Step 2: Normative Requirements Pass (Discussion)
Extract principles, obligations, constraints, and capabilities from the discussion section
Pipeline Steps
Overview Step 1: Contextual Framework Step 2: Normative Requirements Step 3: Temporal Dynamics
Generate Scenario (Coming Soon)
Use of Artificial Intelligence in Engineering Practice
Step 2 of 3
Discussion Section
Section Content:
Facts: Engineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern. This work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year. In addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site. Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing. Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired and was no longer available to Engineer A in a work capacity. Faced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents. The AI drafting software was new to the market and Engineer A had no previous experience with the tool. The AI drafting software was also open-sourced. For the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report. Engineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software. Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language. Engineer A also made minor adjustments to some of the wording to personalize the content. Engineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law. For the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications. Engineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions. Again, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents. When Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished. The Client commented that the report read as if written by two different authors but was otherwise satisfactory. Client W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations. Client W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.
Principles Extraction
LLM Prompt
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:
{'title': 'Facts', 'html': 'Engineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern. This work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year. In addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing. Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired and was no longer available to Engineer A in a work capacity.Faced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents. The AI drafting software was new to the market and Engineer A had no previous experience with the tool. The AI drafting software was also open-sourced.For the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report. Engineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language. Engineer A also made minor adjustments to some of the wording to personalize the content. Engineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.For the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications. Engineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions. Again, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.When Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished. The Client commented that the report read as if written by two different authors but was otherwise satisfactory. Client W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations. Client W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.', 'raw_key': 'facts', 'llm_text': 'Facts:\nEngineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern.\nThis work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year.\nIn addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.\nEngineer A is known for their strong technical expertise but is, personally, less confident in their technical writing.\nPreviously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts.\nBut Engineer B recently retired and was no longer available to Engineer A in a work capacity.\nFaced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents.\nThe AI drafting software was new to the market and Engineer A had no previous experience with the tool.\nThe AI drafting software was also open-sourced.\nFor the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report.\nEngineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.\nNot being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language.\nEngineer A also made minor adjustments to some of the wording to personalize the content.\nEngineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.\nFor the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications.\nEngineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions.\nAgain, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.\nWhen Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished.\nThe Client commented that the report read as if written by two different authors but was otherwise satisfactory.\nClient W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations.\nClient W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.'}
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"]
}
],
"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",
"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"
}
]
}
Saved: 2025-09-28 16:46
Obligations Extraction
LLM Prompt
You are an expert in professional ethics analyzing a case for obligations (professional duties and requirements).
Based on the literature:
- Obligations are CONCRETE PROFESSIONAL DUTIES derived from abstract principles (Hallamaa & Kalliokoski 2022)
- They specify what professionals MUST, SHOULD, or MUST NOT do (Dennis et al. 2016)
- Obligations have deontic force and are enforceable (Wooldridge & Jennings 1995)
- They operationalize principles in specific contexts (Kong et al. 2020)
Your task is to:
1. Identify NEW OBLIGATION CLASSES not in the existing ontology
2. Extract SPECIFIC OBLIGATION INDIVIDUALS from the case
EXISTING OBLIGATIONS IN ONTOLOGY (check if your identified obligations match these before creating new classes):
- Collegial Obligation: Duties toward professional peers including respect, fairness, and credit for work
- Competence Obligation: Requirement to perform services only in areas of competence (NSPE II.2)
- Conditional Obligation: Obligations that apply only when specific conditions are met
- Confidentiality Obligation: Duty to protect confidential information of clients or employers (NSPE III.4)
- Defeasible Obligation: Obligations that admit justified exceptions under specified conditions (Ganascia 2007)
- Disclosure Obligation: Requirement to inform stakeholders about conflicts, limitations, or risks (NSPE II.3.a)
- Ethical Obligation: Obligations arising from ethical principles beyond legal requirements
- Legal Obligation: Obligations arising from legal requirements and regulations
- Mandatory Obligation: Obligations that MUST be fulfilled (deontic force: mandatory)
- Obligation: An information content entity expressing required actions or behaviors in professional contexts. This is the O component of the formal specification D=(R,P,O,S,Rs,A,E,Ca,Cs).
