Step 2: Normative Requirements Pass (Facts Section)
Extract principles, obligations, constraints, and capabilities from the facts section
Use of Artificial Intelligence in Engineering Practice
Step 2 of 5
Facts 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 (facts 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:
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.
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"
}
]
}
Saved: 2026-01-05 18:51
LLM Response
```json
{
"new_principle_classes": [
{
"label": "Technological Competence",
"definition": "Principle requiring professionals to understand and responsibly use technological tools, including their capabilities, limitations, and risks",
"abstract_nature": "Professional responsibility in technological adoption and application",
"extensional_examples": ["AI tool usage", "Software validation", "Digital system implementation", "Automated design tools"],
"value_basis": "Maintaining professional standards despite technological mediation",
"application_context": ["AI-assisted engineering", "Automated design", "Digital professional practice"],
"operationalization": "Through understanding tool functionality, verifying outputs, acknowledging limitations, and maintaining professional oversight",
"balancing_requirements": ["Efficiency gains", "Innovation adoption", "Traditional competence standards"],
"examples_from_case": ["Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text"],
"source_text": "Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text"
},
{
"label": "Attribution Transparency",
"definition": "Principle requiring disclosure of tools, methods, and sources used in professional work product creation",
"abstract_nature": "Honesty and transparency in work product authorship and methodology",
"extensional_examples": ["AI tool disclosure", "Software attribution", "Collaborative work acknowledgment", "Methodology transparency"],
"value_basis": "Intellectual honesty and client trust",
"application_context": ["AI-assisted work", "Collaborative projects", "Technical documentation"],
"operationalization": "Through citations, acknowledgments, methodology sections, and tool disclosure statements",
"balancing_requirements": ["Efficiency", "Client expectations", "Competitive advantage"],
"examples_from_case": ["Engineer A did not cite their use of AI-software or its large language models"],
"source_text": "Engineer A did not cite their use of AI-software or its large language models"
}
],
"principle_individuals": [
{
"identifier": "Competence_AIUsage_Facts",
"principle_class": "Competence Principle",
"concrete_expression": "Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text",
"invoked_by": ["Narrator describing Engineer A's situation"],
"applied_to": ["Use of AI software for report generation and design documents"],
"interpretation": "Professional competence requires understanding tools being used, which Engineer A lacked",
"source_text": "Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text",
"balancing_with": ["Efficiency needs due to loss of mentor"],
"tension_resolution": "Engineer A attempted thorough review but still had gaps in understanding",
"case_relevance": "Central to evaluating whether Engineer A met professional standards"
},
{
"identifier": "Transparency_NonDisclosure_Facts",
"principle_class": "Transparency Principle",
"concrete_expression": "Engineer A did not cite their use of AI-software or its large language models",
"invoked_by": ["Narrator describing Engineer A's actions"],
"applied_to": ["Submission of draft report and design documents to Client W"],
"interpretation": "Transparency would require disclosure of AI tool usage in work product creation",
"source_text": "Engineer A did not cite their use of AI-software or its large language models",
"balancing_with": ["Professional reputation concerns", "Client confidence"],
"tension_resolution": "Engineer A chose non-disclosure, potentially violating transparency obligations",
"case_relevance": "Key ethical violation regarding honest representation of work methods"
},
{
"identifier": "PublicWelfare_SafetyOmission_Facts",
"principle_class": "Public Welfare Principle",
"concrete_expression": "omission of key safety features required by local regulations",
"invoked_by": ["Client W's concerns"],
"applied_to": ["AI-generated engineering design documents"],
"interpretation": "Public welfare requires ensuring safety features are included in designs",
"source_text": "omission of key safety features required by local regulations",
"balancing_with": ["Efficiency through AI usage", "Time constraints"],
"tension_resolution": "Client identified failures requiring revision to meet standards",
"case_relevance": "Demonstrates risk to public welfare from inadequate AI oversight"
},
{
"identifier": "Competence_TechnicalWriting_Facts",
"principle_class": "Competence Principle",
"concrete_expression": "Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing",
"invoked_by": ["Narrator describing Engineer A's capabilities"],
"applied_to": ["Decision to use AI for report writing"],
"interpretation": "Recognition of personal limitations in writing competence led to seeking assistance",
