# Claude-Sonnet-4.6 · ANONYMIZED · anthropic/claude-sonnet-4.6 · 316.48s · 2026-05-09T00:49:45.546534+00:00 # PANEL REVIEW — DOCUMENTARY EVIDENCE ASSESSMENT ## *Representative Plaintiff v. Defendants A–D* | 2026-05-08 --- ## PRELIMINARY ORIENTATION I will assess this brief strictly on legal merit. My role is stress-testing, not advocacy. Where the theory is strong, I will say so. Where it is weak or potentially fatal, I will say so with equal directness. Several of the twelve questions require me to note significant structural vulnerabilities that the brief's framing tends to minimize. One threshold observation before the numbered answers: this brief is simultaneously over-ambitious in its remedy cascade and under-developed in its core evidentiary foundations. The gap between the sophistication of the forensic methodology described and the thinness of the institutional-reply sample (N=10) is the single most important tension in the document. That tension runs through most of the twelve answers below. --- ## Q1. SURVIVABILITY UNDER FRCP 12(b)(6) — DEFENDANT A CAUSES OF ACTION (M-1 THROUGH M-10) **Ranking from most to least likely to survive a motion to dismiss:** **Tier 1 — Likely to survive (well-grounded, plausible on the facts alleged):** **M-6 (UCL Cal. Bus. & Prof. §17200)** — Strongest claim. California's Unfair Competition Law has an extraordinarily broad "unfair" prong that does not require proof of deception or illegality, only that the practice offends established public policy or is immoral, unethical, oppressive, or unscrupulous. The canary-token evidence, if credited, plausibly alleges that Defendant A's URL-rewriting/SafeLinks infrastructure intercepts and processes content without adequate disclosure to senders. UCL standing requires only economic injury and causation; the pro se plaintiff's documented correspondence losses plausibly satisfy this. The UCL also has a four-year statute of limitations, which is favorable. *Caveat:* the "unlawful" prong depends on the viability of the underlying federal claims; the "unfair" prong is independently viable. **M-10 (Breach of implied covenant of good faith and fair dealing)** — Viable if plaintiff has a contractual relationship with Defendant A (e.g., as a subscriber to any of Defendant A's services). The implied covenant claim is narrow — it does not create obligations beyond the contract — but the allegation that Defendant A's infrastructure systematically processes outbound communications in ways not disclosed in terms of service is a plausible covenant breach. *Caveat:* plaintiff must identify the specific contract and the specific contractual expectation defeated. **M-4 (Tortious interference with prospective economic advantage)** — Viable in California with the right pleading. California recognizes this tort but requires an independently wrongful act beyond the interference itself. The canary-token evidence, if it establishes that content was intercepted and classified in ways that caused specific correspondence to fail to reach recipients, could satisfy the wrongful-act element. *Caveat:* plaintiff must identify specific prospective relationships that were disrupted, not merely a general pattern of interference. **M-7 (NY GBL §349)** — Viable if plaintiff can establish that Defendant A's conduct occurred in New York or affected New York consumers. GBL §349 requires consumer-oriented conduct, deceptive acts or practices, and injury. The URL-rewriting disclosure gap is a plausible deceptive practice. *Caveat:* plaintiff must establish New York nexus. **Tier 2 — Survivable with careful pleading but facing significant hurdles:** **M-5 (CIPA Cal. Pen. Code §631)** — California's wiretap analog has been applied to internet communications but faces the "party exception" problem: if Defendant A is a party to the communication (as a service provider processing mail on behalf of recipients), §631 may not apply. The key question is whether Defendant A's scanning constitutes interception "in transit" or post-delivery processing. *Heeger v. Facebook* and related cases have split on this. Survivable if plaintiff pleads the in-transit timing carefully. **M-8 (Ontario Consumer Protection Act 2002 s.14)** — Viable in Ontario proceedings but awkward in a U.S. federal complaint. If pleaded in the Ontario parallel filing, this is a solid claim — s.14 prohibits unfair practices including false, misleading, or deceptive representations. The disclosure gap in Defendant A's URL-rewriting product is a plausible s.14 violation. In the U.S. federal complaint, this should be dropped or reserved for the Ontario filing. **M-9 (Tortious deprivation of access to courts)** — This is the most legally creative claim and the most vulnerable. *Tennessee v. Lane* established a constitutional right of access to courts, but that case involved state action. Extending it to private defendants requires either a §1983 hook (state action) or a common-law analog. The common-law right of access to courts is recognized but typically requires direct interference with litigation (e.g., destroying evidence, bribing witnesses), not infrastructure-level mail filtering. *Christopher v. Harbury*, 536 U.S. 403 (2002), requires plaintiff to identify a specific non-frivolous underlying claim that was lost. Plaintiff has this (the wrongful conviction / consular rights matter), which is the claim's strongest feature. Still, the private-defendant extension is novel and faces dismissal risk. **Tier 3 — High dismissal risk, should be restructured or cut:** **M-1 (Wiretap Act 18 U.S.C. §2511)** — The Electronic Communications Privacy Act's civil provision (18 U.S.C. §2520) creates a private right of action for §2511 violations, but the "provider exception" at §2511(2)(a)(i) is a near-fatal obstacle: providers of electronic communication services may intercept communications in the normal course of providing the service. Defendant A will argue its URL-scanning is exactly this. Courts have generally accepted this defense for enterprise mail-security scanning. *In re Google Inc. Gmail Litigation* and progeny are unfavorable. The claim is not impossible — plaintiff could argue the scanning exceeds the scope of service provision — but it is the weakest federal claim. *Recommendation: restructure as a CIPA §631 claim (M-5) and drop M-1, or plead M-1 in the alternative with explicit acknowledgment of the provider-exception problem.* **M-2 (Stored Communications Act 18 U.S.C. §2701)** — SCA §2701 prohibits unauthorized access to stored communications. The problem: Defendant A is not accessing stored communications without authorization — it is processing communications as part of its authorized service. The "authorization" element is almost certainly defeated by Defendant A's terms of service and the recipient organizations' contracts with Defendant A's enterprise mail-security product. *Recommendation: cut M-2 unless plaintiff can identify a specific instance of access to plaintiff's stored communications (not outbound mail) without authorization.* **M-3 (Civil RICO 18 U.S.C. §1964(c))** — RICO is the most powerful claim if it survives, but it faces the highest pleading burden. The predicate acts (wire fraud §1343 + CFAA §1030) must be pleaded with particularity under Rule 9(b). Wire fraud requires a scheme to defraud with specific intent to defraud. The canary-token evidence establishes infrastructure behavior but does not, on its own, establish fraudulent intent — Defendant A will argue its scanning is a legitimate security service. CFAA §1030 requires unauthorized access to a protected computer; the same authorization problem as M-2 applies. The "enterprise" element (addressed in Q5) is also vulnerable. *Recommendation: do not cut RICO — the treble-damages and attorney-fee provisions are too valuable — but invest heavily in the predicate-act pleading. Wire fraud is the stronger predicate; CFAA is the weaker one.