- Prima Facie Obligation: Obligations that hold at first appearance but may be overridden by stronger duties (Anderson & Anderson)
- Professional Obligation: A duty or responsibility arising from professional role or standards
- Reporting Obligation: Duty to report violations or unsafe conditions to appropriate authorities
- Safety Obligation: Duty to hold paramount the safety, health, and welfare of the public (NSPE I.1)
Analyze this discussion section:
{'title': 'Facts', 'html': 'Engineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern. This work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year. In addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing. Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired and was no longer available to Engineer A in a work capacity.Faced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents. The AI drafting software was new to the market and Engineer A had no previous experience with the tool. The AI drafting software was also open-sourced.For the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report. Engineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language. Engineer A also made minor adjustments to some of the wording to personalize the content. Engineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.For the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications. Engineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions. Again, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.When Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished. The Client commented that the report read as if written by two different authors but was otherwise satisfactory. Client W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations. Client W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.', 'raw_key': 'facts', 'llm_text': 'Facts:\nEngineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern.\nThis work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year.\nIn addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.\nEngineer A is known for their strong technical expertise but is, personally, less confident in their technical writing.\nPreviously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts.\nBut Engineer B recently retired and was no longer available to Engineer A in a work capacity.\nFaced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents.\nThe AI drafting software was new to the market and Engineer A had no previous experience with the tool.\nThe AI drafting software was also open-sourced.\nFor the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report.\nEngineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.\nNot being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language.\nEngineer A also made minor adjustments to some of the wording to personalize the content.\nEngineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.\nFor the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications.\nEngineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions.\nAgain, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.\nWhen Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished.\nThe Client commented that the report read as if written by two different authors but was otherwise satisfactory.\nClient W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations.\nClient W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.'}
Extract obligations following this JSON structure:
{
"new_obligation_classes": [
{
"label": "Clear, specific obligation class name",
"definition": "What this type of obligation requires professionals to do",
"derived_from_principle": "Which principle this operationalizes (e.g., 'Public Safety', 'Honesty')",
"duty_type": "professional|legal|ethical|societal",
"enforcement_mechanism": "How this obligation is typically enforced",
"violation_consequences": "What happens when this obligation is violated",
"examples_from_case": ["Example 1 from the case", "Example 2"],
"confidence": 0.0-1.0,
"reasoning": "Why this is a new class not in existing ontology"
}
],
"obligation_individuals": [
{
"identifier": "Unique name for this specific obligation instance",
"obligation_class": "Name of the obligation class (new or existing)",
"obligated_party": "Who has this obligation (e.g., 'Engineer L', 'All Licensed PEs')",
"obligation_statement": "The specific duty statement (e.g., 'Report safety risks to authorities')",
"derived_from": "Source principle or law (e.g., 'NSPE Code', 'State Law')",
"enforcement_context": "How enforced in this case",
"temporal_scope": "When this obligation applies",
"compliance_status": "met|unmet|unclear|pending",
"case_context": "How this obligation manifests in the specific case",
"is_existing_class": true/false,
"confidence": 0.0-1.0
}
]
}
Focus on:
1. NEW obligation types that represent novel professional duties
2. Specific obligation instances showing how duties apply in this case
3. The relationship between obligations and the principles they operationalize
4. Enforcement mechanisms and compliance status
Return ONLY the JSON structure, no additional text.
Saved: 2025-09-28 16:48
Constraints Extraction
LLM Prompt
You are an expert in professional ethics analyzing a case for constraints (boundaries, limitations, and restrictions).
Based on the literature:
- Constraints are INVIOLABLE BOUNDARIES that limit acceptable actions (Dennis et al. 2016)
- They differ from obligations by being restrictions rather than requirements
- Constraints can be legal, physical, resource-based, or procedural
- They define the space within which ethical decisions must be made
Your task is to:
1. Identify NEW CONSTRAINT CLASSES not in the existing ontology
2. Extract SPECIFIC CONSTRAINT INDIVIDUALS from the case
EXISTING CONSTRAINTS IN ONTOLOGY (check if your identified constraints match these before creating new classes):
- Competence Constraint: Boundaries defined by agent capabilities and technical limitations (Hallamaa & Kalliokoski 2022)
- Confidentiality Constraint: Boundaries on information disclosure and privacy (Dennis et al. 2016)
- Defeasible Constraint: Constraints that admit justified exceptions under specified conditions (Ganascia 2007)
- Ethical Constraint: Professional ethical boundaries beyond legal requirements (Benzmüller et al. 2020)
- Inviolable Constraint: Absolute constraints that cannot be overridden under any circumstances (Dennis et al. 2016)