"source_text": "Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing",
"balancing_with": ["Professional autonomy", "Client expectations"],
"tension_resolution": "Previously resolved through mentorship, now attempted through AI",
"case_relevance": "Contextualizes why Engineer A turned to AI assistance"
},
{
"identifier": "Integrity_SealApplication_Facts",
"principle_class": "Integrity Principle",
"concrete_expression": "applied their seal consistent with state law",
"invoked_by": ["Engineer A's action"],
"applied_to": ["Draft report submission"],
"interpretation": "Professional seal represents personal accountability for work product",
"source_text": "applied their seal consistent with state law",
"balancing_with": ["Legal compliance", "Professional responsibility for AI-generated content"],
"tension_resolution": "Engineer A sealed work despite not fully understanding AI contribution",
"case_relevance": "Raises question of integrity in sealing partially AI-generated work"
}
]
}
```
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):
- Attribution Obligation: Duty to properly cite and acknowledge all sources, tools, and methods used in creating professional deliverables
- 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
- Quality Assurance Obligation: Requirement to implement appropriate review and verification processes for all professional deliverables before submission
- Reporting Obligation: Duty to report violations or unsafe conditions to appropriate authorities
- Responsible Charge Obligation: Duty to maintain active engagement and personal decision-making authority throughout engineering process from conception to completion
- Safety Obligation: Duty to hold paramount the safety, health, and welfare of the public (NSPE I.1)
- Technology Competence Obligation: Requirement to understand and verify the capabilities, limitations, and risks of technological tools used in professional practice
- Technology Verification Obligation: Requirement to thoroughly verify and validate outputs from technological tools including AI before incorporating them into professional work
Analyze this facts section:
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.
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"],
"source_text": "EXACT text snippet from case where this obligation is identified (max 200 characters)",
"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",
"source_text": "EXACT text snippet from case where this obligation is mentioned (max 200 characters)",
"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: 2026-01-05 18:51
LLM Response
```json
{
"new_obligation_classes": [
{
"label": "Supervision Transition Obligation",
"definition": "Duty to ensure adequate alternative quality assurance and review mechanisms when losing supervisory support",
"derived_from_principle": "Competence and Quality Assurance",
"duty_type": "professional",
"enforcement_mechanism": "Professional board review, client complaints, quality audits",
"violation_consequences": "Substandard work products, professional sanctions, client dissatisfaction",
"examples_from_case": ["Engineer A lost mentorship from Engineer B but failed to establish alternative review processes"],
"source_text": "Previously, Engineer A had relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B",
"confidence": 0.85,
"reasoning": "Existing ontology lacks obligations addressing transitions in supervision/mentorship and ensuring continuity of quality assurance"
},
{
"label": "Tool Familiarity Obligation",
"definition": "Requirement to gain adequate familiarity with new technological tools before using them for professional deliverables",
"derived_from_principle": "Competence and Due Diligence",
"duty_type": "professional",
"enforcement_mechanism": "Professional standards review, client quality requirements",
"violation_consequences": "Errors in deliverables, regulatory non-compliance, professional liability",
"examples_from_case": ["Engineer A used AI software without being familiar with its full functionality"],
"source_text": "Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text",
"confidence": 0.9,
"reasoning": "While Technology Competence exists, this specifically addresses the duty to become familiar with tools BEFORE professional use"
},
{
"label": "Regulatory Compliance Verification Obligation",
"definition": "Duty to verify that all design elements meet applicable regulatory standards before submission",
"derived_from_principle": "Public Safety and Legal Compliance",
"duty_type": "legal",
"enforcement_mechanism": "Regulatory audits, building permits, professional board enforcement",
"violation_consequences": "Project delays, legal penalties, license sanctions",
"examples_from_case": ["Design documents omitted key safety features required by local regulations"],
"source_text": "omission of key safety features required by local regulations",
"confidence": 0.8,
"reasoning": "Distinct from general Safety Obligation - specifically requires verification of regulatory compliance in designs"
}
],
"obligation_individuals": [
{
"identifier": "EngineerA_Attribution_AI_Report",
