Never before has so much airtime been devoted to balloons.  And, as it turns out, there have been lawsuits about balloons.  Lots – of all shapes and sizes. Are you surprised? 

But, sadly, balloon litigation is an overlooked aspect of our judicial system.  I set out to change that with this recent piece in the New York Daily News. 

I hope you can check it out.

https://www.coverageopinions.info/Balloons.pdf

 

At the end of February, I did an article, for a Coverage Opinions email blast, that shared the results of my ChatGPT insurance coverage test.  I had asked the much talked-about artificial intelligence platform – that offers answers to questions in human-like conversation – what it knew about insurance coverage.
 
Very simple. I asked five very specific questions with answers that have been clearly stated by a state supreme court.  The verdict – ChatGPT got 4 out of 5 wrong. But not just wrong – dead wrong. 

I received loads of reader mail about the article.  It was clear that the role of artificial intelligence in insurance coverage is on people’s minds.  I decided to do a follow-up.  It summarizes the first article – for those who didn’t read it – and then addresses the issue from a legal perspective and bad faith considerations. 
 
ChatGPT: Potential Impact Of Using Artificial Intelligence In Claims Handling

Under Illinois law, does the pollution exclusion preclude coverage for carbon monoxide poisoning?

I posed that question to ChatGPT not long ago. The artificial intelligence platform paused a moment, seemingly thinking, and then replied: “Yes, the pollution exclusion in Illinois law typically precludes coverage for carbon monoxide poisoning.”

In Am. States Ins. Co. v. Koloms, 687 N.E.2d 72 (Ill. 1997), the Illinois Supreme Court said just the opposite.

With all the ballyhoo of late, about the supposedly life-altering impacts of ChatGPT, I was surprised that its answer was so wide of the mark -- especially to such a straightforward yes-no question.  But, to be fair, everyone has off-days.  I gave it another chance.

Under Pennsylvania law, I asked, is extrinsic evidence permitted to determine an insurer’s duty to defend?

ChatGPT responded “Yes, extrinsic evidence is permitted to determine an insurer’s duty to defend in Pennsylvania.” It went on to further explain that “[i]n order to determine whether an insurer has a duty to defend, courts in Pennsylvania will review the language of the insurance policy and the facts of the underlying case, including any extrinsic evidence that is offered.”

That sounds very authoritative. And, if you didn’t know better, you’d probably be impressed that artificial intelligence could do that. But, those who do know better, are aware that the answer is flat out wrong. The Pennsylvania Supreme Court, in Kvaerner Metals Div. of Kvaerner U.S., Inc. v. Commercial Union Ins. Co., 908 A.2d 888 (Pa. 2006) -- and too many other cases to count -- have said that, under Pennsylvania law, extrinsic evidence is not permitted to determine an insurer’s duty to defend.

I soldiered on. You know what they say about the third time.

Under Washington law, can an insurer seek reimbursement of defense costs following a determination that it had no duty to defend? 

Said ChatGPT: “Yes, an insurer may seek reimbursement of defense costs under Washington law. According to Washington state law, an insurer may be entitled to reimbursement of defense costs if it can prove that it had no duty to defend the insured, and that the insured’s claims are not covered by the policy.”

A decade ago, the Washington high court, in National Surety Corp. v. Immunex Corp., 297 P.3d 688 (Wash. 2013), was clear in its pronouncement that insurers in the Evergreen State have no such right.

Two more insurance coverage questions. The AI application at last got one right.  Final grade: one out of five correct.  My cousin Vinny could have done better.  

What made the results of my insurance coverage pop quiz particularly surprising was the nature of the questions. I asked yes-no questions, ones that have definitive answers, dictated by long-standing state high court precedent. I did not ask trick questions. Nor pose situations where the law is not clear or the answer depends on the particular policy language. I lobbed what should have been softballs for an artificial intelligence platform being showered with such praise.

Despite my experiment demonstrating that ChatGPT seemingly has no aptitude for insurance coverage, I put it to another test. This time, I asked a different type of question. Instead of narrowly-focused questions – what is the law on this particular issue, in this specific state? – I asked the program to discuss a coverage issue in general terms. 

