Step 1: Contextual Framework Pass (Facts)
Extract roles, states, and resources from the facts section
Use of Artificial Intelligence in Engineering Practice
Step 1 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.
Roles Extraction
LLM Prompt
DUAL ROLE EXTRACTION - Professional Roles Analysis
EXISTING ROLE CLASSES IN ONTOLOGY:
- Employer Relationship Role: Organizational relationship balancing loyalty and independence
- Engineer Role: A professional role involving engineering practice and responsibilities
- Participant Role: A role of an involved party or stakeholder that does not itself establish professional obligations (
- Professional Peer Role: Collegial relationship with mentoring and review obligations
- Professional Role: A role within a profession that entails recognized ends/goals of practice (e.g., safeguarding public
- Provider-Client Role: Service delivery relationship with duties of competence and care
- Public Responsibility Role: Societal obligation that can override other professional duties
- Role: A role that can be realized by processes involving professional duties and ethical obligations. This
- Stakeholder Role: A participant role borne by stakeholders such as Clients, Employers, and the Public. Typically not t
=== TASK ===
From the following case text (facts section), extract information at TWO levels:
LEVEL 1 - NEW ROLE CLASSES: Identify professional roles that appear to be NEW types not covered by existing classes above. Look for:
- Specialized professional functions
- Emerging role types in engineering/technology
- Domain-specific professional positions
- Roles with unique qualifications or responsibilities
For each NEW role class, provide:
- label: Clear professional role name
- definition: Detailed description of role function and scope
- distinguishing_features: What makes this role unique/different
- professional_scope: Areas of responsibility and authority
- typical_qualifications: Required education, licensing, experience
- generated_obligations: What specific duties does this role create?
- associated_virtues: What virtues/qualities are expected (integrity, competence, etc.)?
- relationship_type: Provider-Client, Professional Peer, Employer, Public Responsibility
- domain_context: Engineering/Medical/Legal/etc.
- examples_from_case: How this role appears in the case text
- source_text: EXACT text snippet from the case where this role class is first identified or described (max 200 characters)
LEVEL 2 - ROLE INDIVIDUALS: Identify specific people mentioned who fulfill professional roles. For each person:
- name: EXACT name or identifier as it appears in the text (e.g., "Engineer A", "Client B", "Dr. Smith")
- role_classification: Which role class they fulfill (use existing classes when possible, or new class label if discovered)
- attributes: Specific qualifications, experience, titles, licenses mentioned in the text
- relationships: Employment, reporting, collaboration relationships explicitly stated
- Each relationship should specify: type (employs, reports_to, collaborates_with, serves_client, etc.) and target (person/org name)
- active_obligations: What specific duties is this person fulfilling in the case?
- ethical_tensions: Any conflicts between role obligations and personal/other obligations?
- case_involvement: How they participate in this case
- source_text: EXACT text snippet from the case where this individual is first mentioned or described (max 200 characters)
IMPORTANT: Use ONLY the actual names/identifiers found in the case text. DO NOT create realistic names or make up details not explicitly stated.
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_role_classes": [
{
"label": "Environmental Compliance Specialist",
"definition": "Professional responsible for ensuring projects meet environmental regulations and standards",
"distinguishing_features": ["Environmental regulation expertise", "Compliance assessment capabilities", "EPA standards knowledge"],
"professional_scope": "Environmental impact assessment, regulatory compliance review, permit coordination",
"typical_qualifications": ["Environmental engineering degree", "Regulatory compliance experience", "Knowledge of EPA standards"],
"generated_obligations": ["Ensure regulatory compliance", "Report violations", "Maintain environmental standards"],
"associated_virtues": ["Environmental stewardship", "Regulatory integrity", "Technical competence"],
"relationship_type": "Provider-Client",
"domain_context": "Engineering",
"examples_from_case": ["Engineer A was retained to prepare environmental assessment", "specialist reviewed compliance requirements"],
"source_text": "Engineer A was retained to prepare environmental assessment"
}
],
"role_individuals": [
{
"name": "Engineer A",
"role_classification": "Environmental Compliance Specialist",
"attributes": {
"title": "Engineer",
"license": "professional engineering license",
"specialization": "environmental engineer",
"experience": "several years of experience"
},
"relationships": [
{"type": "retained_by", "target": "Client W"}
],
"case_involvement": "Retained to prepare comprehensive report addressing organic compound characteristics",