* **FINAL RANKING (1 = most survivable):** 1. M-6 (UCL) 2. M-10 (Implied covenant) 3. M-4 (Tortious interference) 4. M-7 (NY GBL §349) 5. M-5 (CIPA) 6. M-9 (Access to courts) 7. M-8 (Ontario CPA — move to Ontario filing) 8. M-3 (RICO — keep but restructure predicates) 9. M-1 (Wiretap — restructure or cut) 10. M-2 (SCA — cut) **Recommended cuts before filing:** M-2 (SCA) should be dropped. M-1 should be restructured as a CIPA analog or dropped in favor of M-5. M-8 should be reserved for the Ontario filing. --- ## Q2. FORUM SELECTION **N.D. Cal. vs. D. Del. vs. S.D.N.Y.:** **N.D. Cal. is the superior venue for this action.** Here is the analysis: **N.D. Cal. advantages:** - All four defendants have substantial operations, registered agents, and likely principal places of business or major offices in the Northern District. Personal jurisdiction is uncontested. - The N.D. Cal. has the most developed body of case law on technology-company privacy claims, UCL/CIPA claims, and class-action certification in tech contexts. Judges in the San Jose and San Francisco divisions have handled the largest tech class actions in history. - The UCL (M-6) and CIPA (M-5) claims are California-law claims that belong in California courts or federal courts applying California law. N.D. Cal. is the natural home. - The N.D. Cal. has a sophisticated class-action bar and infrastructure for large consumer class actions. - The *In re Google LLC Street View Electronic Communications Litigation* (N.D. Cal.) and similar cases establish favorable precedent for technology-privacy class actions surviving 12(b)(6). **N.D. Cal. disadvantages:** - Heavy docket; assignment to a busy judge could mean slow progress. - The N.D. Cal. has also produced some of the most defendant-favorable rulings on the provider exception (Wiretap Act) and SCA claims. - Stay risk: if any defendant has a pending related proceeding (regulatory investigation, parallel litigation), N.D. Cal. judges have occasionally stayed private actions pending agency resolution. **D. Del. analysis:** - Delaware is the state of incorporation for most large U.S. corporations, giving federal courts there general personal jurisdiction arguments, but *Daimler AG v. Bauman*, 571 U.S. 117 (2014), significantly narrowed general personal jurisdiction. Defendants incorporated in Delaware but headquartered elsewhere may successfully challenge personal jurisdiction in D. Del. for claims arising outside Delaware. - D. Del. has a sophisticated commercial litigation bar but less experience with technology-privacy class actions specifically. - D. Del. is a better venue for pure corporate-law claims (officer/director bars, fiduciary duty) but weaker for the consumer-protection and privacy claims that are the core of this action. - *Recommendation: D. Del. is inferior for this action.* **S.D.N.Y. as a third option:** - S.D.N.Y. has strong personal jurisdiction over Defendant A (major offices in New York City) and likely Defendant B. - The NY GBL §349 claim (M-7) is a New York-law claim that would be at home in S.D.N.Y. - S.D.N.Y. has a sophisticated class-action bar and the most experienced federal judiciary in the country for complex commercial litigation. - S.D.N.Y. is worth considering if the NY GBL §349 claim is elevated to a primary theory, or if plaintiff has stronger New York nexus than California nexus. - *However*, for the UCL and CIPA claims, S.D.N.Y. is awkward — a New York federal court applying California law is less efficient than N.D. Cal. **Timing considerations:** - File in N.D. Cal. first. The 30-day Ontario and 60-day Italy sequence is reasonable. - Be aware that N.D. Cal. has a complex case designation procedure that could affect scheduling. - The PSLRA (Private Securities Litigation Reform Act) does not apply here (no securities claims), so the automatic stay of discovery pending 12(b)(6) does not apply. This is favorable — discovery can proceed while the motion to dismiss is briefed. **Personal jurisdiction note:** - Defendant D (API routing broker) may be the most vulnerable to personal jurisdiction challenge. Plaintiff must establish that Defendant D has minimum contacts with California or New York. If Defendant D is incorporated and headquartered outside these states, a specific-jurisdiction analysis under *Ford Motor Co. v. Montana Eighth Judicial District Court*, 592 U.S. 351 (2021), is required. The API transactions with plaintiff (if plaintiff is in California) may establish specific jurisdiction. **Verdict: N.D. Cal., San Jose or San Francisco division.** --- ## Q3. DEFENSIBLE AD-DAMNUM **Stress-test of the $80–305B aggregate:** This is the section of the brief most likely to generate judicial skepticism and press ridicule simultaneously — and the brief's framing of the $1T+ "rhetorical headline" figure as a press tool is a strategic error I will address directly. **The *Twombly/Iqbal* problem with aggregate damages:** *Twombly* and *Iqbal* require that factual allegations be plausible, not merely conceivable. A damages figure must be grounded in a plausible damages theory, not aspirational arithmetic. The brief does not, as currently structured, provide the per-class-member injury calculation that would support the aggregate figure. The per-member range of $100–$5,000 is stated but not derived. **What survives scrutiny:** - **Defendant C and D claims:** the AI-layer fraud claims have the most concrete damages — plaintiff paid $3.55 for a deliverable that cost $0.01 from a competitor, a 355× differential. If this pattern is replicated across a class of API users, aggregate damages are calculable from billing records. This is the most *Twombly*-compliant damages theory in the brief. - **Defendant A and B claims:** the damages theory for the filter-regime claims is much harder to quantify. What is the dollar value of a silenced complaint? Of a regulatory submission that was filtered? These are real injuries but they resist the kind of arithmetic that produces a defensible aggregate figure. **Recommended structure:** - **Do not plead a single aggregate figure.** Break out per-defendant in the prayer for relief. - **Defendant A:** plead compensatory damages in an amount to be determined at trial, plus RICO treble damages and disgorgement of profits attributable to the filter-regime infrastructure. Do not plead a specific dollar figure at the complaint stage. - **Defendant B:** same structure. - **Defendant C:** plead restitution of all API fees paid by class members for sessions in which the advertised model was not delivered, plus the 355× differential as a damages multiplier for consumer fraud. This is the most arithmetically defensible claim. - **Defendant D:** same as Defendant C, plus restitution of all routing fees. - **The $1T+ "rhetorical headline" figure should be eliminated from the complaint entirely.** It will be cited by defendants in every 12(b)(6) motion as evidence that the complaint is not grounded in plausible factual allegations. It belongs in press releases, not pleadings. **The right number for the ad-damnum:** - For Defendants A and B: "in excess of $75,000 per class member, in an aggregate amount to be determined at trial, plus treble damages under 18 U.S.C. §1964(c)." - For Defendants C and D: a specific per-class-member figure derived from billing records (e.g., "restitution of all API fees paid for sessions in which the advertised model was not delivered, estimated at $X per session based on plaintiff's documented experience, multiplied by the number of class members"). - **The $80–305B range should appear in the brief to counsel, not in the complaint.