Here, examining coverage concepts in broad strokes, ChatGPT performed significantly better.  It was quite adept at knowing if an insured being defended under a reservation of rights is entitled to independent counsel, how to determine number of occurrences under a liability insurance policy and how to know if an insurer has a duty to defend.  In each case, its response was several paragraphs and, for the most part, correct. It even picked up on some nuances of the issue.

Interestingly, the responses also ended with the following caution or something along these lines: “It’s important to consult with an experienced insurance attorney to evaluate the facts of the specific case and determine the appropriate [issue being addressed].”       

Of course, even if the artificial intelligence platform can talk the talk on coverage principles, that is no help to a coverage professional in need of an answer to a specific question. Imagine a policyholder that demands coverage for pre-tender defense costs in Indiana. The insurer’s response cannot be a three-paragraph tutorial on whether they are generally covered, or not, on a national basis.   

ChatGPT: The Consequences for Claims Handling

Media stories abound of businesses putting ChatGPT to their own tests. Like me, they were curious to know how artificial intelligence could affect their way of doing things.  However, for insurance coverage, that question is more significant than for many others.

Suppose you make widgets. You turn to ChatGPT to see if there is a way to improve upon your various manufacturing processes. ChatGPT offers some suggestions and you give them a try. Since widgets are your business – you are a widget expert -- you’ll know immediately if ChatGPT has offered a better way to make one. It is unlikely that the artificial intelligence platform will cause you to send inferior widgets out the door.

But the same cannot be said of insurance coverage. Here, what ChatGPT offers – answers to questions – goes to the heart of the insurer’s product: payment of appropriately covered claims.
Take an adjuster confronted with a claim involving New York law who needs to know if emotional injury qualifies as “bodily injury” for purposes of triggering a defense under a commercial general liability policy.

He or she turns to ChatGPT and is told as follows (as I was): “Under New York law, emotional injury is generally not considered bodily injury for purposes of a commercial general liability policy. Bodily injury, as defined by most commercial general liability policies, typically refers to physical injury, sickness, or disease that is caused by an accident or event. Emotional injury, on the other hand, generally refers to mental or emotional distress that is caused by non-physical events, such as emotional or psychological trauma.”

Armed with this answer, the adjuster denies a defense to the insured.

However, under New York law, emotional injury is, in fact, considered “bodily injury” for purposes of a standard commercial general liability policy. It may be a minority rule nationally, but, here, only New York matters. And the state’s Court of Appeals, in Lavanant v. Gen. Accident Ins. Co. of Am., 595 N.E.2d 819 (N.Y. 1992), ruled that it is.
 

Unlike the widget manufacturer, where ChatGPT is unlikely to cause it to sell inferior products to customers, here the artificial intelligence platform caused the insurer to do just that. And, of course, a variety of harmful consequences for an insured – and the insurer -- can flow from the improper denial of a defense.

Insurers sometimes improperly deny a defense. And erroneous denials happen even when the insurer has used experienced counsel and done extensive research on the question – and using law books (or what used to be books). So what happened here through the use of ChatGPT is not unusual.

But what about the consequences?

Courts almost always conclude that an insurer, despite getting the answer to a coverage question wrong, has not committed bad faith.  The various state standards to prove bad faith are generally high – the conduct had an intentional aspect; the issue was not fairly debatable; the denial was unreasonable (and others, along these lines). Reaching an incorrect coverage determination is unlikely to satisfy this heavy burden. See Yamagata Enters. v. Gulf Ins. Co., 2008 U.S. Dist. LEXIS 138942 (D. Nev. Feb. 4, 2008) (citing American Excess Ins. Co. v. MGM Grand Hotels, 729 P.2d 1352 (Nev. 1986)) (“The mere fact that an insurer was incorrect in its coverage determination does not render it liable for bad faith if its position was reasonable.”)

However, while getting a coverage determination incorrect is unlikely to lead to bad faith, the same cannot always be said about the manner in which an insurer reached the incorrect determination. Bad faith can occur “when an insurance company makes an inadequate investigation or fails to perform adequate legal research concerning a coverage issue.” Sypherd Enters. v. Auto-Owners Ins. Co., 420 F. Supp. 3d 372 (W.D. Pa. 2019) (citations and internal quotes omitted).