"source_text": "Engineer A, a professional engineer with several years of experience, was retained by Client W"
}
]
}
Saved: 2026-01-05 18:46
LLM Response
```json
{
"new_role_classes": [
{
"label": "Environmental Engineer Role",
"definition": "A specialized engineering role focused on environmental assessment, contamination analysis, and groundwater infrastructure design",
"distinguishing_features": ["Groundwater monitoring expertise", "Contaminant analysis capabilities", "Environmental infrastructure design"],
"professional_scope": "Environmental site assessment, contaminant characterization, groundwater monitoring, infrastructure modification design",
"typical_qualifications": ["Environmental engineering degree", "Professional engineering license", "Experience with groundwater systems"],
"generated_obligations": ["Accurate contaminant analysis", "Proper infrastructure design", "Regulatory compliance", "Environmental protection"],
"associated_virtues": ["Environmental stewardship", "Technical competence", "Scientific accuracy"],
"relationship_type": "Provider-Client",
"domain_context": "Engineering",
"examples_from_case": ["prepare comprehensive report addressing manufacture, use, and characteristics of organic compound", "develop engineering design documents for groundwater infrastructure"],
"source_text": "Engineer A, an environmental engineer with several years of experience and holding a professional engineering license"
},
{
"label": "Engineering Mentor Role",
"definition": "A senior engineering professional who provides guidance, quality assurance reviews, and technical writing support to less experienced engineers",
"distinguishing_features": ["Quality assurance review authority", "Technical writing expertise", "Supervisory capacity"],
"professional_scope": "Mentoring junior engineers, reviewing technical reports, providing quality assurance, refining engineering documents",
"typical_qualifications": ["Senior engineering experience", "Supervisory position", "Technical writing expertise"],
"generated_obligations": ["Provide guidance", "Ensure quality of work products", "Support professional development"],
"associated_virtues": ["Professional wisdom", "Teaching ability", "Quality commitment"],
"relationship_type": "Professional Peer",
"domain_context": "Engineering",
"examples_from_case": ["relied on guidance and quality assurance reviews by their mentor and supervisor", "refine report drafts"],
"source_text": "relied on guidance and quality assurance reviews by their mentor and supervisor, Engineer B, to refine report drafts"
}
],
"role_individuals": [
{
"name": "Engineer A",
"role_classification": "Environmental Engineer Role",
"attributes": {
"title": "environmental engineer",
"license": "professional engineering license",
"experience": "several years of experience",
"weakness": "less confident in their technical writing"
},
"relationships": [
{"type": "retained_by", "target": "Client W"},
{"type": "mentored_by", "target": "Engineer B"}
],
"active_obligations": ["Prepare comprehensive report on organic compound", "Develop engineering design documents", "Analyze groundwater monitoring data"],
"ethical_tensions": "Using AI software without disclosure while applying professional seal",
"case_involvement": "Primary engineer responsible for delivering report and design documents using AI assistance",
"source_text": "Engineer A, an environmental engineer with several years of experience and holding a professional engineering license"
},
{
"name": "Client W",
"role_classification": "Stakeholder Role",
"attributes": {
"role": "Client requiring environmental engineering services"
},
"relationships": [
{"type": "retains", "target": "Engineer A"}
],
"active_obligations": ["Review draft reports", "Provide feedback on deliverables", "Ensure regulatory compliance"],
"ethical_tensions": null,
"case_involvement": "Retained Engineer A for environmental analysis and raised concerns about AI-generated design accuracy",
"source_text": "was retained by Client W to prepare a comprehensive report addressing the manufacture, use, and characteristics"
},
{
"name": "Engineer B",
"role_classification": "Engineering Mentor Role",
"attributes": {
"role": "mentor and supervisor",
"status": "recently retired"
},
"relationships": [
{"type": "mentored", "target": "Engineer A"},
{"type": "supervised", "target": "Engineer A"}
],
"active_obligations": ["Previously provided guidance and quality assurance reviews"],
"ethical_tensions": null,
"case_involvement": "Former mentor no longer available to provide guidance",
"source_text": "their mentor and supervisor, Engineer B, to refine report drafts. But Engineer B recently retired"
}
]
}
```
States Extraction
LLM Prompt
EXISTING STATE CLASSES IN ONTOLOGY (DO NOT RE-EXTRACT THESE):
STATE STATES:
- AI Tool Inexperience State: A state where a professional is using AI tools without prior experience or full understanding of their functionality, accuracy, and limitations
- AI Tool Reliance State: A state where a professional is using AI-generated content or tools for technical work without full verification processes