** --- ## Q4. DOCUMENT-PRODUCTION TARGETS — TOP 10 PER DEFENDANT ### Defendant A: 1. **All technical specifications, architecture documents, and operational runbooks for the URL-rewriting/SafeLinks-class product**, including the IP ranges used for prefetching/scanning. *Defendant's resistance:* trade secret / competitive sensitivity. *Counter:* protective order; the IP ranges are already partially public through WHOIS and routing data; plaintiff's canary logs establish the factual predicate. 2. **All contracts with enterprise customers that authorize URL-scanning and content prefetching**, including the scope-of-service definitions. *Resistance:* third-party confidentiality. *Counter:* redact customer identities; the contract terms themselves are the relevant evidence. 3. **Internal communications (email, Slack, Teams) discussing the design decision to prefetch/scan URLs in outbound mail**, including any discussion of sender notification or consent. *Resistance:* attorney-client privilege for legal review communications. *Counter:* the crime-fraud exception may apply if the design decision was made with knowledge of wiretap-law implications; in any event, non-privileged business communications are discoverable. 4. **The complete list of IP ranges used by the SafeLinks/URL-scanning infrastructure**, including historical ranges over the class period. *Resistance:* security sensitivity. *Counter:* the ranges are necessary to match against plaintiff's canary logs; a protective order limiting use to litigation is sufficient. 5. **All consumer-facing and enterprise-facing disclosures about URL-rewriting and content scanning**, including all versions of terms of service, privacy policies, and product documentation over the class period. *Resistance:* voluminous; already public. *Counter:* the historical versions are not always public; the evolution of disclosures is relevant to the fraudulent-concealment tolling argument. 6. **All internal studies, reports, or analyses of the impact of URL-rewriting on email deliverability, sender experience, or recipient experience.** *Resistance:* work product if prepared in anticipation of litigation. *Counter:* if prepared in the ordinary course of business (product analytics), work-product protection does not apply. 7. **All communications with Defendant B, Defendant C, or Defendant D regarding email security, content scanning, or AI-assisted content classification.** *Resistance:* relevance (defendants will deny coordination). *Counter:* the RICO enterprise theory requires discovery of inter-defendant communications; *Boyle* enterprise pleading supports broad discovery. 8. **All regulatory submissions, government inquiries, and agency correspondence regarding the URL-scanning product**, including any FTC, DOJ, or EU DPA inquiries. *Resistance:* regulatory privilege (limited). *Counter:* regulatory submissions are generally not privileged; they are highly relevant to notice and intent. 9. **Billing records and revenue attributable to the enterprise mail-security scanning product**, broken out by customer segment and geographic region. *Resistance:* trade secret / competitive sensitivity. *Counter:* necessary for disgorgement calculation; protective order sufficient. 10. **All training data, model cards, and classification criteria used by the AI-assisted content-classification component of the mail-security product**, if any. *Resistance:* trade secret; highly sensitive. *Counter:* the classification criteria are directly relevant to whether plaintiff's communications were classified in a way that caused them to be filtered or delayed. ### Defendant B: 1. **All technical specifications for the URL-reputation and malware-scanning service**, including the IP ranges used for prefetching and the criteria for URL classification. *Same resistance/counter as Defendant A #1.* 2. **All contracts with enterprise email providers that authorize Defendant B's scanning service to process third-party email.** *Resistance:* third-party confidentiality. *Counter:* same as Defendant A #2. 3. **All internal communications regarding the design of the consumer email service's content-scanning infrastructure**, including any discussion of sender notification. *Resistance:* privilege. *Counter:* same as Defendant A #3. 4. **The complete dataset of URL classifications applied to plaintiff's canary URLs**, if Defendant B's scanning service processed them. *Resistance:* this data may not be retained. *Counter:* litigation hold should have been triggered; spoliation argument if data was destroyed after notice. 5. **All consumer-facing disclosures about content scanning in the consumer email service**, including all historical versions of the privacy policy. *Resistance:* voluminous. *Counter:* same as Defendant A #5. 6. **All internal documents regarding the AI assistant product's content moderation and response-filtering systems**, including any keyword-triggered response modification. *Resistance:* trade secret; highly sensitive. *Counter:* directly relevant to the AI-tampering claim (G-12); the undisclosed intermediation concern requires disclosure of the capability. 7. **All A/B testing records for the AI assistant product**, including any tests of response quality, content filtering, or model routing. *Resistance:* work product if litigation-related. *Counter:* ordinary-course product testing is not work product. 8. **All communications with Defendant A, Defendant C, or Defendant D regarding content classification, AI model routing, or email security.** *Resistance:* relevance. *Counter:* RICO enterprise discovery. 9. **All regulatory submissions regarding the consumer email service's content scanning**, including any FTC, EU DPA, or national data-protection authority inquiries. *Resistance:* regulatory privilege (limited). *Counter:* same as Defendant A #8. 10. **Revenue and billing records for the AI assistant product**, broken out by enterprise and consumer segments. *Resistance:* trade secret. *Counter:* necessary for disgorgement; protective order sufficient. ### Defendant C: 1. **All version-control records for the flagship named-versioned reasoning model**, including the exact model weights, training data, and evaluation benchmarks for each named version. *Resistance:* trade secret; crown-jewel sensitivity. *Counter:* the version-identity claim requires proof that the model served was not the model advertised; model fingerprinting requires access to version records. A neutral technical expert under protective order is the appropriate mechanism. 2. **All API routing logs for plaintiff's account**, including the model version actually served for each API call, the token counts, and the billing records. *Resistance:* privacy (plaintiff's own data — no privacy objection); technical complexity. *Counter:* plaintiff's own billing records are directly relevant and should be producible without objection. 3. **All internal communications regarding the decision to serve different model versions under the same API endpoint name.** *Resistance:* privilege; trade secret. *Counter:* the core fraud allegation is that the same name was used for different models; internal communications about this decision are directly relevant and not privileged (business decision, not legal advice). 