Step 4: Case Synthesis

Build a coherent case model from extracted entities

Back to Case
Pipeline Steps
Overview
1 Contextual Framework
2 Normative Requirements
3 Temporal Dynamics Reconcile
4 Whole-Case Synthesis
Extraction Review Full View
Provenance
Use of Artificial Intelligence in Engineering Practice
Step 4 of 5
Four-Phase Synthesis Pipeline
1
Entity Foundation
Passes 1-3
2
Analytical Extraction
2A-2E
3
Decision Synthesis
E1-E3 + LLM
4
Narrative
Timeline + Scenario
Phase 1 Entity Foundation
211 entities
Pass 1: Contextual Framework
  • 15 Roles
  • 23 States
  • 12 Resources
Pass 2: Normative Requirements
  • 29 Principles
  • 34 Obligations
  • 32 Constraints
  • 33 Capabilities
Pass 3: Temporal Dynamics
  • 33 Temporal Dynamics
Phase 2 Analytical Extraction
2A: Code Provisions 9
LLM detect algorithmic linking Case text + Phase 1 entities
I.1. Hold paramount the safety, health, and welfare of the public.
I.2. Perform services only in areas of their competence.
I.5. Avoid deceptive acts.
II.1.c. Engineers shall not reveal facts, data, or information without the prior consent of the client or employer except as authorized or required by law or ...
II.2.a. Engineers shall undertake assignments only when qualified by education or experience in the specific technical fields involved.
II.2.b. Engineers shall not affix their signatures to any plans or documents dealing with subject matter in which they lack competence, nor to any plan or doc...
III.3. Engineers shall avoid all conduct or practice that deceives the public.
III.8.a. Engineers shall conform with state registration laws in the practice of engineering.
III.9. Engineers shall give credit for engineering work to those to whom credit is due, and will recognize the proprietary interests of others.
2B: Precedent Cases 2
LLM extraction Case text
BER Case 90-6 analogizing
linked
It is ethical for an engineer to sign and seal documents created using a CADD system, whether prepared by the engineer themselves or by others working under their direction and control, provided the engineer has the requisite background, education, and training to be proficient with the technology and its limitations.
BER Case 98-3 distinguishing
linked
It is unethical for an engineer to offer services using new technology in areas where they lack competence and experience; technology has an important place in engineering practice but must never be a replacement or substitute for engineering judgment.
2C: Questions & Conclusions 21 28
Board text parsed LLM analytical Q&C LLM Q-C linking Case text + 2A provisions
Questions (21)
Question_1 Was Engineer A’s use of AI to create the report text ethical, given that Engineer A thoroughly checked the report?
Question_2 Was Engineer A’s use of AI-assisted drafting tools to create the engineering design documents ethical, given that Engineer A reviewed the design at a ...
Question_3 If the use of AI was acceptable, did Engineer A have an ethical obligation to disclose the use of AI in any form to the Client?
Question_101 By uploading Client W's confidential site data and groundwater monitoring information into an open-source AI platform without obtaining prior consent,...
Question_102 Given that Engineer B's retirement removed the primary quality assurance mechanism Engineer A had relied upon, did Engineer A have an independent ethi...
Question_103 When Client W observed that the report read as if written by two different authors, did Engineer A incur an immediate ethical obligation to proactivel...
Question_104 Does Engineer A's failure to include citations to the professional journal articles used to cross-check AI-generated content constitute a violation of...
Question_201 Does the principle of Professional Competence Satisfied for Report Writing conflict with the principle of Intellectual Honesty in Authorship when Engi...
Question_202 Does the principle of Responsible Charge Engagement conflict with the principle of Competence Assurance Under Novel Tool Adoption when an engineer app...
Question_203 Does the principle of Client Data Confidentiality in AI Tool Use conflict with the principle of Mentorship Continuity and Succession Planning when an ...
Question_204 Does the principle of Public Welfare Paramount conflict with the principle of AI Tool Transparency and Disclosure Applied to Client W Relationship whe...