"obligation_class": "Attribution Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must cite use of AI software and large language models in report generation",
"derived_from": "Professional integrity and transparency standards",
"enforcement_context": "Client review and professional standards",
"temporal_scope": "At time of report submission",
"compliance_status": "unmet",
"case_context": "Engineer A failed to cite AI software use in draft report",
"source_text": "Engineer A did not cite their use of AI-software or its large language models",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "EngineerA_Attribution_AI_Design",
"obligation_class": "Attribution Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must cite use of AI-assisted drafting tools in engineering design documents",
"derived_from": "Professional transparency requirements",
"enforcement_context": "Client requirements and professional standards",
"temporal_scope": "At time of design document submission",
"compliance_status": "unmet",
"case_context": "Failed to cite AI tools in design document generation",
"source_text": "Engineer A did not cite the AI-assisted drafting tools they used to generate the engineering design documents",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "EngineerA_Technology_Verification",
"obligation_class": "Technology Verification Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must thoroughly verify AI-generated outputs before professional use",
"derived_from": "Professional competence standards",
"enforcement_context": "Client quality requirements",
"temporal_scope": "Before submission of deliverables",
"compliance_status": "unmet",
"case_context": "Only conducted cursory review of AI-generated design plans",
"source_text": "Engineer A completed a cursory review of the AI-generated plans",
"is_existing_class": true,
"confidence": 0.9
},
{
"identifier": "EngineerA_Quality_Assurance",
"obligation_class": "Quality Assurance Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must implement appropriate review processes for all deliverables",
"derived_from": "Professional standards of practice",
"enforcement_context": "Client expectations and professional standards",
"temporal_scope": "Throughout project delivery",
"compliance_status": "unmet",
"case_context": "Failed to establish alternative QA after mentor retired",
"source_text": "Client W noticed several issues with the AI-generated design documents, including misaligned dimensions",
"is_existing_class": true,
"confidence": 0.85
},
{
"identifier": "EngineerA_Responsible_Charge",
"obligation_class": "Responsible Charge Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must maintain personal decision-making authority throughout engineering process",
"derived_from": "State licensing requirements",
"enforcement_context": "State law and professional board",
"temporal_scope": "Throughout project lifecycle",
"compliance_status": "unclear",
"case_context": "Applied seal to AI-generated work with limited personal involvement",
"source_text": "applied their seal consistent with state law",
"is_existing_class": true,
"confidence": 0.8
},
{
"identifier": "EngineerA_Tool_Familiarity",
"obligation_class": "Tool Familiarity Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must become familiar with AI software functionality before professional use",
"derived_from": "Professional competence requirements",
"enforcement_context": "Professional standards and client expectations",
"temporal_scope": "Before using tool for client deliverables",
"compliance_status": "unmet",
"case_context": "Used unfamiliar AI software for critical client deliverables",
"source_text": "The AI drafting software was new to the market and Engineer A had no previous experience with the tool",
"is_existing_class": false,
"confidence": 0.9
},
{
"identifier": "EngineerA_Regulatory_Compliance",
"obligation_class": "Regulatory Compliance Verification Obligation",
"obligated_party": "Engineer A",
"obligation_statement": "Must verify designs meet all local regulatory requirements",
"derived_from": "Local regulations and professional standards",
"enforcement_context": "Regulatory review and client requirements",
"temporal_scope": "Before design submission",
"compliance_status": "unmet",
"case_context": "Submitted designs missing required safety features",
"source_text": "omission of key safety features required by local regulations",
"is_existing_class": false,
"confidence": 0.85
}
]
}
```
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):
- Attribution Constraint: Requirements and limitations regarding the disclosure and citation of tools, methods, or sources used in professional work products
- 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)
- Constraint: An information content entity expressing limitations or restrictions on professional actions or decisions. This is the Cs component of the formal specification D=(R,P,O,S,Rs,A,E,Ca,Cs).
- 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)
- Technology Substitution Constraint: Boundaries preventing technology from replacing professional judgment and human oversight in critical decision-making
Analyze this facts section:
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.