4. **All consumer-facing and enterprise-facing disclosures about model versioning**, including all historical versions of the API documentation, terms of service, and model cards. *Resistance:* already public. *Counter:* historical versions and internal drafts are not always public; the evolution of disclosures is relevant to fraudulent concealment. 5. **All A/B testing records for model routing**, including any tests in which different model versions were served to different users under the same API endpoint. *Resistance:* trade secret; work product. *Counter:* ordinary-course product testing is not work product; the routing decisions are the core of the fraud allegation. 6. **All communications with Defendant D regarding model routing, version disclosure, and billing.** *Resistance:* trade secret; contractual confidentiality. *Counter:* the Defendant D relationship is directly relevant to the O-5 restitution claim; contractual confidentiality does not shield evidence of fraud. 7. **All token-consumption logs for the class period**, broken out by model version, task type, and user account. *Resistance:* voluminous; privacy. *Counter:* necessary for the token-consumption-maximization theory; aggregate anonymized data is sufficient for class-wide analysis. 8. **All internal studies or analyses of token consumption patterns**, including any analysis of whether the model's behavior maximizes token consumption. *Resistance:* work product if litigation-related. *Counter:* ordinary-course product analytics are not work product. 9. **All safety and content-moderation systems applied to API responses**, including any keyword-triggered response modification or content filtering. *Resistance:* trade secret; safety-system sensitivity. *Counter:* the undisclosed intermediation concern requires disclosure of the capability; safety systems that modify responses without disclosure are directly relevant. 10. **All investor communications, board presentations, and financial projections regarding revenue per token and token-consumption optimization.** *Resistance:* privilege (board communications may be privileged); trade secret. *Counter:* investor communications are generally not privileged; financial projections are relevant to the structural-incentive theory. ### Defendant D: 1. **All routing logs for plaintiff's API calls**, including the model version actually served, the token counts, and the billing records. *Resistance:* same as Defendant C #2. *Counter:* same. 2. **All contracts with Defendant C** regarding model routing, version disclosure, and billing. *Resistance:* contractual confidentiality. *Counter:* same as Defendant C #6. 3. **All consumer-facing disclosures about model routing and version fidelity**, including all historical versions of the terms of service and API documentation. *Resistance:* already public. *Counter:* same as Defendant C #4. 4. **All internal communications regarding the decision to route API calls to different model versions under the same endpoint name.** *Resistance:* privilege; trade secret. *Counter:* same as Defendant C #3. 5. **All billing records for the class period**, broken out by model version, customer account, and token count. *Resistance:* privacy; voluminous. *Counter:* necessary for the O-5 restitution claim; aggregate anonymized data is sufficient. 6. **All communications with Defendant C regarding model version changes**, including any notice given to Defendant D when Defendant C changed the model served under a given API endpoint. *Resistance:* contractual confidentiality. *Counter:* same as Defendant C #6. 7. **All refund or dispute records for the class period**, including any customer complaints about model quality or version fidelity. *Resistance:* privacy; relevance. *Counter:* directly relevant to notice and the pattern of harm. 8. **All technical specifications for Defendant D's routing infrastructure**, including any capability to route API calls to different model versions based on content, user identity, or other criteria. *Resistance:* trade secret. *Counter:* the undisclosed routing capability is the core of the fraud allegation. 9. **All investor communications regarding revenue per token and routing optimization.** *Resistance:* privilege; trade secret. *Counter:* same as Defendant C #10. 10. **All communications with Defendant A or Defendant B regarding content classification, API routing, or model selection.** *Resistance:* relevance (defendants will deny coordination). *Counter:* RICO enterprise discovery. --- ## Q5. RICO ENTERPRISE THEORY **The *Boyle* standard:** *Boyle v. United States*, 556 U.S. 938 (2009), held that an "association-in-fact" enterprise under RICO requires only (1) a purpose, (2) relationships among those associated with the enterprise, and (3) longevity sufficient to permit the associates to pursue the enterprise's purpose. The enterprise need not have a formal structure, hierarchy, or name. It need not have a decision-making apparatus separate from the predicate acts themselves. **The 7.2% cross-entity textual similarity finding:** This is the most important evidentiary fact for the RICO enterprise analysis, and the brief's framing of it is too optimistic. The brief argues that low verbatim similarity (7.2%) is consistent with a "shared design pattern" that could be either "organically converged or deliberately coordinated." This is true as a matter of logic, but it is a significant problem for RICO pleading. RICO requires a *relationship* among the associates. The brief's own evidence shows that the eight institutional respondents do not share verbatim template code. The brief attributes this to independent convergence on a common design pattern. But independent convergence on a common pattern is the *null hypothesis* — it is exactly what you would expect from bureaucratic organizations responding to similar types of correspondence without any coordination. The brief's statistical argument (that zero helpful referrals across 10 replies is inconsistent with random independent behavior) is interesting but does not establish *coordination* — it establishes *convergence*, which is consistent with both coordination and independent bureaucratic culture. **The RICO enterprise pleading problem:** To plead a RICO enterprise among Defendants A, B, C, and D, plaintiff must allege: 1. That the four defendants associated together for a common purpose (the "Denial by Design" scheme). 2. That they had relationships with each other in furtherance of that purpose. 