Question_301 From a deontological perspective, did Engineer A fulfill their duty of candor toward Client W by submitting AI-generated work products without disclos...
Question_302 From a deontological perspective, did Engineer A breach their categorical duty to maintain Responsible Charge by sealing engineering design documents ...
Question_303 From a consequentialist perspective, did the harm produced by Engineer A's cursory review of AI-generated design documents - resulting in misaligned d...
Question_304 From a virtue ethics perspective, did Engineer A demonstrate the professional integrity and intellectual honesty expected of a licensed engineer by pe...
Question_305 From a virtue ethics perspective, did Engineer A exhibit the prudence and professional humility expected of a competent engineer by choosing to deploy...
Question_306 From a consequentialist perspective, did Engineer A's decision to input Client W's confidential site data into open-source AI software - without obtai...
Question_401 If Engineer A had disclosed their intended use of open-source AI software to Client W before beginning work, and Client W had withheld consent to uplo...
Question_402 If Engineer A had conducted a rigorous, line-by-line technical review of the AI-generated design documents - equivalent to the thorough review applied...
Question_403 If Engineer B had not retired and had continued to provide quality assurance review of Engineer A's work products, would Engineer A have been less lik...
Question_404 If Engineer A had explicitly cited the use of AI software in the report - including identifying which sections were AI-generated and which were indepe...
Conclusions (28)
Conclusion_1 Engineer A's use of AI in report writing was partly ethical, and partly unethical.
Conclusion_2 The use of AI-assisted drafting tools by Engineer A was not unethical per se.
Conclusion_3 Similar to other software used in the design or detailing process, Engineer A has no professional or ethical obligation to disclose AI use to Client W...
Conclusion_101 Beyond the Board's finding that Engineer A's use of AI in report writing was partly ethical and partly unethical, a critical and independent ethical b...
Conclusion_102 The Board's conclusion that AI-assisted drafting tools are not unethical per se must be qualified by a competence threshold that Engineer A did not me...
Conclusion_103 The Board's conclusion that Engineer A has no universal ethical obligation to disclose AI use to Client W - analogizing AI tools to other engineering ...
Conclusion_104 The Board's analysis does not address a systemic professional vulnerability exposed by this case: Engineer A's over-reliance on AI tools was directly ...
Conclusion_105 The Board's finding that Engineer A's use of AI was partly unethical with respect to the design documents is further supported by the public safety di...
Conclusion_106 Engineer A's failure to cite the professional journal articles used to cross-check AI-generated content, and the absence of any attribution for the AI...
Conclusion_201 In response to Q101: Engineer A's upload of Client W's confidential site data and groundwater monitoring information into an open-source AI platform c...
Conclusion_202 In response to Q102: Engineer B's retirement did not merely create an inconvenience for Engineer A - it removed the primary quality assurance mechanis...
Conclusion_203 In response to Q103: When Client W directly observed that the report appeared to have been written by two different authors - a stylistically inconsis...
Conclusion_204 In response to Q104: Engineer A's failure to cite the professional journal articles used to cross-check AI-generated content raises a concern under Co...
Conclusion_205 In response to Q201: A genuine tension exists between the principle that professional competence in report writing can be satisfied through thorough p...
Conclusion_206 In response to Q202: The tension between Responsible Charge Engagement and Competence Assurance Under Novel Tool Adoption is not merely theoretical - ...
Conclusion_207 In response to Q204: The Board's conclusion that there is no universal ethical obligation to disclose AI use is placed under significant strain by the...
Conclusion_208 In response to Q301: From a deontological perspective, Engineer A did not fulfill their duty of candor toward Client W. Kantian deontological ethics e...
Conclusion_209 In response to Q302: From a deontological perspective, Engineer A breached their categorical duty to maintain Responsible Charge by sealing engineerin...
Conclusion_210 In response to Q303: From a consequentialist perspective, the harm produced by Engineer A's cursory review of AI-generated design documents - resultin...