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"],
"source_text": "EXACT text snippet from case where this constraint is identified (max 200 characters)",
"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",
"source_text": "EXACT text snippet from case where this constraint is mentioned (max 200 characters)",
"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: 2026-01-05 18:52
LLM Response
```json
{
"new_constraint_classes": [
{
"label": "Tool Familiarity Constraint",
"definition": "Limitations arising from lack of experience or understanding of tools, software, or technologies used in professional work",
"constraint_type": "procedural",
"flexibility": "soft",
"violation_impact": "Potential errors, omissions, or quality issues in work products due to improper tool usage",
"mitigation_possible": "Can be mitigated through training, documentation review, or seeking expert guidance",
"examples_from_case": ["Engineer A had no previous experience with the AI drafting tool", "Not being familiar with the full functionality of the AI software"],
"source_text": "The AI drafting software was new to the market and Engineer A had no previous experience with the tool",
"confidence": 0.9,
"reasoning": "This represents a distinct constraint type not covered by existing Competence Constraint, as it specifically addresses tool/technology familiarity rather than general professional competence"
},
{
"label": "Mentorship Availability Constraint",
"definition": "Limitations on access to guidance, review, and quality assurance from experienced professionals or mentors",
"constraint_type": "resource",
"flexibility": "hard",
"violation_impact": "Reduced quality assurance and potential errors in work products without experienced review",
"mitigation_possible": "Can be mitigated by finding alternative reviewers or using other quality assurance methods",
"examples_from_case": ["Engineer B recently retired and was no longer available", "Previously relied on guidance and quality assurance reviews by Engineer B"],
"source_text": "But Engineer B recently retired and was no longer available to Engineer A in a work capacity",
"confidence": 0.85,
"reasoning": "Distinct from Resource Constraint as it specifically addresses human expertise availability for mentorship and review, not general human resources"
}
],
"constraint_individuals": [
{
"identifier": "AI_Tool_Experience_Limitation",
"constraint_class": "Tool Familiarity Constraint",
"constrained_entity": "Engineer A",
"constraint_statement": "Cannot fully utilize AI software capabilities due to lack of previous experience with the tool",
"source": "Engineer A's lack of experience with new AI drafting software",
"enforcement_mechanism": "Self-limiting based on knowledge gaps",
"temporal_scope": "During report and design document preparation",
"severity": "major",
"case_context": "Engineer A's unfamiliarity with AI software accuracy and originality features led to inadequate quality control",
"source_text": "Not being familiar with the full functionality of the AI software, including the accuracy and originality of AI-generated text",
"is_existing_class": false,
"confidence": 0.9
},
{
"identifier": "Mentor_Unavailability",
"constraint_class": "Mentorship Availability Constraint",
"constrained_entity": "Engineer A",
"constraint_statement": "Cannot access Engineer B's guidance and quality assurance reviews due to retirement",
"source": "Engineer B's retirement",
"enforcement_mechanism": "Physical unavailability of mentor",
"temporal_scope": "After Engineer B's retirement",
"severity": "major",
"case_context": "Engineer A had to find alternative methods (AI) to compensate for lost mentorship",
"source_text": "But Engineer B recently retired and was no longer available to Engineer A in a work capacity",
"is_existing_class": false,
"confidence": 0.95
},
{
"identifier": "AI_Attribution_Requirement",
"constraint_class": "Attribution Constraint",
"constrained_entity": "Engineer A",
"constraint_statement": "Must disclose use of AI software and large language models in professional work products",
"source": "Professional standards for tool disclosure",
"enforcement_mechanism": "Professional ethics requirements",
"temporal_scope": "When submitting work products",
"severity": "critical",
"case_context": "Engineer A failed to cite AI software use in both report and design documents",
"source_text": "Engineer A did not cite their use of AI-software or its large language models",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "Local_Safety_Regulations",
"constraint_class": "Regulatory Constraint",
"constrained_entity": "Engineering design documents",
"constraint_statement": "Must include key safety features required by local regulations",
"source": "Local regulatory requirements",
"enforcement_mechanism": "Regulatory compliance review",
"temporal_scope": "During design document preparation",
"severity": "critical",
"case_context": "AI-generated designs omitted required safety features",