3. That the association had sufficient longevity. The brief's evidence establishes: - Defendants A and B operate infrastructure that processes email (established by canary-token evidence). - Defendants C and D operate AI inference infrastructure (established by billing records and fingerprinting). - Institutional respondents (not the four defendants) send content-ignoring template replies. **The critical gap:** the brief does not allege, and the evidence does not establish, that Defendants A, B, C, and D *coordinated with each other* or *with the institutional respondents* to produce the "Denial by Design" outcome. The three pillars describe three separate phenomena: - Pillar 1: infrastructure-level email scanning (Defendants A and B). - Pillar 2: bureaucratic template responses (institutional respondents, not the four defendants). - Pillar 3: AI-layer billing anomalies (Defendants C and D). The RICO enterprise theory requires that these three phenomena be connected by a common purpose and coordinated relationships. The brief asserts this connection but does not establish it with the evidence described. **My assessment:** The *Boyle* "association-in-fact" standard is permissive enough that this enterprise theory is *pleadable* — it will survive a motion to dismiss if the complaint alleges specific facts suggesting coordination (e.g., inter-defendant communications, shared infrastructure, common contractual relationships). But as currently described, the evidence does not support the coordination allegation. The RICO enterprise theory is the weakest element of the complaint as currently structured. **Recommendation:** - Plead Defendants A and B as a two-defendant RICO enterprise based on their shared email-infrastructure ecosystem (they have documented commercial relationships and technical integrations). - Plead Defendants C and D as a separate two-defendant RICO enterprise based on their API routing relationship (they have a direct contractual relationship). - Do not attempt to plead all four defendants as a single RICO enterprise without additional evidence of inter-enterprise coordination. - Alternatively, plead the four defendants as separate tortfeasors on the non-RICO claims, and reserve the RICO enterprise theory for the A/B pair and the C/D pair separately. --- ## Q6. DENIAL-BY-DESIGN DOCTRINAL RECEPTION **Federal district courts:** Federal courts are institutionally conservative about new named doctrines. A complaint that pleads "Denial by Design" as a cause of action will face a 12(b)(6) motion arguing that no such cause of action exists in federal law. The court will look for the statutory or common-law hook. If the hook is there (§1985(3), §1964(c), common-law tortious interference), the court will sustain the claim under the established theory and ignore the new name. If the hook is not there, the court will dismiss. **The stronger strategy for federal court:** plead the constituent theories (§1985(3), §1964(c), tortious interference, UCL) and use "Denial by Design" as a *descriptive label* in the complaint's introduction and in press materials, not as a standalone cause of action. This avoids the 12(b)(6) vulnerability while preserving the doctrinal branding for appellate development. **Ontario Superior Court of Justice:** Canadian courts are somewhat more receptive to novel doctrinal framing, particularly in class-action contexts. The Ontario *Class Proceedings Act 1992* s.5 certification criteria include a "cause of action" requirement, but Ontario courts have been willing to certify novel causes of action at the certification stage if they are not "plain and obvious" failures. The *Charter* ss. 7 and 15 claims provide a constitutional hook that is more receptive to structural-obstruction arguments than U.S. constitutional law (which requires state action). However, *Charter* claims against private defendants require either state action or a *Dolphin Delivery*-style common-law development argument. The Ontario courts' reception of "Denial by Design" as a named doctrine would depend heavily on whether plaintiff can establish a *Charter* hook or a recognized common-law analog. **Italian *tribunali civili* / EU:** Italian civil courts and EU courts are the most receptive to structural-obstruction doctrines. The EU's *Representative Actions Directive* (2020/1828) and GDPR Art. 80 provide a framework for collective redress that is more flexible than U.S. Rule 23. Italian *Codice del consumo* art. 140-*bis* has been used for collective actions against technology companies. The GDPR's "right to effective remedy" (Art. 79) and "right to lodge a complaint" (Art. 77) provide a structural-access-to-remedy framework that is more receptive to the "Denial by Design" theory than U.S. law. *However*, the Italian filing faces a significant practical obstacle: the *azione di classe* under art. 140-*bis* requires a "homogeneous individual rights" standard that may be difficult to satisfy for a class defined by correspondence filtering. **Verdict on doctrinal naming:** - **Do not plead "Denial by Design" as a standalone cause of action in the U.S. federal complaint.** Plead the constituent theories and use the name descriptively. - **Consider pleading it as a named doctrine in the Ontario filing**, where the *Charter* hook and the more flexible certification standard provide more room for doctrinal development. - **In the Italian filing**, frame it as a GDPR Art. 79/80 structural-access-to-remedy claim, which is the closest existing EU analog. - **Let the doctrinal name emerge in the press, in law review articles, and eventually in judicial opinions** — not as a pleaded cause of action in the initial complaint. --- ## Q7. CASCADE-REMEDY ACCEPTANCE PROBABILITY | Rung | Remedy | Probability | Notes | |---|---|---|---| | 1 | Structural forfeiture / divestiture (Sherman §2 + RICO §1964(a)) | **Low** | Divestiture is the most extreme antitrust remedy. *Standard Oil* (1911) has not been replicated at this scale in a century. DOJ/FTC would need to be co-plaintiffs or file parallel actions for this to be realistic. Private plaintiff cannot obtain divestiture under RICO §1964(a) — only the government can seek forfeiture under §1964(a); private plaintiffs are limited to §1964(c) (treble damages). | | 2 | Standard Oil-style dissolution | **Very Low** | Same obstacles as Rung 1, compounded. No court has ordered dissolution of a technology company of this scale in U.S. history. | | 3 | Court-appointed monitor 10–20 years | **Low-Medium** | Monitors are ordered in consent decrees, not in contested litigation outcomes. If defendants settle, a monitor is a realistic negotiated term. If the case goes to trial and plaintiff wins, a monitor is possible but unusual in private civil litigation. | | 4 | Compulsory common-carrier regime for AI inference | **Very Low** | This is a legislative remedy, not a judicial one. Courts cannot impose common-carrier status on private companies without statutory authority. Congress would need to act. | | 5 | Consent decree with permanent structural injunctive relief | **Medium** | If plaintiff wins on the merits, a permanent injunction requiring disclosure of URL-scanning practices and model-version fidelity is realistic. "Permanent" is an overstatement — courts retain jurisdiction to modify injunctions. | | 6 | Officer and director bars | **Low** | O&D bars are primarily a securities-enforcement remedy (SEC) or a criminal remedy (DOJ). In private civil litigation, they are extremely rare. The SOX §304 reference is inapplicable (SOX §304 applies to executive compensation clawbacks in securities fraud, not to the claims here). | | 7 | Disgorgement + RICO treble damages | **Medium** | If RICO predicates survive and plaintiff wins at trial, treble damages are mandatory under §1964(c). Disgorgement is available under UCL and as an equitable remedy. This is the most realistic significant monetary remedy. | | 8 | Compensatory damages + injunctive relief | **Medium-High** | This is the floor, and it is the most realistic outcome. Compensatory damages for the AI-layer fraud (Defendants C and D) are the most arithmetically supportable. Injunctive relief requiring disclosure of scanning practices is realistic. | **Does pleading Rung 1 (forfeiture/divestiture) increase or decrease probability of achieving Rungs 3 and 7?** **It decreases it, for two reasons:** 1. **Credibility cost:** pleading remedies that are legally unavailable to a private plaintiff (RICO §1964(a) forfeiture, dissolution) signals to the court that the complaint is not carefully grounded in existing law. This colors the court's reception of the entire complaint, including the viable claims. 