Conclusion_211 In response to Q304: From a virtue ethics perspective, Engineer A did not demonstrate the professional integrity and intellectual honesty expected of ...
Conclusion_212 In response to Q305: From a virtue ethics perspective, Engineer A did not exhibit the prudence and professional humility expected of a competent engin...
Conclusion_213 In response to Q306: From a consequentialist perspective, Engineer A's decision to input Client W's confidential site data into open-source AI softwar...
Conclusion_214 In response to Q401: If Engineer A had disclosed their intended use of open-source AI software to Client W before beginning work, and Client W had wit...
Conclusion_215 In response to Q402: If Engineer A had conducted a rigorous, line-by-line technical review of the AI-generated design documents - equivalent in thorou...
Conclusion_216 In response to Q404: If Engineer A had explicitly cited the use of AI software in the report - identifying which sections were AI-generated and which ...
Conclusion_301 The tension between Professional Competence Satisfied for Report Writing and Intellectual Honesty in Authorship was left substantively unresolved by t...
Conclusion_302 The tension between Responsible Charge Engagement and Competence Assurance Under Novel Tool Adoption was resolved against Engineer A in the design doc...
Conclusion_303 The tension between Client Data Confidentiality in AI Tool Use and Mentorship Continuity and Succession Planning exposes a systemic vulnerability that...
2D: Transformation Classification
stalemate 82%
LLM classification Phase 1 entities + 2C Q&C

Engineer A remains trapped between irreconcilable professional obligations that the Board acknowledged but declined to definitively prioritize: the obligation to exercise responsible charge conflicts with the obligation to deploy only competently understood tools; the obligation of intellectual honesty in authorship conflicts with the Board's acceptance of thorough verification as sufficient; the obligation to protect client confidentiality conflicts with the practical need for quality assurance after Engineer B's retirement; and the Board's general no-disclosure rule conflicts with the specific facts that created an affirmative duty to speak when Client W raised the stylistic anomaly. No obligation was cleanly transferred to another party, no cycle of alternating responsibility was established, and no temporal gap between action and consequence defines the primary pattern — instead, multiple valid but incompatible duties persist simultaneously across the Engineer A / Client W / public safety triad, with the Board explicitly noting that its conclusions are conditional, provisional, or require qualification rather than resolved.

Reasoning

The Board's resolution produced multiple qualified, conditional, and explicitly unresolved conclusions rather than clean handoffs of responsibility to any single party. Competing obligations — competence versus authorship integrity, public welfare versus disclosure discretion, confidentiality versus quality assurance — were acknowledged as simultaneously valid but left without definitive hierarchical resolution, precisely matching the Marchais-Roubelat & Roubelat definition of stakeholders trapped in a set of rules where competing duties cannot both be fulfilled. The Board's own language — 'provisional rather than definitive,' 'conditional not categorical,' 'requires significant qualification' — signals that the ethical situation did not resolve into a new stable configuration but remained suspended in unresolved tension across multiple obligation axes.

2E: Rich Analysis (Causal Links, Question Emergence, Resolution Patterns)
LLM batched analysis label-to-URI resolution Phase 1 entities + 2C Q&C + 2A provisions
Causal-Normative Links (6)
CausalLink_Chose AI for Report Drafting Engineer A's decision to select an AI drafting tool to compensate for self-assessed technical writing limitations, without prior experience or mentor ...
CausalLink_Input Confidential Data into P Uploading Client W's confidential information into a publicly accessible open-source AI interface directly violates the obligation to obtain client co...
CausalLink_Conducted Thorough Report Revi Although Engineer A conducted a thorough review of the AI-generated report draft, partially satisfying responsible charge and competence verification ...
CausalLink_Submitted Report Without AI Di Submitting the AI-drafted report to Client W without disclosing the use of AI tools or providing proper attribution violates multiple disclosure, tran...
CausalLink_Used AI for Design Document Ge Engineer A's use of an unfamiliar open-source AI tool to generate groundwater infrastructure design documents, without adequate verification or respon...