- Certification Required State: Checkpoint state requiring formal validation processes
- Client Risk Acceptance State: A state where a client has been fully informed of specific risks to vulnerable populations but chooses to proceed without mitigation measures
- Climate Resilience Policy State: A state where an organization has formal policies requiring infrastructure projects to incorporate climate change resilience and sustainability considerations
- Competing Duties State: State requiring ethical prioritization between conflicting obligations
- Confidentiality Breach State: A state where client confidential information has been exposed to unauthorized parties or systems without prior consent
- Conflict of Interest State: Professional situation where personal and professional interests compete
- Disproportionate Impact Discovery State: A state where a professional has discovered that a proposed solution would disproportionately harm a specific vulnerable population under certain conditions
- Insufficient Attribution State: A state where substantial contributions to work product from AI or other sources are not properly acknowledged or cited
- Make Objective Truthful Statements: Requirement for honesty in professional communications
- Mentor Absence State: A state where a professional lacks access to their established mentor or supervisor for guidance and quality assurance, affecting their confidence and work processes
- Non-Compliant State: State requiring compliance remediation
- Non-Compliant State: Problematic state requiring immediate corrective action
- Objective and Truthful Statements: Requirement for honesty in professional communications
- Professional Position Statement: Official position statements from professional organizations defining key concepts and standards
- Provide Objective Statements: Professional communication standard
- Public Statements: Requirement for honesty and objectivity in all public communications and professional statements
- Regulatory Compliance State: Legal compliance context constraining actions
- Stakeholder Division State: A state where stakeholder groups have expressed conflicting preferences for different technical solutions, creating competing pressures on professional decision-making
- State: A quality representing conditions that affect ethical decisions and professional conduct. This is the S component of the formal specification D=(R,P,O,S,Rs,A,E,Ca,Cs).
- Technical Writing Insecurity State: A state where a professional lacks confidence in a specific technical skill area despite having expertise in other aspects of their field
IMPORTANT: Only extract NEW state types not listed above!
You are analyzing a professional ethics case to extract both STATE CLASSES and STATE INSTANCES.
DEFINITIONS:
- STATE CLASS: A type of situational condition (e.g., "Conflict of Interest", "Emergency Situation", "Resource Constraint")
- STATE INDIVIDUAL: A specific instance of a state active in this case attached to specific people/organizations
CRITICAL REQUIREMENT: Every STATE CLASS you identify MUST be based on at least one specific STATE INDIVIDUAL instance in the case.
You cannot propose a state class without providing the concrete instance(s) that demonstrate it.
KEY INSIGHT FROM LITERATURE:
States are not abstract - they are concrete conditions affecting specific actors at specific times.
Each state has a subject (WHO is in the state), temporal boundaries (WHEN), and causal relationships (WHY).
YOUR TASK - Extract two LINKED types of entities:
1. NEW STATE CLASSES (types not in the existing ontology above):
- Novel types of situational states discovered in this case
- Must be sufficiently general to apply to other cases
- Should represent distinct environmental or contextual conditions
- Consider both inertial (persistent) and non-inertial (momentary) fluents
2. STATE INDIVIDUALS (specific instances in this case):
- Specific states active in this case narrative
- MUST be attached to specific individuals or organizations in the case
- Include temporal properties (when initiated, when terminated)
- Include causal relationships (triggered by what event, affects which obligations)
- Map to existing classes where possible, or to new classes you discover
EXTRACTION GUIDELINES:
For NEW STATE CLASSES, identify:
- Label: Clear, professional name for the state type
- Definition: What this state represents
- Activation conditions: What events/conditions trigger this state
- Termination conditions: What events/conditions end this state
- Persistence type: "inertial" (persists until terminated) or "non-inertial" (momentary)
- Affected obligations: Which professional duties does this state affect?
- Temporal properties: How does this state evolve over time?
- Domain context: Medical/Engineering/Legal/etc.
- Examples from case: Specific instances showing this state type
For STATE INDIVIDUALS, identify:
- Identifier: Unique descriptor (e.g., "John_Smith_ConflictOfInterest_ProjectX")
- State class: Which state type it represents (existing or new)
- Subject: WHO is in this state (person/organization name from the case)
- Initiated by: What event triggered this state?