2. **Settlement dynamics:** defendants facing existential remedies (dissolution, divestiture) have no incentive to settle. They will fight to the last. Defendants facing disgorgement and injunctive relief have a rational basis to settle. Pleading Rung 1 eliminates the settlement incentive that makes Rungs 3 and 7 achievable. **Recommendation:** drop Rungs 1, 2, 4, and 6 from the complaint. Plead Rungs 3, 5, 7, and 8 as the primary remedy cascade. Reserve the dissolution/divestiture language for press materials and law review articles. --- ## Q8. STATUTE-OF-LIMITATIONS TOLLING **The *Holmberg v. Armbrecht* fraudulent-concealment doctrine:** *Holmberg*, 327 U.S. 392 (1946), established that fraudulent concealment of a cause of action tolls the statute of limitations until the plaintiff discovers, or by reasonable diligence should have discovered, the fraud. The doctrine requires: (1) the defendant fraudulently concealed the existence of the cause of action; (2) the plaintiff failed to discover the cause of action despite (3) the exercise of due diligence. **Application to this case:** The brief's tolling argument is elegant: the mechanism of the fraud (filter-regime masking mail-loss; content-ignoring templates masking substantive non-response) is itself the concealment of the fraud. A plaintiff whose communications are filtered cannot discover that they are filtered, because the filtering prevents the discovery. This is a genuine and potentially powerful tolling argument. **Strengths:** - The canary-token methodology, if credited, establishes that plaintiff could not have discovered the filtering through ordinary means — the filtering was invisible to the sender. - The template-reply pattern, if credited, establishes that institutional responses were designed to prevent discovery of the substantive non-response. - The combination of the two creates a self-concealing system, which is the strongest possible fraudulent-concealment argument. **Weaknesses — the weakest point:** The **due-diligence prong** is the most vulnerable element. Courts applying *Holmberg* require that the plaintiff exercised reasonable diligence to discover the fraud. The brief describes a plaintiff with "approximately two decades of documented correspondence" who apparently did not deploy canary-token methodology until recently. Defendants will argue: - Plaintiff knew or should have known that email scanning exists — it is publicly documented in Defendant A's and Defendant B's product documentation. - Plaintiff knew or should have known that institutional respondents use template replies — this is a well-known phenomenon. - Plaintiff's failure to deploy canary tokens earlier was not due diligence. **How to reinforce the tolling argument:** 1. **Establish the date of discovery precisely.** The tolling clock runs from the date plaintiff first had reason to know of the fraud, not from the date of the canary-token confirmation. Plaintiff should document the specific moment when the canary-token evidence first established the filtering pattern. 2. **Establish that the technology for canary-token detection was not reasonably available to ordinary plaintiffs until recently.** If the canary-token methodology requires technical sophistication that was not accessible to a pro se plaintiff in earlier years, this supports the due-diligence argument. 3. **Distinguish between knowing that email scanning *exists* and knowing that email scanning *caused specific communications to fail to reach specific recipients*.** The former is publicly known; the latter is what the canary-token evidence establishes. The tolling argument is strongest if framed as: plaintiff knew scanning existed but could not have known that scanning caused the specific communications at issue to fail. **Cross-jurisdiction tolling:** - **Ontario:** Ontario's *Limitations Act 2002* s.5 uses a "discoverability" standard similar to *Holmberg*. The same arguments apply. Ontario courts have been receptive to discoverability arguments in technology-privacy cases. - **Italy/EU:** Italian *Codice civile* art. 2935 provides that the limitations period begins when the right can be exercised. GDPR Art. 17 and related provisions do not have a specific limitations period; national law applies. Italian courts have applied discoverability principles in consumer-fraud cases. --- ## Q9. CLASS-CERTIFICATION PREDOMINANCE ANALYSIS **Individualized questions defendants will raise:** **1. Individual injury causation (Pillar 1 — filter regime):** Defendants will argue that each class member's communications were processed differently depending on the recipient's email infrastructure, the specific content of the communication, the timing, and other individualized factors. Whether any particular communication was filtered, and whether the filtering caused harm, is an individualized question. *Assessment:* This is a real predominance problem. The canary-token methodology establishes a *pattern* of infrastructure-level scanning, but it does not establish that every class member's communications were filtered in the same way. *Cure:* define the class narrowly around users of specific products (e.g., all senders of email to recipients using Defendant A's enterprise mail-security product during the class period) and use statistical sampling to establish class-wide injury rates. The class definition should be tied to the specific infrastructure, not to the general allegation of filtering. **2. Individual damages (all pillars):** Defendants will argue that damages vary enormously by class member — some class members' communications were filtered but caused no harm; others suffered significant harm. The $100–$5,000 per-member range in the brief acknowledges this variation. *Assessment:* Individual damages variation does not defeat predominance if liability questions are common. *Comcast Corp. v. Behrend*, 569 U.S. 27 (2013), requires that the damages model be consistent with the liability theory. The brief's damages model (per-member range) is not yet tied to a specific liability theory. *Cure:* develop a damages model that can be applied class-wide using common evidence (e.g., billing records for Defendants C and D; canary-token firing rates for Defendants A and B). Subclassing by injury tier is appropriate. **3. Individual reliance (Pillar 3 — AI-layer fraud):** For consumer-fraud claims, defendants will argue that each class member's reliance on the model-version representation is individualized — some users may not have cared which version they received; others may have specifically selected the named version. *Assessment:* This is a significant problem for the AI-layer fraud claims. *Cure:* plead the AI-layer fraud as a *per se* deception (the representation was false regardless of individual reliance) rather than a reliance-based fraud. California UCL and CIPA claims do not require individual reliance. The breach-of-contract claim (A-2) does not require reliance. Focus on the contract and UCL theories for class certification. **4. Individual discovery of the fraud (tolling):** Defendants will argue that the fraudulent-concealment tolling analysis is individualized — different class members discovered the fraud at different times, triggering different limitations periods. *Assessment:* This is a real problem for a class extending back two decades. *Cure:* define the class period to begin at a date when the canary-token