textured and requiring interpretation - Principles mediate moral ideals into concrete reality through context-specific application - They cannot be applied deductively but require balancing and interpretation EXISTING PRINCIPLE CLASSES IN ONTOLOGY: - Competence Principle: Balances professional autonomy with recognition of limitations and need for collaboration. - Confidentiality Principle: Must be balanced against public safety obligations and legal disclosure requirements. - Domain-Specific Principle: Examples: Environmental Stewardship (engineering), Patient Autonomy (medicine), Academic Freedom (education). These address domain-specific ethical ch - Environmental Stewardship Principle: Bridges engineering practice with broader environmental and societal responsibilities. - Ethical Principle: Legacy synonym for Principle. Use :Principle for new concepts. - Fundamental Ethical Principle: Examples: Public Welfare Paramount, Respect for Persons, Justice, Beneficence. These require extensive interpretation and balancing in specific contex - Integrity Principle: Central to professional identity formation and trust maintenance in professional relationships. - Principle: An information content entity representing ethical values and guidelines for conduct. This is the P component of the formal specification D=(R,P,O,S,R - Principle Argument: An argument based on fundamental ethical principles or values. - Principle Refinement: Capability to evolve principles as inconsistencies are resolved and new cases are added (GenEth system, Anderson & Anderson 2018) - Professional Virtue Principle: Examples: Integrity, Competence, Honesty, Professional Courage, Accountability. These shape professional character and decision-making. - Public Welfare Principle: Requires contextual interpretation to balance against client confidentiality and employer loyalty when public safety is at risk. - Relational Principle: Examples: Confidentiality, Loyalty, Fairness, Transparency, Respect for Autonomy. These govern interpersonal professional dynamics. - Transparency Principle: Essential for maintaining trust and enabling stakeholder participation in professional decisions. === TASK === From the following case text (discussion section), extract information at TWO levels: LEVEL 1 - NEW PRINCIPLE CLASSES: Identify ethical principles that appear to be NEW types not covered by existing classes above. Look for: - Fundamental ethical values being invoked - Abstract moral ideals guiding decisions - Constitutional-like principles requiring interpretation - Values that transcend specific rules or obligations For each NEW principle class, provide: - label: Clear principle name (e.g., "Environmental Stewardship", "Professional Autonomy") - definition: What moral ideal this principle represents - abstract_nature: The abstract ethical foundation (justice, welfare, autonomy, etc.) - extensional_examples: Concrete cases/situations where this principle applies - value_basis: Core moral value underlying the principle - application_context: Professional domains or situations where relevant - operationalization: How this abstract principle becomes concrete in practice - balancing_requirements: What other principles it typically must be balanced against - examples_from_case: How this principle appears in the case text LEVEL 2 - PRINCIPLE INDIVIDUALS: Identify specific instances where principles are invoked or applied. For each instance: - identifier: Unique identifier for this principle instance (e.g., "PublicSafety_Case8_Discussion") - principle_class: Which principle class it instantiates (use existing classes when possible) - concrete_expression: EXACT text showing how the principle is expressed - invoked_by: Who invokes or appeals to this principle - applied_to: What decision/situation/dilemma it applies to - interpretation: How the principle is interpreted in this specific context - balancing_with: Other principles that must be balanced against it - tension_resolution: How conflicts between principles are resolved - case_relevance: Why this principle matters in this specific case IMPORTANT: - Focus on ABSTRACT ethical foundations, not specific rules or procedures - Principles are broader than obligations - they generate obligations in context - Use EXACT quotes from case text where principles are expressed - Distinguish between the abstract principle CLASS and its concrete APPLICATION CASE TEXT: The Board of Ethical Review (BER) has a long history of open and welcome advocacy for the introduction of new technologies in engineering work, so long as the technologies are used in such a way that the engineering is done professionally. Artificial intelligence (AI) language processing software and AI-assisted drafting tools are in this category. The AI issues examined in this case are characteristic of engineering practice and are discussed and analyzed accordingly. However, other ethical considerations may arise when applying AI in different engineering contexts such as engineering education or engineering research. The following discussion does not attempt to address any of the potential legal considerations that may arise in such circumstances. Almost 35 years ago, in BER Case 90-6 , the BER looked at a hypothetical involving an engineer’s use of computer assisted drafting and design tools. The BER was asked if it was ethical for an engineer to sign and seal documents prepared using such a system. The introductory paragraph in that case gives a nice summary of the issue and looks ahead to one of the questions we see in this case – use of AI. The case begins: In recent years, the engineering profession has been ‘revolutionized’ by exponential growth in new and