This was on display last year in Sec. Nat’l Ins. Co. v. Constr. Assocs. of Spokane, 2022 U.S. Dist. LEXIS 53533 (E.D. Wash. Mar. 24, 2022), where a Washington federal court held that an insurer was liable for bad faith for reaching an incorrect coverage determination. The adjuster was not aware of a Washington Supreme Court decision that would have dictated a different result.
.
In explaining the role of legal research in making a coverage determination, the court explained:

“True adjustors are not attorneys in Washington and are presumably not trained in the same kinds of legal research techniques as lawyers. But that does not excuse an adjustor from having a at least a baseline understanding of the relevant state’s law necessary to carry out their duties. Instead, it means insurance companies must undertake what in practice are reasonably small steps to ensure adjustors are equipped to make reasonable coverage and defense determinations. Such steps could include teaching adjustors to run case searches or, more likely, supplying adjustors with subscriptions to relevant legal newsletters, a resource most attorneys rely on to keep apprised of legal developments. Regardless, ignorance of the applicable case law, even of a relatively new case law, does not excuse the conduct of adjustors who deny defense or indemnification. Doing otherwise would allow insurance carriers to intentionally stay ignorant and hide behind their ignorance when their claim denials are challenged. Adjustors must equip themselves or else seek out those with the requisite tools and knowledge.” Id. at *34.

An insurer that uses an artificial intelligence program to answer a legal coverage question, and then uses that answer to improperly deny coverage – especially with known flaws in the application’s accuracy – is unlikely to get the benefit of having acted reasonably for purposes of defeating a bad faith finding. To the contrary, such practice is likely to be tantamount to having done no research, as was the case in Constr. Assocs. of Spokane.

Herein lies the risk for insurers using ChatGPT to assist with answering coverage questions as part of claims handling.

No doubt artificial intelligence, like most technologies, will improve as time goes on. But for now, and probably a long time, despite the praise being heaped on AI, insurers would be well-served to resist the temptation to use a coverage lawyer in a chat box.

Some of the most important and complex legal disputes in America are handled by the United States District Court for the Southern District of New York.  So it’s a good thing that the vexing question -- when are renovations to a bathroom in an office building complete? -- landed in Lower Manhattan. 

In March 2015, Hajdine Shuku was performing janitorial services in a 12th floor bathroom of law firm Mayer Brown’s New York City office.  Ms. Shuku alleges that, while cleaning the bathroom, a stall door fell off and hit her.  She filed suit against Mayer Brown, as tenant, and 1221 Avenue Holdings, LLC, its landlord.  Construction work had previously been performed in the bathroom. You know where this is going.  It didn’t take long before various construction companies/contractors were parties to the suit.  And then it didn’t take long before a dispute over additional insured coverage arose.

I’ll try to keep it simple.  These kinds of cases have a way of getting bogged down with many parties’ names, who’s suing whom, who insured this party and that party, who’s seeking additional insured coverage from whom, etc.

There were two liability insurers involved.  Travelers insured J.T. Magen, the construction company that Mayer Brown contracted with to do work in its office.  Netherlands Insurance Company issued a policy to Division Ten, which signed a purchase order to perform work for Magen in connection with the bathrooms.  The Netherlands policy contained some additional insured endorsements.  Again, keeping it simple, Travelers sought additional insured coverage from Netherlands for Travelers’ insureds – Magen, Mayer Brown and 1221 Avenue Holdings.  Netherlands denied Travelers’s tender.  

Two of the Netherlands additional insured endorsements – one being Scheduled Person and the other affording additional insured coverage to an entity that the insured is contractually obligated to name as an additional insured – contained the following exclusion:

This insurance does not apply to "bodily injury" or "property damage" occurring after:

2. That portion of “your work” out of which the injury or damage arises has been put to its intended use by any person or organization other than another contractor or subcontractor engaged in performing operations for a principal as a part of the same project.

Netherlands argued that this exclusion applied.  Travelers disagreed.  The court in Travelers Prop. Cas. Co. of Am. v. Neth. Ins. Co., No. 21-6061 (S,D.N.Y. Mar. 1, 2023), after examining when the construction work in the office bathroom was complete, sided with Netherlands.  To reach its conclusion, the court made the following observations about how bathrooms work:

“From the fact of Shuku’s presence late at night cleaning the Mayer Brown bathrooms arises the inference—the only reasonable one—that Shuku was cleaning bathrooms that needed upkeep, that is, ones in use by individuals during the day.  Travelers, despite the opportunity, has not adduced any evidence on which to infer that she was performing janitorial service in the bathrooms in the midst of the construction process.”