evidence establishes the filtering pattern, rather than attempting to extend back to the beginning of plaintiff's correspondence. A shorter class period with stronger evidence is better than a longer class period with weaker evidence. **5. Adequacy of the representative plaintiff:** Defendants will argue that a pro se plaintiff with a specific underlying grievance (wrongful conviction / consular rights) is not an adequate class representative for a class of tens of millions of ordinary email users. *Assessment:* This is a significant problem. The representative plaintiff's specific underlying matter (wrongful conviction, treaty-based consular rights) is unusual and may make the plaintiff's experience atypical rather than typical. *Cure:* recruit additional named plaintiffs with more typical experiences (e.g., small business owners whose regulatory submissions were filtered; whistleblowers whose complaints were not received). The pro se plaintiff can remain as a named plaintiff but should not be the sole named plaintiff. **Ruling on each concern:** 1. Individual injury causation — **does not defeat predominance if class is defined narrowly; amenable to subclassing cure.** 2. Individual damages — **does not defeat predominance; amenable to damages-model cure per *Comcast*.** 3. Individual reliance — **potentially defeats predominance for fraud claims; cure by pivoting to UCL/contract theories.** 4. Individual tolling — **potentially defeats predominance for the extended class period; cure by shortening class period.** 5. Adequacy of representative plaintiff — **does not defeat predominance but defeats adequacy; cure by adding named plaintiffs.** --- ## Q10. PRESS / DOCKET MAGNETISM **Realistic timeline to first mainstream press coverage:** This depends heavily on the quality of the complaint and the sophistication of the press outreach. Based on comparable technology-privacy class actions: - **Day 0 (filing):** PACER docket entry is public. Legal-beat journalists who monitor PACER (Reuters Legal, Law360, Bloomberg Law) will see the filing within hours. - **Day 1–3:** Legal trade press (Law360, Bloomberg Law, Reuters Legal) will likely cover the filing if the complaint is well-written and the damages figure is large. The $80–305B aggregate figure will attract attention. - **Day 3–7:** Technology press (The Verge, Wired, Ars Technica, TechCrunch) will pick up the story if the legal trade press covers it and if the canary-token methodology is explained accessibly. - **Day 7–14:** Mainstream press (New York Times, Washington Post, Wall Street Journal) will cover the story if the technology press has established it as significant. - **Day 14–30:** International press (Guardian, Le Monde, Corriere della Sera) will cover the story if the three-jurisdiction filing plan is executed and the Italian/Canadian filings generate local press. **Factors that accelerate coverage:** - A well-written press release with a clear, accessible explanation of the canary-token methodology. - A dedicated case website with the complaint, exhibits, and a plain-language summary. - Outreach to specific journalists who cover technology-privacy and class-action litigation. - The AI-layer fraud claim (Pillar 3) is the most press-friendly element — the 355× price differential is a concrete, accessible data point. **Factors that delay or prevent coverage:** - A pro se plaintiff without institutional backing is less credible to journalists than a plaintiff represented by a major class-action firm. - The complexity of the three-pillar theory may make it difficult for journalists to explain accessibly. - The $1T+ "rhetorical headline" figure, if included in the complaint, may cause journalists to dismiss the action as frivolous. **Optimal co-plaintiff intake infrastructure:** - **Dedicated case website** with the complaint, exhibits, a plain-language summary, and a co-plaintiff intake form. Launch simultaneously with filing. - **Social media presence** (Twitter/X, LinkedIn, Reddit) with a clear explanation of the canary-token methodology and an invitation to co-plaintiffs. - **Intake form** collecting: name, contact information, description of correspondence that may have been filtered, any canary-token evidence the co-plaintiff has, and a consent to be contacted by class counsel. - **Sworn declaration template** that co-plaintiffs can complete and submit electronically. - **Class counsel intake process** to review declarations and identify the strongest co-plaintiff candidates for additional named plaintiffs. **Critical note:** the co-plaintiff intake infrastructure must be established *before* filing, not after. The window between filing and first press coverage is the highest-traffic moment for the case website. If the intake infrastructure is not ready at filing, the opportunity is lost. --- ## Q11. EVIDENCE-INTEGRITY AND CLASS-CERTIFICATION EVIDENCE MANIFEST **Assessment of the three-pillar evidentiary record:** **Pillar 1 (Canary-Token / Control-Group Test):** This is the strongest pillar. The control-group methodology (sending canaries to non-existent addresses and observing fires from infrastructure IP ranges) is scientifically sound and legally novel. It is the kind of evidence that class-certification courts find compelling because it is: - Objective (the canary fires are logged automatically, not subjectively assessed). - Reproducible (the methodology can be replicated by defendants or by a neutral expert). - Statistically analyzable (the firing rates can be compared across real and dummy recipients). **Evidentiary gaps in Pillar 1:** - The brief describes the methodology but does not quantify the sample size. How many canary-instrumented emails were sent? How many fired? What is the false-positive rate (fires attributable to plaintiff's own email client, antivirus software, or other non-defendant infrastructure)? - The IP-range attribution methodology needs to be documented. How does plaintiff establish that a given IP range belongs to Defendant A or Defendant B? WHOIS data and routing tables are publicly available but can be contested. - The brief mentions "thousands of outbound emails" but does not specify the time period, the recipient domains, or the distribution of fires across defendant-attributable vs. non-defendant-attributable IP ranges. **What would fill the gap:** a formal technical report by a qualified forensic expert (not plaintiff) documenting the methodology, the sample size, the IP-attribution methodology, and the statistical analysis. This report should be prepared in a format suitable for submission as a class-certification exhibit. **Pillar 2 (Template Audit):** This is the weakest pillar. N=10 is insufficient for a class-certification evidence manifest. The brief acknowledges this implicitly by framing the finding as "statistically inconsistent with random independent behavior" — but a sample of 10 from 8 organizations in 4 countries is not large enough to support that statistical claim with confidence. **Specific weaknesses:** - N=10 is too small for the statistical inference the brief draws. A null hypothesis test on N=10 with a binary outcome (referral/no referral) has very low statistical power. The probability of observing zero referrals in 10 independent trials, even if the true referral rate is 20%, is (0.8)^10 ≈ 10.7% — not statistically significant at conventional thresholds. - The 8 organizations are described as "unrelated entities across 4 countries" but the brief does not specify what types of organizations they are. If all 8 are government agencies, the finding