CausalLink_Conducted Cursory Design Docum By performing only a cursory review of AI-generated design documents rather than a thorough, responsible-charge-level verification, Engineer A failed ...
Question Emergence (21)
QuestionEmergence_1 The question emerged because Engineer A's thorough review created a plausible claim of responsible charge compliance, yet the AI's role as primary tex...
QuestionEmergence_2 The question arose because the combination of an unfamiliar AI tool, a complex dual-scope engagement, and only cursory review produced design document...
QuestionEmergence_3 The question emerged precisely because it is conditional: even granting the permissibility of AI use, a separate normative question remains about whet...
QuestionEmergence_4 The question emerged because Engineer A's upload of confidential client data to a public AI platform created a potential confidentiality breach that i...
QuestionEmergence_5 The question emerged because Engineer B's retirement transformed what had been a structural quality assurance feature of Engineer A's practice into a ...
QuestionEmergence_6 This question emerged because the data event of Client W detecting a stylistic inconsistency created a concrete moment at which the gap between Engine...
QuestionEmergence_7 This question arose because the data configuration-AI-generated prose validated against uncited journal sources and submitted as a professional report...
QuestionEmergence_8 This conflict question emerged because the same factual act-thorough verification-simultaneously satisfies one principle and is invoked to justify con...
QuestionEmergence_9 This conflict question emerged because the introduction of a novel AI drafting tool created a situation where two obligations that normally reinforce ...
QuestionEmergence_10 This conflict question emerged because Engineer B's retirement created a structural gap in Engineer A's quality assurance infrastructure at precisely ...
QuestionEmergence_11 This question emerged because the Board's ruling created a logical gap: by declining to establish a universal AI disclosure obligation, it left unreso...
QuestionEmergence_12 This question arose because deontological duty of candor contains an internal ambiguity: it is unclear whether the duty runs to the accuracy of output...
QuestionEmergence_13 This question emerged because the act of sealing is legally and ethically binary - the seal is either properly affixed or it is not - yet the standard...
QuestionEmergence_14 This question arose because consequentialism's standard unit of analysis - the action and its consequences - is ambiguous when the action is composite...
QuestionEmergence_15 This question emerged because virtue ethics evaluates character rather than acts or outcomes, yet the relevant virtues - integrity, honesty, and compe...
QuestionEmergence_16 This question emerged because Engineer B's retirement removed the established quality assurance structure precisely when Engineer A introduced an unfa...
QuestionEmergence_17 This question emerged because the act of inputting confidential client data into a public AI platform without disclosure created a concrete, identifia...
QuestionEmergence_18 This question emerged from the structural gap between Engineer A's undisclosed AI use and the consent framework that should have governed it, forcing ...
QuestionEmergence_19 This question emerged because the contrast between Engineer A's thorough review of the report and cursory review of the design documents created an ob...
QuestionEmergence_20 This question emerged because Engineer B's retirement created a structural discontinuity in Engineer A's professional support system that coincided wi...
QuestionEmergence_21 This question emerged because Client W's observation of stylistic inconsistency created an evidentiary gap: without disclosure, the anomaly is unexpla...
Resolution Patterns (28)
ResolutionPattern_1 The board reached a split conclusion by anchoring its analysis on the quality and depth of Engineer A's post-AI review rather than on AI use itself: b...
ResolutionPattern_2 The board concluded that AI-assisted drafting is not inherently unethical because the Code's obligations attach to the engineer's professional judgmen...
ResolutionPattern_3 The board concluded there is no freestanding ethical obligation to disclose AI use to a client because engineering accountability runs through the pro...
ResolutionPattern_4 The board identified a self-standing ethical violation under Code provision II.1.c because Engineer A's act of uploading confidential client data to a...
ResolutionPattern_5 The board concluded that C2's permissive finding about AI drafting tools must be read as conditional rather than categorical: because ethical AI tool ...
ResolutionPattern_6 The board resolved the disclosure question by rejecting a blanket rule in either direction: Engineer A had no universal obligation to disclose AI use,...