- Initiated at: When did this state begin?
- Terminated by: What event ended this state (if applicable)?
- Terminated at: When did this state end (if applicable)?
- Affects obligations: Which specific obligations were affected?
- Urgency/Intensity: Does this state's urgency change over time?
- Related parties: Who else is affected by this state?
- Case involvement: How this state affected the case outcome
CASE TEXT FROM 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.
Respond with a JSON structure. Here's a CONCRETE EXAMPLE showing the required linkage:
EXAMPLE (if the case mentions "Engineer A faced a conflict when discovering his brother worked for the contractor"):
{
"new_state_classes": [
{
"label": "Family Conflict of Interest",
"definition": "A state where a professional's family relationships create potential bias in professional decisions",
"activation_conditions": ["Discovery of family member involvement", "Family member has financial interest"],
"termination_conditions": ["Recusal from decision", "Family member withdraws"],
"persistence_type": "inertial",
"affected_obligations": ["Duty of impartiality", "Disclosure requirements"],
"temporal_properties": "Persists until formally addressed through recusal or disclosure",
"domain_context": "Engineering",
"examples_from_case": ["Engineer A discovered brother worked for ABC Contractors"],
"source_text": "Engineer A faced a conflict when discovering his brother worked for the contractor",
"confidence": 0.85,
"rationale": "Specific type of conflict not covered by general COI in existing ontology"
}
],
"state_individuals": [
{
"identifier": "EngineerA_FamilyConflict_ABCContractors",
"state_class": "Family Conflict of Interest",
"subject": "Engineer A",
"initiated_by": "Discovery that brother is senior manager at ABC Contractors",
"initiated_at": "When bidding process began",
"terminated_by": "Engineer A recused from contractor selection",
"terminated_at": "Two weeks after discovery",
"affects_obligations": ["Maintain impartial contractor selection", "Disclose conflicts to client"],
"urgency_level": "high",
"related_parties": ["Client B", "ABC Contractors", "Engineer A's brother"],
"case_involvement": "Led to Engineer A's recusal from contractor selection process",
"source_text": "Engineer A discovered his brother is senior manager at ABC Contractors during the bidding process",
"is_existing_class": false,
"confidence": 0.9
}
]
}
YOUR RESPONSE FORMAT (use the same structure with YOUR case's specific details):
{
"new_state_classes": [
// For each new state type you discover
],
"state_individuals": [
// For each specific instance in the case (MUST have at least one per new class)
]
}
EXTRACTION RULES:
1. For EVERY new state class you identify, you MUST provide at least one corresponding state individual
2. State individuals MUST have a clear subject (specific person/organization from the case)
3. If you cannot identify a specific instance, do not create the state class
4. States without subjects are invalid (e.g., cannot have "general emergency" - must be "City M's water emergency")
5. Each state individual should clearly demonstrate why its state class is needed
Focus on states that:
1. Are attached to specific individuals or organizations mentioned in the case
2. Have clear temporal boundaries (when initiated, when terminated)
3. Affect specific ethical obligations or professional duties
4. Show causal relationships with events in the case
5. Demonstrate the context-dependent nature of professional ethics
EXAMPLE OF CORRECT EXTRACTION:
State Class: "Public Health Risk State"
State Individual: "City_M_PublicHealthRisk_2023" with subject="City M", initiated_by="Decision to change water source", affects_obligations=["Ensure public safety", "Provide clean water"]
EXAMPLE OF INCORRECT EXTRACTION:
State Class: "Emergency Situation" with NO corresponding individual (INVALID - no specific instance)
Saved: 2026-01-05 18:47
LLM Response
```json
{
"new_state_classes": [
{
"label": "Mentor Loss State",
"definition": "A state where a professional has lost access to their established mentor or supervisor due to retirement, departure, or other circumstances, affecting their work processes and confidence",
"activation_conditions": ["Mentor retires", "Mentor leaves organization", "Mentor becomes unavailable"],
"termination_conditions": ["New mentor assigned", "Professional develops independent confidence", "Alternative support system established"],
"persistence_type": "inertial",
"affected_obligations": ["Quality assurance processes", "Professional development", "Work product review"],
"temporal_properties": "Persists until alternative support or confidence is established",
"domain_context": "Engineering",