Second, and interestingly, just days before the incident in question, the Mayer Brown bathroom had been the source of some excitement.  Two people got stuck in bathroom stalls -- as well as a member of the maintenance crew.  Luckily, he has a screwdriver with him and was able to get out without assistance.    

From this situation, the court concluded that this could only mean one thing: “[T]hat ordinary bathroom users (law firm’s employees or visitors) had become stuck in the bathroom stalls while trying to use them for their intended purpose. That one of the issues raised involved the bathroom locks getting stuck makes all the more reasonable the inference that the persons inside were using the toilets to relieve themselves, as opposed to being present to do ongoing construction work.”

The court rejected Travelers’s argument that, while most of the work on the bathrooms has been completed at the time of the injury, it was not all completed.  Essentially, as the court saw it, whatever work was left to be done were “punch list” items, a situation not inconsistent with the regular use of a premises having been resumed.    
   

To my surprise, I used no bathroom puns here!  Not that I didn’t think off some. I stopped counting at ten.

I do not do a lot with additional insured decisions in Coverage Opinions.  They are usually fact and policy language specific, which limits their ability to offer guidance or be relevant to future cases.  But I selected Travelers Indem. Co. v. Southwest Marine and General Ins. Co., No. 21-1828 (E.D.N.Y. Feb. 10, 2023) to address here.  A New York federal Magistrate Judge
authored a Report and Recommendation that addressed a different kind of AI issue – and one that I’ve never seen.  If you work with AI endorsements, I think you’ll find this interesting.

Like so many additional insured issues, it started with a construction site injury.  And, as if often the case, there are lots of parties involved – owner, construction manager, construction company, subcontractor.  That makes it complex and difficult to keep everyone straight.  But I’ll simplify it.

The claim involved additional insured coverage for parties for a claim by a worker who was injured when a bucket of spackle fell off a scaffold and injured him.

[Incidentally, I am really un-handy around the house.  There is pretty much nothing I can do to fix things.  More like make it worse is my specialty.  But -- and now, I don’t want to brag here -- I am very good at spackling.  A real pro.  You would marvel at my work.  Of course, how did I get so good?  From my skill at hanging pictures.]

Back to the wayward bucket of spackle. To not bog this down with all kinds of names and who did what on the project, here are the only facts needed. A construction company did the spackling work (incidentally, I’ve never dropped a bucket of spackle).  The construction company is the named insured.  There are other parties – owner, general contractor and construction manager -- seeking to be additional insureds on the named insured’s liability policy.  Even though they are seeking to be additional insureds, I’ll still simply refer to them as the additional insureds.

Southwest Marine issued a general liability policy to the named insured-spackler.  Travelers, which generally owed obligations to the additional insureds, said that the Southwest policy should be primary and non-contributory to any coverage that Travelers owed to the additional insureds.  This is certainly not an unusual argument in this situation.

Here’s where it gets interesting.      

The Southwest Policy contained an additional insured endorsement -- CG 20 10 04 13, Owners, Lessees or Contractors – Scheduled Person or Organization.  Under “Name Of Additional Insured Person(s) Or Organization(s)” appeared the word “BLANKET.”  The “Location(s) of Covered Operations” portion of the Schedule of the AI Endorsement was blank.

A purchase order, for the named insured-construction company’s spackling work, obligated the company to have a $1 million general liability policy and name the owner as an additional insured.  “Owner” was not defined in the P.O. and the space on the P.O. for “owner” was blank.

So, as Southwest saw it, it had no obligation to provide coverage to the additional insureds, since the purchase order did not require them to be named as additional insureds.  That was a requirement of the additional insured endorsement as it was a “Scheduled Person or Organization” form.  