ResolutionPattern_7 The board resolved this question by finding that Engineer A's ethical failure was not merely in how AI was used but in the prior decision to use it as...
ResolutionPattern_8 The board resolved the design document ethics question by elevating it beyond a procedural review lapse: because Engineer A sealed documents containin...
ResolutionPattern_9 The board resolved the citation and attribution question by reading Code provision III.9 expansively: beyond preventing credit-theft, it carries an af...
ResolutionPattern_10 The board resolved the confidentiality question by establishing that Engineer A committed a discrete, self-contained ethical violation under Code prov...
ResolutionPattern_11 The board concluded that Engineer A violated the competence standard under I.2 and II.2.a because qualification for a complex engagement includes main...
ResolutionPattern_12 The board concluded that Engineer A's silence when Client W identified the stylistic inconsistency constituted a deceptive act under I.5 and conduct t...
ResolutionPattern_13 The board concluded that Engineer A's failure to cite the journal articles used to verify AI-generated content violated the credit-giving obligation u...
ResolutionPattern_14 The board concluded that Engineer A's thorough factual verification of AI-generated report text was sufficient to render that use of AI ethical under ...
ResolutionPattern_15 The board concluded that Engineer A violated II.2.b by affixing their professional seal to AI-generated design documents after only a cursory review, ...
ResolutionPattern_16 The Board resolved Q11 by qualifying its general conclusion that disclosure is not universally required: it held that the public welfare paramount pri...
ResolutionPattern_17 The Board resolved Q12 by applying Kantian deontological analysis: because the maxim underlying Engineer A's conduct - submitting AI-generated work wi...
ResolutionPattern_18 The Board resolved Q13 by holding that Engineer A categorically breached the Responsible Charge duty the moment they affixed their seal to documents t...
ResolutionPattern_19 The Board resolved Q14 by applying consequentialist expected-value analysis: because a competent engineer could foresee that deploying an unfamiliar A...
ResolutionPattern_20 The Board resolved Q15 by holding that a person of practical wisdom, confronted with recognized writing limitations and the loss of a peer reviewer, w...
ResolutionPattern_21 The board concluded that Engineer A failed to exhibit prudence and professional humility because the decision to deploy an unfamiliar AI tool as a sub...
ResolutionPattern_22 The board concluded that Engineer A's decision to upload Client W's confidential data to an open-source AI platform without prior consent was a conseq...
ResolutionPattern_23 The board concluded through counterfactual analysis that had Engineer A followed a disclosure-and-consent pathway, the ethical obligation would have b...
ResolutionPattern_24 The board concluded through counterfactual analysis that a rigorous line-by-line review of the AI-generated design documents would very likely have id...
ResolutionPattern_25 The board concluded through counterfactual analysis that explicit citation of AI use in the report would have resolved Client W's authorship concern b...
ResolutionPattern_26 The Board concluded that Engineer A's rigorous fact-checking was professionally adequate for competence purposes but substantively failed to resolve w...
ResolutionPattern_27 The Board concluded against Engineer A on the design document question because the professional seal certifies not merely that output was reviewed but...
ResolutionPattern_28 The Board concluded that Engineer A's confidentiality breach was not merely a procedural lapse but a foreseeable consequence of an inadequately struct...
Phase 3 Decision Point Synthesis
Decision Point Synthesis (E1-E3 + Q&C Alignment + LLM)
E1-E3 algorithmic Q&C scoring LLM refinement Phase 1 entities + 2C Q&C + 2E rich analysis
E1
Obligation Coverage
-
E2
Action Mapping
-
E3
Composition
-
Q&C
Alignment
-
LLM
Refinement
-
Phase 4 Narrative Construction
Narrative Elements (Event Calculus + Scenario Seeds)
algorithmic base LLM enhancement Phase 1 entities + Phase 3 decision points
4.1
Characters
-
4.2
Timeline
-
4.3
Conflicts
-
4.4
Decisions
-
Review Entities & Commit View Synthesis

© Licensed under the GNU GPL v3 | Report Issue