"examples_from_case": ["Engineer B retired and was no longer available to Engineer A in a work capacity"],
"source_text": "Engineer B recently retired and was no longer available to Engineer A in a work capacity",
"confidence": 0.95,
"rationale": "Distinct from general Mentor Absence State as it specifically involves permanent loss rather than temporary absence"
},
{
"label": "AI Tool First-Use State",
"definition": "A state where a professional is using AI tools for the first time without prior experience, training, or understanding of the tool's capabilities and limitations",
"activation_conditions": ["First use of AI tool", "No prior training on tool", "Lack of familiarity with tool functionality"],
"termination_conditions": ["Completion of training", "Gaining experience with tool", "Switching to familiar tools"],
"persistence_type": "inertial",
"affected_obligations": ["Competence in tool use", "Understanding tool limitations", "Quality verification"],
"temporal_properties": "Persists through initial usage period until familiarity is gained",
"domain_context": "Engineering",
"examples_from_case": ["The AI drafting software was new to the market and Engineer A had no previous experience with the tool"],
"source_text": "The AI drafting software was new to the market and Engineer A had no previous experience with the tool",
"confidence": 0.9,
"rationale": "More specific than general AI Tool Inexperience State - focuses on first-time usage scenario"
},
{
"label": "Draft Submission State",
"definition": "A state where a professional has submitted draft documents with professional seal applied, creating ambiguity about the document's completeness and review status",
"activation_conditions": ["Submission of draft document", "Application of professional seal to draft", "Client review pending"],
"termination_conditions": ["Final document submitted", "Draft status clarified", "Seal removed from draft"],
"persistence_type": "non-inertial",
"affected_obligations": ["Clear communication of document status", "Proper use of professional seal", "Document completeness standards"],
"temporal_properties": "Momentary state at time of submission",
"domain_context": "Engineering",
"examples_from_case": ["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"],
"source_text": "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",
"confidence": 0.85,
"rationale": "Represents the problematic state of sealed draft documents that may confuse document status"
}
],
"state_individuals": [
{
"identifier": "EngineerA_MentorLoss_EngineerB_Retirement",
"state_class": "Mentor Loss State",
"subject": "Engineer A",
"initiated_by": "Engineer B's retirement",
"initiated_at": "Before the Client W project began",
"terminated_by": "Not terminated in case narrative",
"terminated_at": "Ongoing",
"affects_obligations": ["Quality assurance review of reports", "Technical writing confidence", "Work product refinement"],
"urgency_level": "medium",
"related_parties": ["Engineer B", "Client W"],
"case_involvement": "Led Engineer A to seek AI tools as alternative support for report writing",
"source_text": "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",
"is_existing_class": false,
"confidence": 0.95
},
{
"identifier": "EngineerA_AIFirstUse_OpenSourceAI",
"state_class": "AI Tool First-Use State",
"subject": "Engineer A",
"initiated_by": "Decision to use open-sourced AI software for report drafting",
"initiated_at": "When starting work on Client W's report",
"terminated_by": "Not terminated in case narrative",
"terminated_at": "Ongoing through project",
"affects_obligations": ["Understanding tool accuracy", "Verifying AI-generated content", "Proper attribution of AI use"],
"urgency_level": "high",
"related_parties": ["Client W"],
"case_involvement": "Resulted in incomplete understanding of AI functionality and failure to cite AI use",
"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_TechnicalWritingInsecurity",
"state_class": "Technical Writing Insecurity State",
"subject": "Engineer A",
"initiated_by": "Long-standing personal assessment of writing skills",
"initiated_at": "Pre-existing condition",
"terminated_by": "Not terminated in case narrative",
"terminated_at": "Ongoing",
"affects_obligations": ["Report quality", "Professional communication standards", "Self-sufficiency in deliverables"],
"urgency_level": "medium",
"related_parties": ["Client W", "Engineer B"],
"case_involvement": "Motivated reliance on AI tools and previous dependence on Engineer B's reviews",
"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": 0.95
},
{
"identifier": "EngineerA_DraftSubmission_ClientWReport",
"state_class": "Draft Submission State",
"subject": "Engineer A",
"initiated_by": "Submission of draft report with seal to Client W",