Travelers’s take on the operation of the AI endorsement was different: “Travelers asserts that there are no scheduled limitations to this blanket coverage and that there is no requirement that coverage be required by an underlying written agreement.  Because the Claimant in the Underlying Action has alleged that his injury was caused by [named insured] in its performance of work for [additional insureds], Travelers urges the Court to find that Southwest has the duty to defend [additional insureds].”

The dispute came down to this: what does the word “Blanket,” appearing on the AI endorsement under “Name Of Additional Insured Person(s) Or Organization(s),” mean? 

Southwest argued that “Blanket” “‘can only plausibly mean’ that coverage is only owed to an entity which the insured agrees to provide coverage to by contract.  Southwest avers that the term ‘blanket’ is an industry term which means coverage is to be provided to any person or organization for which the named insured is obligated (such as by contract) to name as an additional insured.  The other option would be to provide for additional insureds by ‘schedule,’ which requires a listing of the additional insureds by name.  Thus, Southwest contends that the only plausible reading of the word ‘blanket’ requires the Court to consult the Purchase Order to determine [named insured’s] obligation, if any, with respect to additional insureds.”

As I said, it’s an interesting issue.  I use the term “banket additional insured endorsement” all the time.  And when I do, I’m describing an AI endorsement that offers AI coverage to a party that the named insured is contractually obligated to name as an additional insured.  I bet most of you also have that meaning in mind when using the term “banket additional insured endorsement.”    

But the court sided with Travelers.  While I am not going to get into every reason discussed by the court, here are the principal ones.

First, the court rejected my thinking – that everyone knows that the term “banket additional insured endorsement” means that AI status is provided to persons or organizations that the named insured is contractually obligated to name as additional insureds. 

While Couch agrees with me, the court poo-pooped that: “Southwest cites to ‘Couch on Insurance"’ (3 Couch on Ins. § 40:30) for the general proposition that a blanket additional insured endorsement ‘generally’ provides coverage to the person or entity who the insured is obligated to name as an additional insured by virtue of a contract. (DE 21-1 at 8-9.) While the Court recognizes the Couch as a leading treatise on insurance law, relying on an excerpt can hardly be deemed sufficient to satisfy one's burden on summary judgment.”

Then IRMI suffered the same fate: “The same,” the court noted, “can be said about Southwest’s citation to the Glossary of Insurance and Risk Management Terms at International Risk Management Institute for its definition of a ‘Blanket Additional Insured Endorsement. (citing ‘Glossary of Insurance and Risk Management Terms at International Risk Management Institute (IRMI).’”
 
Here's where Southwest hit a serious roadblock.  It’s AI endorsement stated: “If coverage provided to the additional insured is required by a contract or agreement, the insurance afforded to such additional insured will not be broader than that which you are required by the contract or agreement to provide for such additional insured.” (italics added).

I’ll set out the court’s take on that verbatim:

“If the Court were to accept Southwest’s reading of ‘blanket’ coverage—that coverage is owed to additional assureds only pursuant to an underlying contract—then the [italicized] phrase in the Southwest AI Endorsement above is rendered superfluous. Put differently, if coverage is only provided based on an underlying contract, then there would be no need to say ‘[i]f coverage. . . is required by a contract.’ Instead, the paragraph above would just read, ‘insurance afforded to such additional insured will not be broader than that which you are required by the contract or agreement to provide for such additional insured.’ The Court finds that by stating ‘[i]f coverage. . . is required by contract or agreement,’ the Southwest AI Endorsement necessarily contemplates a scenario where coverage is not required by contract or agreement. Reading the Southwest AI Endorsement as a whole, it is plain that the above paragraph is meant to limit the scope of coverage provided to additional insureds and does not establish that an underlying contract is a precondition to receiving coverage. The Court finds that under the plain and ordinary meaning of the Southwest AI Endorsement, a party can qualify as an additional insured even where not required by an underlying contract or agreement. Therefore, it is respectfully recommended that the Court find a genuine issue of fact does not exist on this ground.”

Travelers prevailed.  Its insureds were entitled to AI coverage, under the Southwest policy, and on a primary and noncontributory basis.  Southwest was obligated to reimburse Travelers for the defense costs incurred for the additional insureds. 

As is usually the case when it coverage -- the policy language controlled the outcome.