"source_text": "omission of key safety features required by local regulations",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "Technical_Writing_Competence",
"constraint_class": "Competence Constraint",
"constrained_entity": "Engineer A",
"constraint_statement": "Limited by personal lack of confidence in technical writing abilities",
"source": "Engineer A's self-assessed capabilities",
"enforcement_mechanism": "Self-imposed limitation",
"temporal_scope": "Throughout professional practice",
"severity": "minor",
"case_context": "Led Engineer A to seek AI assistance for report writing",
"source_text": "Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing",
"is_existing_class": true,
"confidence": 0.85
},
{
"identifier": "Professional_Standard_Compliance",
"constraint_class": "Regulatory Constraint",
"constrained_entity": "Engineering design documents",
"constraint_statement": "Must satisfy necessary professional and regulatory standards",
"source": "Professional engineering standards",
"enforcement_mechanism": "Client review and regulatory oversight",
"temporal_scope": "During document preparation and submission",
"severity": "critical",
"case_context": "Client required revision to ensure compliance",
"source_text": "ensuring that all elements satisfied the necessary professional and regulatory standards",
"is_existing_class": true,
"confidence": 0.9
}
]
}
```
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):
- AI Tool Evaluation Capability: The competency to assess, validate, and appropriately use AI-generated content in professional work
- Capability: A realizable entity 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
- Data Privacy Protection Capability: The competency to safeguard confidential client information when using digital tools and platforms
- Justification Capability: Capability to trace reasoning paths connecting decisions to authoritative sources (McLaren 2003, Anderson & Anderson 2018)
- Regulatory Compliance Capability: The competency to ensure designs and documents meet local regulations and safety standards
- Responsible Charge Capability: The competency to maintain active engagement and supervisory control from conception to completion of engineering work
- Technical Capability: A specialized technical skill or competency in a professional domain
- Technical Writing Capability: The competency to produce clear, accurate, and professional technical documentation and reports
- Technology Integration Capability: The competency to appropriately integrate new technologies while maintaining professional judgment
Analyze this facts section:
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.
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"],
"source_text": "EXACT text snippet from case where this capability is identified (max 200 characters)",
"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",
"source_text": "EXACT text snippet from case where this capability is mentioned (max 200 characters)",
"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: 2026-01-05 18:53
LLM Response
```json
{
"new_capability_classes": [
{
"label": "Groundwater Monitoring Analysis Capability",
"definition": "The competency to analyze, interpret, and synthesize groundwater monitoring data for environmental assessment and reporting",
"capability_type": "technical",
"norm_competence_related": "Enables accurate environmental assessment and protection of public health through proper contaminant analysis",
"skill_level": "advanced",
"acquisition_method": "Specialized environmental engineering education, field experience, and continuous monitoring practice",
"examples_from_case": ["Analysis of groundwater monitoring data from a site", "Observing site for over a year"],
"source_text": "perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year",
"confidence": 0.9,
"reasoning": "Specific technical capability for environmental engineers not covered by existing general technical capability class"
},
{
"label": "Contaminant Characterization Capability",
"definition": "The competency to comprehensively analyze and document the manufacture, use, and characteristics of chemical compounds and emerging contaminants",
"capability_type": "technical",
"norm_competence_related": "Enables proper risk assessment and environmental protection through accurate contaminant documentation",
"skill_level": "advanced",
"acquisition_method": "Environmental chemistry education, toxicology training, and regulatory compliance experience",
"examples_from_case": ["Prepare comprehensive report on organic compound", "Address manufacture, use, and characteristics of emerging contaminant"],
"source_text": "prepare a comprehensive report addressing the manufacture, use, and characteristics of an organic compound identified as an emerging contaminant",
"confidence": 0.85,
"reasoning": "Specialized environmental engineering capability distinct from general technical capabilities"
},
{
"label": "Self-Assessment Capability",
"definition": "The competency to accurately recognize and acknowledge one's own professional strengths and limitations",