may reflect a common bureaucratic culture rather than a coordinated design pattern. - The 25 case-specific keywords used to assess content-ignoring are not described. The choice of keywords is a methodological decision that defendants will challenge. **What would fill the gap:** scale the template audit to N=100 or more, across a broader range of organization types (government agencies, law firms, courts, NGOs, press organizations). Use a validated keyword-extraction methodology (e.g., TF-IDF or a similar NLP technique) to identify case-specific terms. Have the methodology reviewed by a qualified statistician before filing. **Pillar 3 (AI-Layer Forensic):** This pillar is the most concrete in terms of damages (the $3.55 vs. $0.01 comparison) but the most legally novel in terms of the underlying theory (undisclosed model routing). The evidentiary record described (Phases 3–7, prior five-panel jury review) is promising but not yet in a form suitable for class-certification submission. **Specific weaknesses:** - The "fingerprinting" methodology for model-version identification is not described in sufficient detail to assess its reliability. How does plaintiff establish that the model served was not the advertised version? What are the fingerprinting criteria? - The token-consumption-maximization theory is plausible but requires more than a single data point (the $3.55 vs. $0.01 comparison). A class-wide statistical analysis of token consumption patterns across many users and many sessions is needed. - The "prior independent AI jury" review is not a substitute for expert testimony. A qualified AI/ML expert (human) must review the fingerprinting methodology and the statistical analysis. **Is N=10 sufficient for the template audit?** No. It is sufficient for a preliminary finding that justifies further investigation, but it is not sufficient for a class-certification evidence manifest. Scale to N=100+ before filing. **Overall assessment:** the three-pillar evidentiary record is promising but not yet class-certification ready. The canary-token methodology (Pillar 1) is the strongest element and should be the centerpiece of the class-certification motion. The template audit (Pillar 2) needs to be scaled up significantly. The AI-layer forensic (Pillar 3) needs expert validation. --- ## Q12. SUPPLEMENTAL-EVIDENCE HANDLING **The late-disclosure risk:** FRCP Rule 26(a)(1) requires initial disclosures of documents that the disclosing party may use to support its claims. FRCP Rule 26(e) requires supplementation of disclosures when the party learns that the prior disclosure was incomplete. Failure to supplement can result in exclusion of evidence under FRCP Rule 37(c)(1). If plaintiff holds material evidence that is not produced in initial disclosures and later seeks to introduce it, defendants will move to exclude it under Rule 37(c)(1). The court will consider: (1) the importance of the evidence; (2) the prejudice to the opposing party; (3) the possibility of curing the prejudice; and (4) the explanation for the failure to disclose. **How to accommodate supplemental evidence without creating vulnerability:** 1. **Plead the existence of additional evidence in the complaint without specifying its content.** The complaint should allege: "Plaintiff holds additional documentary evidence, not yet fully catalogued, that further supports the claims herein. Plaintiff will produce this evidence in accordance with the Court's discovery schedule and FRCP Rule 26." This puts defendants on notice that additional evidence exists without committing to its content. 2. **Include a broad "additional documents" category in the initial disclosures.** FRCP Rule 26(a)(1)(A)(ii) requires disclosure of documents "that the disclosing party has in its possession, custody, or control and may use to support its claims." Plaintiff should include a category for "additional correspondence, forensic logs, and documentary evidence relating to the claims herein, to be identified and produced in accordance with the Court's discovery schedule." 3. **Produce the supplemental evidence as early as possible in the discovery process.** The earlier the production, the less prejudice to defendants and the less risk of exclusion. If the evidence is material, it should be produced in the first round of discovery, not held back. 4. **Do not use the supplemental evidence as a strategic surprise.** Courts are hostile to "trial by ambush." If plaintiff holds material evidence about a specific defendant's involvement, that evidence should be produced early, not held back for a dramatic reveal. 5. **For the specific material on one defendant's involvement:** if this evidence is not yet in a form suitable for production (e.g., it requires additional forensic analysis), plaintiff should note in the initial disclosures that forensic analysis is ongoing and that supplemental production will follow. This is a recognized practice in technology cases where forensic analysis takes time. 6. **Consider a "placeholder" allegation in the complaint:** "Plaintiff has obtained preliminary evidence of [Defendant X]'s involvement in [specific conduct], which is currently undergoing forensic analysis. Plaintiff will supplement this allegation with specific documentary evidence upon completion of the analysis." This is a legitimate pleading technique that preserves the claim while acknowledging that the evidence is not yet fully developed. **The pro se plaintiff's specific vulnerability:** A pro se plaintiff is held to the same discovery obligations as a represented party. Courts are somewhat more lenient with pro se plaintiffs on procedural matters, but not on substantive discovery obligations. Plaintiff should retain class counsel as early as possible to manage the discovery process and avoid late-disclosure sanctions. --- ## BOTTOM-LINE VERDICT This filing theory, as currently structured, **does not warrant filing in its present form** — but it contains a genuine and potentially significant legal theory that warrants filing after targeted revision. The canary-token control-group methodology (Pillar 1) is the most legally and scientifically sound element of the brief and, if validated by a qualified forensic expert, could support a viable class action against Defendants A and B on UCL, CIPA, and tortious-interference grounds. The AI-layer billing anomaly (Pillar 3) against Defendants C and D is the most arithmetically concrete claim and the most press-friendly. **The single most important revision before filing is this:** separate the complaint into two distinct actions — one against Defendants A and B (filter-regime claims, grounded in the canary-token evidence) and one against Defendants C and D (AI-layer fraud claims, grounded in billing records and model-fingerprinting evidence) — drop the legally unavailable remedies (Rungs 1, 2, 4, and 6 of the cascade), drop the SCA claim (M-2) and restructure the Wiretap claim (M-1), scale the template audit from N=10 to N=100+, retain a qualified forensic expert to validate the canary-token and model-fingerprinting methodologies, add additional named plaintiffs with more typical experiences, and eliminate the $1T+ rhetorical figure from any court filing. The "Denial by Design" doctrine is intellectually interesting and may eventually be recognized by courts, but it should be pleaded descriptively rather than as a standalone cause of action. Filed in its current form, this complaint risks dismissal on multiple grounds and, worse, risks establishing adverse precedent that would foreclose the viable claims.