- Jurisdictional Constraint: Boundaries of authority and geographical or organizational scope (Dennis et al. 2016)
- Legal Constraint: Constraints arising from legal requirements and statutes that establish inviolable boundaries (Kroll 2020, Stenseke 2024)
- Priority Constraint: Constraints establishing precedence when multiple requirements conflict (Scheutz & Malle 2014)
- Procedural Constraint: Requirements for following specific processes or protocols (Furbach et al. 2014)
- Regulatory Constraint: Constraints from regulatory bodies and professional standards organizations (Taddeo et al. 2024)
- Resource Constraint: Limitations on available time, budget, materials, or human resources (Ganascia 2007)
- Safety Constraint: Constraints ensuring safety requirements are met (Arkin 2008)
- Temporal Constraint: Time-based limitations and deadlines (Govindarajulu & Bringsjord 2017)
Analyze this discussion section:
{'title': 'Facts', 'html': 'Engineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern. This work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year. In addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing. Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired and was no longer available to Engineer A in a work capacity.Faced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents. The AI drafting software was new to the market and Engineer A had no previous experience with the tool. The AI drafting software was also open-sourced.For the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report. Engineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language. Engineer A also made minor adjustments to some of the wording to personalize the content. Engineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.For the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications. Engineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions. Again, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.When Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished. The Client commented that the report read as if written by two different authors but was otherwise satisfactory. Client W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations. Client W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.', 'raw_key': 'facts', 'llm_text': 'Facts:\nEngineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern.\nThis work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year.\nIn addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.\nEngineer A is known for their strong technical expertise but is, personally, less confident in their technical writing.\nPreviously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts.\nBut Engineer B recently retired and was no longer available to Engineer A in a work capacity.\nFaced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents.\nThe AI drafting software was new to the market and Engineer A had no previous experience with the tool.\nThe AI drafting software was also open-sourced.\nFor the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report.\nEngineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.\nNot being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language.\nEngineer A also made minor adjustments to some of the wording to personalize the content.\nEngineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.\nFor the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications.\nEngineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions.\nAgain, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.\nWhen Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished.\nThe Client commented that the report read as if written by two different authors but was otherwise satisfactory.\nClient W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations.\nClient W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.'}
Extract constraints following this JSON structure:
{
"new_constraint_classes": [
{
"label": "Clear, specific constraint class name",
"definition": "What this type of constraint limits or restricts",
"constraint_type": "legal|physical|resource|temporal|procedural",
"flexibility": "hard|soft|negotiable",
"violation_impact": "What happens if this constraint is violated",
"mitigation_possible": "Whether and how this constraint can be mitigated",
"examples_from_case": ["Example 1 from the case", "Example 2"],
"confidence": 0.0-1.0,
"reasoning": "Why this is a new class not in existing ontology"
}
],
"constraint_individuals": [
{
"identifier": "Unique name for this specific constraint instance",
"constraint_class": "Name of the constraint class (new or existing)",
"constrained_entity": "What or who is constrained (e.g., 'Engineer L', 'Project')",
"constraint_statement": "The specific limitation (e.g., 'Cannot exceed budget of $X')",
"source": "Origin of constraint (e.g., 'Client budget', 'Environmental law')",
"enforcement_mechanism": "How this constraint is enforced",
"temporal_scope": "When this constraint applies",
"severity": "critical|major|minor",
"case_context": "How this constraint manifests in the specific case",
"is_existing_class": true/false,
"confidence": 0.0-1.0
}
]
}
Focus on:
1. NEW constraint types that represent novel limitations or boundaries
2. Specific constraint instances showing how limitations apply in this case
3. The difference between constraints (boundaries) and obligations (duties)
4. Impact and severity of constraints on decision-making
Return ONLY the JSON structure, no additional text.
Saved: 2025-09-28 16:50
Capabilities Extraction
LLM Prompt
You are an expert in professional ethics analyzing a case for capabilities (competencies and skills required for professional practice).
Based on the literature:
- Capabilities are COMPETENCIES that enable norm compliance (Hallamaa & Kalliokoski 2022)
- They represent the skills needed to fulfill professional obligations (Dennis et al. 2016)
- Capabilities include technical, ethical, communicative, and analytical competencies
- They constitute "norm competence" - the ability to act ethically (Kong et al. 2020)
Your task is to:
1. Identify NEW CAPABILITY CLASSES not in the existing ontology
2. Extract SPECIFIC CAPABILITY INDIVIDUALS from the case
EXISTING CAPABILITIES IN ONTOLOGY (check if your identified capabilities match these before creating new classes):
- Capability: A disposition that can be realized by specific types of actions or processes in professional contexts. This is the Ca component of the formal specification D=(R,P,O,S,Rs,A,E,Ca,Cs).