"capability_type": "ethical",
"norm_competence_related": "Enables appropriate seeking of assistance and quality assurance to maintain professional standards",
"skill_level": "intermediate",
"acquisition_method": "Professional experience, mentorship, reflective practice, and continuous professional development",
"examples_from_case": ["Engineer A known for strong technical expertise", "Less confident in technical writing"],
"source_text": "Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing",
"confidence": 0.8,
"reasoning": "Ethical capability for professional self-awareness not explicitly covered in existing ontology"
}
],
"capability_individuals": [
{
"identifier": "EngineerA_GroundwaterAnalysis",
"capability_class": "Groundwater Monitoring Analysis Capability",
"possessed_by": "Engineer A",
"capability_statement": "Analyze groundwater monitoring data from environmental sites",
"demonstrated_through": "Over a year of site observation and monitoring",
"proficiency_level": "advanced",
"enables_obligations": "Environmental assessment and reporting obligations",
"temporal_aspect": "Demonstrated over more than one year period",
"case_context": "Applied to analyze data for emerging contaminant report",
"source_text": "perform an analysis of groundwater monitoring data from a site Engineer A had been observing for over a year",
"is_existing_class": false,
"confidence": 0.95
},
{
"identifier": "EngineerA_TechnicalExpertise",
"capability_class": "Technical Capability",
"possessed_by": "Engineer A",
"capability_statement": "Strong technical expertise in environmental engineering",
"demonstrated_through": "Several years of experience and professional engineering license",
"proficiency_level": "expert",
"enables_obligations": "Technical analysis and engineering design obligations",
"temporal_aspect": "Developed over several years of practice",
"case_context": "Recognized strength enabling client retention",
"source_text": "Engineer A, an environmental engineer with several years of experience and holding a professional engineering license",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "EngineerA_TechnicalWriting",
"capability_class": "Technical Writing Capability",
"possessed_by": "Engineer A",
"capability_statement": "Produce technical reports and documentation",
"demonstrated_through": "Previous reliance on mentor guidance and quality assurance reviews",
"proficiency_level": "intermediate",
"enables_obligations": "Professional reporting and documentation obligations",
"temporal_aspect": "Ongoing development, previously supported by mentorship",
"case_context": "Self-identified area of lower confidence requiring support",
"source_text": "Engineer A is known for their strong technical expertise but is, personally, less confident in their technical writing",
"is_existing_class": true,
"confidence": 0.9
},
{
"identifier": "EngineerA_AIToolEvaluation",
"capability_class": "AI Tool Evaluation Capability",
"possessed_by": "Engineer A",
"capability_statement": "Assess and validate AI-generated content through cross-checking and verification",
"demonstrated_through": "Thorough review, cross-checking against journal articles, search engine queries",
"proficiency_level": "basic",
"enables_obligations": "Quality assurance and accuracy verification obligations",
"temporal_aspect": "Newly developed during project execution",
"case_context": "First experience with AI drafting software requiring validation methods",
"source_text": "conducted a thorough review of the report, cross-checking key facts against professional journal articles",
"is_existing_class": true,
"confidence": 0.85
},
{
"identifier": "EngineerA_RegulatoryCompliance",
"capability_class": "Regulatory Compliance Capability",
"possessed_by": "Engineer A",
"capability_statement": "Ensure designs meet local regulations and safety standards",
"demonstrated_through": "Attempted compliance but failed to identify key safety features",
"proficiency_level": "basic",
"enables_obligations": "Safety and regulatory compliance obligations",
"temporal_aspect": "Demonstrated inadequately during design document preparation",
"case_context": "Failed to ensure AI-generated designs met all regulatory requirements",
"source_text": "omission of key safety features required by local regulations",
"is_existing_class": true,
"confidence": 0.9
},
{
"identifier": "EngineerB_TechnicalWriting",
"capability_class": "Technical Writing Capability",
"possessed_by": "Engineer B",
"capability_statement": "Provide guidance and quality assurance for technical reports",
"demonstrated_through": "Years of mentorship and supervisory review",
"proficiency_level": "expert",
"enables_obligations": "Quality assurance and mentorship obligations",
"temporal_aspect": "Previously available, now retired",
"case_context": "Previously supported Engineer A's report development",
"source_text": "relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts",
"is_existing_class": true,
"confidence": 0.95
}
]
}
```