"initiated_at": "Upon initial report submission",
"terminated_by": "Client review and feedback",
"terminated_at": "When Client W provided feedback",
"affects_obligations": ["Clear document status communication", "Appropriate use of professional seal", "Professional standards for draft documents"],
"urgency_level": "medium",
"related_parties": ["Client W"],
"case_involvement": "Created potential confusion about document completeness despite draft labeling",
"source_text": "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",
"is_existing_class": false,
"confidence": 0.85
},
{
"identifier": "EngineerA_InsufficientAttribution_AIContent",
"state_class": "Insufficient Attribution State",
"subject": "Engineer A",
"initiated_by": "Failure to cite AI software use in report and design documents",
"initiated_at": "When submitting documents to Client W",
"terminated_by": "Not terminated in case narrative",
"terminated_at": "Ongoing",
"affects_obligations": ["Transparency in work methods", "Proper attribution of sources", "Honest representation of work origin"],
"urgency_level": "high",
"related_parties": ["Client W"],
"case_involvement": "Client W unaware of AI involvement in document creation",
"source_text": "Engineer A did not cite their use of AI-software or its large language models... Engineer A did not cite the AI-assisted drafting tools",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "EngineerA_NonCompliant_DesignDocuments",
"state_class": "Non-Compliant State",
"subject": "Engineer A's design documents",
"initiated_by": "Discovery of misaligned dimensions and missing safety features",
"initiated_at": "When Client W reviewed the design documents",
"terminated_by": "Revision instructions from Client W",
"terminated_at": "Pending revision completion",
"affects_obligations": ["Meet regulatory standards", "Ensure design accuracy", "Include required safety features"],
"urgency_level": "high",
"related_parties": ["Engineer A", "Client W"],
"case_involvement": "Required immediate revision to meet professional and regulatory standards",
"source_text": "Client W noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations",
"is_existing_class": true,
"confidence": 0.95
}
]
}
```
Resources Extraction
LLM Prompt
EXISTING RESOURCE CLASSES IN ONTOLOGY (DO NOT RE-EXTRACT THESE):
- Legal Resource: Legal framework constraining professional practice
- Resource: An independent continuant entity that serves as input or reference for professional activities. This is the Rs component of the formal specification D=(R,P,O,S,Rs,A,E,Ca,Cs).
- Resource Constrained: Resource limitation affecting available actions
- Resource Constraint: Limitations on available time, budget, materials, or human resources (Ganascia 2007)
- Resource Type: Meta-class for specific resource types recognized by the ProEthica system
- Resources Available: Resource sufficiency enabling full options
IMPORTANT: Only extract NEW resource types not listed above!
You are analyzing a professional ethics case to extract both RESOURCE CLASSES and RESOURCE INSTANCES.
DEFINITIONS:
- RESOURCE CLASS: A type of document, tool, standard, or knowledge source (e.g., "Emergency Response Protocol", "Technical Specification", "Ethics Code")
- RESOURCE INDIVIDUAL: A specific instance of a resource used in this case (e.g., "NSPE Code of Ethics 2023", "City M Water Quality Standards")
CRITICAL REQUIREMENT: Every RESOURCE CLASS you identify MUST be based on at least one specific RESOURCE INDIVIDUAL instance in the case.
You cannot propose a resource class without providing the concrete instance(s) that demonstrate it.
YOUR TASK - Extract two LINKED types of entities:
1. NEW RESOURCE CLASSES (types not in the existing ontology above):
- Novel types of resources discovered in this case
- Must be sufficiently general to apply to other cases
- Should represent distinct categories of decision-making resources
- Consider documents, tools, standards, guidelines, databases, etc.
2. RESOURCE INDIVIDUALS (specific instances in this case):
- Specific documents, tools, or knowledge sources mentioned
- MUST have identifiable titles or descriptions
- Include metadata (creator, date, version) where available
- Map to existing classes where possible, or to new classes you discover
EXTRACTION GUIDELINES:
For NEW RESOURCE CLASSES, identify:
- Label: Clear, professional name for the resource type
- Definition: What this resource type represents
- Resource type: document, tool, standard, guideline, database, etc.
- Accessibility: public, restricted, proprietary, etc.
- Authority source: Who typically creates/maintains these resources
- Typical usage: How these resources are typically used
- Domain context: Medical/Engineering/Legal/etc.