innovative computer technological breakthroughs. None have been more dynamic than the evolution that transformed yesterday's manual design techniques to Computer Aided Design (CAD), thence to Computer Assisted Drafting and Design (CADD) and soon Artificial Intelligence [AI]. The BER considers the change to CAD to merely represent a drafting enhancement. The change to CADD provides the BER with concerns that require assurance that the professional engineer has the requisite background, education and training to be proficient with the dynamics of CADD including the limitations of current technology. As night follows day one can be assured that CADD utilized beyond its ability to serve as a valuable tool has a propensity to be utilized as a crutch or substitute for judgement. That translates to a scenario for potential liability. In BER Case 90-6 , the BER determined that it was ethical for an engineer to sign and seal documents that were created using a CADD system whether prepared by the engineer themselves or by other engineers working under their direction and control. The use of AI in engineering practice raises ethical considerations, particularly concerning competency, direction and control, respect for client privacy, and accurate and appropriate attribution. Culminating in the key question: Is using AI adding a new tool to an engineer’s toolbox, or is it something more? Fundamental Canon I.2 states that engineers “perform services only in areas of their competence” and Code section II.2.a states that engineers must “undertake assignments only when qualified by education or experience in the specific technical fields involved.” Here, Engineer A, as an experienced environmental engineer, was competent to analyze groundwater monitoring data and assess contaminant risks. Because Engineer A performed a thorough review, cross-checked key facts against professional sources, and made adjustments to the text, the final document remained under Engineer A’s direction and control, as required by Code section II.2.b, “[e]ngineers shall not affix their signatures to any plans or documents . . . not prepared under their direction and control.” Further, the use of AI to assist with writing does not inherently constitute deception. Engineer A did not misrepresent their qualifications or technical expertise, nor did the AI-generated text contain inaccuracies. Fundamental Canon I.5 requires an Engineer to “avoid deceptive acts,” which was not violated here. Finally, Engineer A performed a thorough review and cross-checked the work on the report, much like Engineer A would have likely done if the report had been initially drafted by an engineer intern or other support staff. Per Code section II.1.c, confidential information can only be shared with prior consent of the Client. While careful review and checking of AI-generated content was consistent for ethical use, this does not end the inquiry into Engineer A’s actions. When Engineer A uploaded Client W’s information into the AI open-source interface, this was tantamount to placing the Client’s private information in the public domain. The facts here do not indicate Engineer A obtained permission from Client W to use the private information in the public domain. Similarly, the facts do not indicate the AI-generated report included citations of pertinent documents of technical authority. Per Code section III.9, engineers are required to “give credit for engineering work to those to whom credit is due,” so Engineer A’s ethical use of the AI software would need to include appropriate citations. Absent this professional level of care, diligence, and documentation, Engineer A’s use of the AI language processing software would be less than ethical. In addition to using AI to prepare the report, Engineer A also prepared draft design documents with a AI-assisted drafting tool that was new to the market. Engineer A elected to only conduct a high-level review and adjusted certain elements to align with site-specific conditions. When Client W reviewed the design documents, they found misaligned dimensions and key safety features (including those necessary for compliance with local regulations) were omitted. Turning to the omission of key safety features in the AI-generated plans, the BER looked at a similar situation previously. BER Case 98-3 discussed a solicitation by mail for engineers to use new technology to help gain more work. The solicitation read “Now - - thanks to a revolutionary new CD-ROM - specifying, designing and costing out any construction project is as easy as pointing and clicking your mouse - no matter your design experience. For instance, never designed a highway before? No problem. Just point to the ‘Highways’ window and click.” The engineer in BER Case 98-3 ordered the CD-ROM and began offering facilities design and construction services despite having no experience in this area or with the software. In its discussion in BER Case 98-3 , the BER reviewed several cases involving engineering competency, and concluded it would be unethical for an engineer to offer facilities design and construction services using a tool like this CD-ROM based on the facts presented in the case. They noted: In closing, the [BER]’s decision should not be understood as a wholesale rejection of the use of computers, CD-ROMs and other technological advances. Rather, it is the [BER]’s position that technology has an important place in the practice of engineering, but it must never be a replacement of a substitute for engineering judgment. Thus, Engineer A’s approach to reviewing AI-generated engineering designs presents greater ethical concerns than the ultimate use of AI for report