- Capability Type: Meta-class for specific capability types recognized by the ProEthica system
- Justification Capability: Capability to trace reasoning paths connecting decisions to authoritative sources (McLaren 2003, Anderson & Anderson 2018)
- Technical Capability: A specialized technical skill or competency in a professional domain
Analyze this discussion section:
{'title': 'Facts', 'html': 'Engineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern. This work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year. In addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing. Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired and was no longer available to Engineer A in a work capacity.Faced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents. The AI drafting software was new to the market and Engineer A had no previous experience with the tool. The AI drafting software was also open-sourced.For the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report. Engineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language. Engineer A also made minor adjustments to some of the wording to personalize the content. Engineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.For the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications. Engineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions. Again, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.When Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished. The Client commented that the report read as if written by two different authors but was otherwise satisfactory. Client W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations. Client W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.', 'raw_key': 'facts', 'llm_text': 'Facts:\nEngineer A, an environmental engineer with several years of experience and holding a professional engineering license, was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant of concern.\nThis work required Engineer A to perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year.\nIn addition, Engineer A was tasked to develop engineering design documents (plans and specifications) for modifications to groundwater infrastructure at the same site.\nEngineer A is known for their strong technical expertise but is, personally, less confident in their technical writing.\nPreviously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts.\nBut Engineer B recently retired and was no longer available to Engineer A in a work capacity.\nFaced with the need to deliver both the report and the engineering design documents without the review by and mentorship from Engineer B, Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report and to use AI-assisted drafting tools to generate preliminary design documents.\nThe AI drafting software was new to the market and Engineer A had no previous experience with the tool.\nThe AI drafting software was also open-sourced.\nFor the report, Engineer A gathered the relevant information provided by Client W and relied on the AI software to synthesize the information and generate an initial draft of the necessary report.\nEngineer A input the information gathered from Client W into the AI software, and, after a few refining prompts, received a first draft of the report generated by the AI software.\nNot being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text, Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles and verifying the phrasing by running search engine queries to ensure the content did not match any existing language.\nEngineer A also made minor adjustments to some of the wording to personalize the content.\nEngineer A did not cite their use of AI-software or its large language models, and submitted the draft report to Client W for review, including language to clearly identify that the supplied report was a draft, but applied their seal consistent with state law.\nFor the engineering design documents, Engineer A entered the information gathered from Client W into the AI software and relied on the AI-assisted drafting tools to generate a preliminary design of the plans, including basic layouts and technical specifications.\nEngineer A completed a cursory review of the AI-generated plans and adjusted certain elements to align with site-specific conditions.\nAgain, Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents.\nWhen Client W reviewed the draft report, Client W noted that the section analyzing the groundwater monitoring data would benefit from minor edits for grammar and clarity, but found the introduction discussing the contaminant’s manufacture, use, and characteristics to be exceptionally polished.\nThe Client commented that the report read as if written by two different authors but was otherwise satisfactory.\nClient W, however, noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations.\nClient W raised concerns about the accuracy and reliability of the engineering design and instructed Engineer A to revise the plans, ensuring that all elements satisfied the necessary professional and regulatory standards.'}
Extract capabilities following this JSON structure:
{
"new_capability_classes": [
{
"label": "Clear, specific capability class name",
"definition": "What competency or skill this capability represents",
"capability_type": "technical|ethical|communicative|analytical",
"norm_competence_related": "Which professional obligations this capability enables",
"skill_level": "basic|intermediate|advanced|expert",
"acquisition_method": "How this capability is typically acquired (education, training, experience)",
"examples_from_case": ["Example 1 from the case", "Example 2"],
"confidence": 0.0-1.0,
"reasoning": "Why this is a new class not in existing ontology"
}
],
"capability_individuals": [
{
"identifier": "Unique name for this specific capability instance",
"capability_class": "Name of the capability class (new or existing)",
"possessed_by": "Who has this capability (e.g., 'Engineer L', 'All Licensed PEs')",
"capability_statement": "The specific competency (e.g., 'Design stormwater systems')",
"demonstrated_through": "How shown in the case (e.g., 'Years of experience', 'Professional license')",
"proficiency_level": "basic|intermediate|advanced|expert",
"enables_obligations": "Which obligations this capability enables",
"temporal_aspect": "When this capability is relevant",
"case_context": "How this capability manifests in the specific case",
"is_existing_class": true/false,
"confidence": 0.0-1.0
}
]
}
Focus on:
1. NEW capability types that represent novel competencies
2. Specific capability instances showing professional competencies in this case
3. The relationship between capabilities and norm competence
4. How capabilities enable fulfillment of professional obligations
Return ONLY the JSON structure, no additional text.
Saved: 2025-09-28 16:54