- Examples from case: Specific instances showing this resource type
For RESOURCE INDIVIDUALS, identify:
- Identifier: Unique descriptor (e.g., "NSPE_CodeOfEthics_2023")
- Resource class: Which resource type it represents (existing or new)
- Document title: Official name or description
- Created by: Organization or authority that created it
- Created at: When it was created (if mentioned)
- Version: Edition or version information
- URL or location: Where to find it (if mentioned)
- Used by: Who used this resource in the case
- Used in context: How this resource was applied
- Case involvement: How this resource affected decisions
CASE TEXT FROM 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.
Respond with a JSON structure. Here's an EXAMPLE:
EXAMPLE (if the case mentions "Engineer A consulted the NSPE Code of Ethics and the state's engineering regulations"):
{
"new_resource_classes": [
{
"label": "State Engineering Regulations",
"definition": "Legal requirements and regulations governing engineering practice at the state level",
"resource_type": "regulatory_document",
"accessibility": ["public", "official"],
"authority_source": "State Engineering Board",
"typical_usage": "Legal compliance and professional practice guidance",
"domain_context": "Engineering",
"examples_from_case": ["State engineering regulations consulted by Engineer A"],
"source_text": "Engineer A consulted the state's engineering regulations",
"confidence": 0.85,
"rationale": "Specific type of regulatory resource not in existing ontology"
}
],
"resource_individuals": [
{
"identifier": "NSPE_CodeOfEthics_Current",
"resource_class": "Professional Ethics Code",
"document_title": "NSPE Code of Ethics",
"created_by": "National Society of Professional Engineers",
"created_at": "Current version",
"version": "Current",
"used_by": "Engineer A",
"used_in_context": "Consulted for ethical guidance on conflict of interest",
"case_involvement": "Provided framework for ethical decision-making",
"source_text": "Engineer A consulted the NSPE Code of Ethics",
"is_existing_class": true,
"confidence": 0.95
},
{
"identifier": "State_Engineering_Regulations_Current",
"resource_class": "State Engineering Regulations",
"document_title": "State Engineering Practice Act and Regulations",
"created_by": "State Engineering Board",
"used_by": "Engineer A",
"used_in_context": "Referenced for legal requirements",
"case_involvement": "Defined legal obligations for professional practice",
"source_text": "Engineer A referenced the State Engineering Practice Act and Regulations",
"is_existing_class": false,
"confidence": 0.9
}
]
}
EXTRACTION RULES:
1. For EVERY new resource class you identify, you MUST provide at least one corresponding resource individual
2. Resource individuals MUST have identifiable titles or descriptions
3. If you cannot identify a specific instance, do not create the resource class
4. Focus on resources that directly influence decision-making in the case
5. Each resource individual should clearly demonstrate why its resource class is needed
Focus on resources that:
1. Are explicitly mentioned or referenced in the case
2. Guide professional decisions or actions
3. Provide standards, requirements, or frameworks
4. Serve as knowledge sources for the professionals involved
Saved: 2026-01-05 18:48
LLM Response
```json
{
"new_resource_classes": [
{
"label": "AI Software Tool",
"definition": "Artificial intelligence software applications used to assist in professional tasks such as drafting, analysis, or design generation",
"resource_type": "software_tool",
"accessibility": ["open-source", "commercial", "proprietary"],
"authority_source": "Software developers/AI companies",
"typical_usage": "Automated content generation, design assistance, data analysis support",
"domain_context": "Cross-domain (Engineering, Technical Writing)",
"examples_from_case": ["Open-sourced AI software for report drafting", "AI-assisted drafting tools for design documents"],
"source_text": "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",
"confidence": 0.95,
"rationale": "Specific type of technological tool resource increasingly relevant to professional practice"
},
{
"label": "Professional Journal Article",
"definition": "Peer-reviewed academic or professional publications containing technical information, research findings, or industry standards",
"resource_type": "document",
"accessibility": ["public", "subscription-based"],
"authority_source": "Academic institutions, professional societies, research organizations",
"typical_usage": "Fact verification, technical reference, knowledge validation",
"domain_context": "Engineering, Environmental Science",
"examples_from_case": ["Professional journal articles used for cross-checking facts"],
"source_text": "Engineer A conducted a thorough review of the report, cross-checking key facts against professional journal articles",
"confidence": 0.9,
"rationale": "Distinct type of authoritative knowledge resource used for validation"
},
{
"label": "Local Safety Regulations",