writing. While AI-assisted drafting can be beneficial, the identified errors suggest insufficient review, which could compromise public welfare and impinge on Engineer A’s ethical and professional obligations. To begin, it is the BER’s view that under the facts, unlike the situation of BER Case 98-3 , Engineer A is not incompetent. The facts specifically note Engineer A has “several years of experience” and “strong technical expertise.” But the facts also note Engineer A appears to be operating in a compromised manner – namely, without the help of Engineer B – such that Engineer A relied on the AI-generated plans and specifications without proper oversight. Code section II.2.b states that, “[e]ngineers shall not affix their signatures to any plans or documents dealing with subject matter in which they lack competence, nor to any plan or document not prepared under their direction and control.” By relying on AI-assisted tools without a comprehensive verification process of its output, Engineer A risked violating this requirement. Furthermore, failure to detect misaligned dimensions and omitted safety features further indicates that Engineer A did not exercise sufficient diligence. The errors in the AI-generated design documents could have led to regulatory noncompliance and safety hazards, conflicting with the Fundamental Canon I.1, “hold paramount the safety, health, and welfare of the public”. Engineer A’s oversight of engineering plans was inadequate, raising ethical concerns. AI-generated technical work requires at least the same level of scrutiny as human-created work. Engineer A did not maintain responsible charge in violation of licensure law which violates Code section III.8.a. NSPE defines “Responsible Charge” in NSPE Position Statement No. 10-1778 as “being actively engaged in the engineering process, from conception to completion. Engineering decisions must be personally made by the professional engineer or by others over which the professional engineer provides supervisory direction and control authority. Reviewing drawings or documents after preparation without involvement in the design and development process does not satisfy the definition of Responsible Charge.” Engineer A, as the engineer in Responsible Charge of the project, is required to provide an experienced-based quality assurance review, engaging in critical discussions, mentorship, and professional development—elements that AI cannot replicate. The BER notes that in BER Case 98-3 , the BER stated that technology must not replace or be used as a substitute for engineering judgement. Much like directing an engineering intern to solve a problem, responsible use of AI requires an engineer to outline solution guidelines and constraints. Recommendations from the program or intern should not be blindly accepted, they should be considered and challenged and the resulting outputs should be understood. Only after the engineer in Responsible Charge has satisfied themselves that the proposed solution is in accordance with their own and professional standards should the design/report be accepted. These are steps that, in this case, Engineer A chose not to follow. While Engineer A reviewed the content, the lack of disclosure raises concerns about transparency. BER Case 98-3 emphasized that engineers must acknowledge significant contributions by others. AI, while not a human contributor, fundamentally shaped the report and design documents, warranting disclosure under Code section III.9, “[e]ngineers shall give credit for engineering work to those to whom credit is due, and will recognize the proprietary interests of others.” There are currently no universal guidelines mandating AI disclosure in engineering work, but best practices suggest informing clients when AI substantially contributes to a work product. Given that Client W identified issues in the engineering design and questioned inconsistencies in the report, proactive disclosure could have prevented misunderstandings and strengthened trust. Respond with valid JSON in this format: { "new_principle_classes": [ { "label": "Sustainable Development", "definition": "Principle that engineering solutions must balance current needs with long-term environmental and societal impacts", "abstract_nature": "Intergenerational justice and environmental stewardship", "extensional_examples": ["Green building design", "Renewable energy projects", "Resource conservation"], "value_basis": "Responsibility to future generations", "application_context": ["Infrastructure projects", "Environmental engineering", "Urban planning"], "operationalization": "Through environmental impact assessments, lifecycle analysis, sustainable design criteria", "balancing_requirements": ["Economic feasibility", "Immediate safety needs", "Client requirements"], "examples_from_case": ["Engineer considered long-term environmental impacts", "balanced immediate needs with sustainability"], "source_text": "Engineer considered long-term environmental impacts and balanced immediate needs with sustainability" } ], "principle_individuals": [ { "identifier": "PublicSafety_Case8_Facts", "principle_class": "Public Safety", "concrete_expression": "the safety of the public must be held paramount", "invoked_by": ["Engineer L"], "applied_to": ["stormwater management system design"], "interpretation": "Safety considerations override cost savings in drainage design", "source_text": "the safety of the public must be held paramount", "balancing_with": ["Cost Efficiency", "Client Interests"], "tension_resolution": "Safety takes precedence even if it increases project costs", "case_relevance": "Critical for evaluating adequacy of proposed drainage solution" } ] }