I have never addressed a case in Coverage Opinions involving fraudulent joinder.  It is hard to imagine anything that could be more dull.  Plus, while the issue certainly arises in coverage litigation, it is not a coverage issue per se.  You know where this is going.  The fraudulent joinder drought is over.  A big welcome to CO to Glidedowan, LLC v. Hiscox, Inc., No. 22-6540 (W.D.N.Y. Mar. 8, 2023).

At issue in Glidedowan is whether a declaratory judgment action could remain in federal court on the basis of diversity of citizenship -- as the supposedly non-diverse party was fraudulently joined in an effort to defeat diversity.  It is a fraudulent joinder case, period.  It is not a case with several issues, and one just happens to be fraudulent joinder.  I’m glad about this.  The first fraudulent joinder case in CO should be one where the issue does not need to share the spotlight.

In general, the case is eye-glazing and with a complex procedural history – which demonstrates why it has taken ten years for a fraudulent joinder case to make it into CO.  Here’s the part that matters.

Glidedowan LLC was sued for wrongful death in connection with its home health care business.  Lloyd’s issued the company a professional liability policy and Hiscox was the administrator.  Hiscox sent a reservation of rights letter stating: “Hiscox will agree to provide [Plaintiff] a defense under the policy, subject to the below reservation of rights.”  A dispute arose over choice of counsel.  Glidedowan rejected Hiscox’s chosen counsel and retained its own.

Coverage litigation ensued.  Glidedowan filed suit in New York state court against a Lloyd’s syndicate, Hiscox and certain insurance parties associated with its business automobile policy.  Putting aside various details, the case was removed to federal court.  At issue was whether it could remain there.  Specifically, for purposes of the relevant time period, Hiscox was a citizen of New York.  And since the plaintiff was also a New York citizen, it was argued that there was no diversity of citizenship.  Hence, there was no federal court jurisdiction. 

But there would be diversity of citizenship if Hiscox had been fraudulently joined.  Specifically, if, from the pleadings, there in no possibility that the claims against the non-diverse defendant could be asserted in state court, then the court will disregard the presence of such non-diverse defendant. 

In making the determination, the court turned to the issues in the coverage case.  One of them was the possible violation of New York Insurance Law Section 3420(d)(2) – namely, Hiscox did not disclaim coverage or reserve its rights within the time prescribed by the statute and, therefore, is liable for defense costs and may not disclaim indemnity coverage.

Hiscox argued that a 3420 claim cannot be asserted against it because the statute regulates insurers.  Hiscox was the policy administrator and a Lloyd’s syndicate issued the policy.  But the court disagreed that Hiscox could not be liable for a violation of 3420.  The court was influenced by the Hiscox logo on the reservation of rights letter:

“New York courts, however, have rejected the argument that Section 3420 applies only to the specific entity that issued the policy. See, e.g., B&R Consol., LLC v. Zurich Am. Ins. Co., 993 N.Y.S.2d 121, 123-124 (2d Dep't 2014). In B&R Consolidated, LLC v Zurich American Ins. Co., the Second Department rejected the defendants’ contention that ‘Zurich is not a proper party to this action under Insurance Law § 3420(b) because it did not issue the subject policy.’ Id. at 124. Although Section 3420(b), like Section 3420(d), refers to ‘an insurer,’ the Appellate Division held that the evidence of ‘Zurich's direct participation in the administration of [plaintiff’s] claim is sufficient to establish, prima facie, that an agency relationship existed between Zurich and American Guarantee such that Zurich may be held liable to [plaintiff].’ Id. The Appellate Division noted that Zurich's logo was present on the relevant documents and that Zurich's claims counsel was assigned to handle the underlying action. Id.

“Here, as with Zurich, Hiscox’s logo was present on the policy documents and the Reservation of Rights letter, which was sent by Hiscox's claim counsel.  Accordingly, resolving all factual and legal ambiguities in favor of Plaintiff, Hiscox’s assertion that it is not a proper party because it did not issue the policy fails to establish that there is ‘no possibility’ that Plaintiff could assert a Section 3420 claim against Hiscox in state court.”

Other arguments concerning Hiscox’s role were rejected.  So there was no fraudulent joinder since it was not a situation of no possibility that the claims against the non-diverse defendant could be asserted in state court.  In other words, Hiscox was properly before the court, so diversity was defeated and the case was remanded to state court.