"definition": "Municipality or locality-specific regulations governing safety requirements for engineering projects and infrastructure",
"resource_type": "regulatory_document",
"accessibility": ["public", "official"],
"authority_source": "Local government, municipal authorities",
"typical_usage": "Compliance verification, safety standard implementation, design requirements",
"domain_context": "Engineering, Construction",
"examples_from_case": ["Local regulations requiring key safety features"],
"source_text": "Client W noticed several issues with the AI-generated design documents, including misaligned dimensions and an omission of key safety features required by local regulations",
"confidence": 0.85,
"rationale": "Specific type of local regulatory resource distinct from state-level regulations"
},
{
"label": "Groundwater Monitoring Data",
"definition": "Technical data collected from environmental monitoring systems tracking groundwater conditions, contamination levels, and related parameters",
"resource_type": "dataset",
"accessibility": ["restricted", "client-proprietary"],
"authority_source": "Environmental monitoring systems, client organizations",
"typical_usage": "Environmental analysis, contamination assessment, engineering design input",
"domain_context": "Environmental Engineering",
"examples_from_case": ["Groundwater monitoring data from site observed for over a year"],
"source_text": "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",
"confidence": 0.9,
"rationale": "Specific type of technical data resource essential for environmental engineering decisions"
}
],
"resource_individuals": [
{
"identifier": "OpenSource_AI_ReportDrafting_Software",
"resource_class": "AI Software Tool",
"document_title": "Open-sourced AI software for report generation",
"created_by": "Unspecified AI software developer",
"version": "New to market version",
"used_by": "Engineer A",
"used_in_context": "Used to synthesize information and generate initial draft of contamination report",
"case_involvement": "Generated initial report draft that required review and verification",
"source_text": "Engineer A opted to use open-sourced artificial intelligence (AI) software to create an initial draft of the necessary report",
"is_existing_class": false,
"confidence": 0.95
},
{
"identifier": "AI_Assisted_Design_Drafting_Tools",
"resource_class": "AI Software Tool",
"document_title": "AI-assisted drafting tools for engineering design",
"created_by": "Unspecified software developer",
"used_by": "Engineer A",
"used_in_context": "Generated preliminary design plans and technical specifications",
"case_involvement": "Produced design documents with errors including misaligned dimensions and missing safety features",
"source_text": "use AI-assisted drafting tools to generate preliminary design documents",
"is_existing_class": false,
"confidence": 0.95
},
{
"identifier": "Professional_Journal_Articles_Verification",
"resource_class": "Professional Journal Article",
"document_title": "Professional journal articles (multiple, unspecified)",
"created_by": "Various academic and professional authors",
"used_by": "Engineer A",
"used_in_context": "Cross-checking key facts in AI-generated report",
"case_involvement": "Served as authoritative sources for fact verification",
"source_text": "cross-checking key facts against professional journal articles",
"is_existing_class": false,
"confidence": 0.85
},
{
"identifier": "Local_Safety_Regulations_Site",
"resource_class": "Local Safety Regulations",
"document_title": "Local regulations for groundwater infrastructure safety",
"created_by": "Local regulatory authority",
"used_by": "Client W (for review)",
"used_in_context": "Identified missing safety features in AI-generated design",
"case_involvement": "Revealed compliance gaps in engineering design documents",
"source_text": "omission of key safety features required by local regulations",
"is_existing_class": false,
"confidence": 0.85
},
{
"identifier": "Site_Groundwater_Monitoring_Data_Year",
"resource_class": "Groundwater Monitoring Data",
"document_title": "Groundwater monitoring data from observed site",
"created_by": "Site monitoring system/Client W",
"created_at": "Collected over one year period",
"used_by": "Engineer A",
"used_in_context": "Analysis for contamination report and infrastructure design",
"case_involvement": "Primary data source for engineering analysis and recommendations",
"source_text": "groundwater monitoring data from a site Engineer A had been observing for over a year",
"is_existing_class": false,
"confidence": 0.9
},
{
"identifier": "Client_W_Information_Package",
"resource_class": "Resource",
"document_title": "Relevant information provided by Client W",
"created_by": "Client W",
"used_by": "Engineer A",
"used_in_context": "Input into AI software for report and design generation",
"case_involvement": "Source material for AI-generated documents",
"source_text": "Engineer A gathered the relevant information provided by Client W",
"is_existing_class": true,
"confidence": 0.85
}
]
}
```