I follow reservation of rights cases very closely – and discuss this “letterhead issue” in my “50 Item ROR Checklist” webinar.  The court didn’t mention this, but the reservation of rights letter stated: “Hiscox will agree to provide [Plaintiff] a defense under the policy, subject to the below reservation of rights.”  This is also an issue to consider regarding who issued the policy.         

So, despite it being a fraudulent joinder case, Glidedowan had a strong enough hook to coverage, not to mention and interesting issue, to make it into CO. 

I rarely address the “is faulty workmanship an ‘occurrence?’” issue in Coverage Opinions.  The case law is pretty well-developed, the facts often similar and the issue the same.  In general, a contractor performs work on a construction project that turns out to be defective -- and it may or may not have caused damage to other property, perhaps to other work at the project or away from the project. In general, arguments will be made that there is no coverage for the cost to repair or replace the insured’s defective work, as it was not caused by an “occurrence,” but any damage as a consequence of the insured’s defective work was caused by an “occurrence.”

The Alabama federal court’s decision in Frankenmuth Mut. Ins. Co. v. Ivan’s Painting LLC, No. 21-945 (N.D. Ala. Dec. 19, 2022) addresses the “occurrence” issue, but in a less common scenario.  A contractor performed defective work – but what to make of the damage caused?  Was it damage to the contractor’s work – not an “occurrence” -- or something else, thereby satisfying the “occurrence” requirement.

TCC, Inc. was a general contractor for the construction on a home in Tuscaloosa. [Alabama fans, welcome back, after having just taken a second to stop and say Roll Tide.]  TCC hired Ivan’s Painting to pain and clean windows – a lot of them.  The homeowners demanded that Ivan’s relace the 87 windows that it damaged. 

Coverage litigation arose, including an additional insured issue and whether an insurer could intervene in the case.  None of that is important here.

What caught my attention was the “occurrence” issue.  The court started out with a basic statement of Alabama law: “When a contractor performs faulty work ... there is no accident or occurrence, but, when the contractor’s faulty work creates a condition that in turn damages property, under Alabama law, that damage results from an accident.”

What made the issue here a little different was that Ivan’s was hired to paint the window frames.  But, in the course of doing so, it scratched the glass.  Ivan’s explained that the windowpanes were damaged “during the sanding process, to get the wooden frames to the tone desired by TCC and/or owners of the home.”

One insurer argued that there was no “occurrence” as the only damage was to Ivan’s work, with no resulting damage.  Ivan’s [and another insurer] countered that the “damage at issue is the scratched glass and Ivan’s work was limited to the adjacent frames.  Thus, … there is an occurrence under Alabama law because ‘[t]he claim does not simply seek to redo or repair Ivan’s Painting's faulty painting or staining work, which would not be an occurrence.’”

Following a review of Alabama case law on the “occurrence” issue, the court – looking at it from a foreseeability perspective -- concluded that there was no occurrence: “Damage to the tangible property immediately adjacent to the property on which Ivan’s was working was foreseeable, and thus it should be reasonably anticipated.  Indeed, Ivan’s did anticipate as much when it put a protective liquid masking on the glass before the work commenced.  Therefore, this damage cannot be considered an ‘accident’ under Alabama law and consequently it does not fall within the definition of occurrence under the policy.”

Again, it’s a “occurrence” decision, but with a unique aspect to the consequential damages issue.    

Dude Products – I love that name – sold an alternative to toilet paper called “Dude Wipes.”  Some users sued Dude, alleging that the Dude Wipes did not break apart or disperse in a reasonable time after flushing, resulting in clogs or other sewer damage.

At issue in an eventual declaratory judgment action was coverage under Dude’s commercial general liability policy.   
 
The insurer argued that an underlying complaint did not allege “property damage,” as the clogging did not cause physical injury to tangible property.  The court in Harleysville Preferred Ins. Co. v. Dude Prods., No. 21 C 5249 (N.D. Ill. Dec. 21, 2022) disagreed, concluding that allegations of “other sewage damage” was enough to qualify as physical injury to tangible property.

With that issue down the drain, the court turned to the “occurrence” question, concluding that the definition had been satisfied: “Here, the underlying complaint does not describe a direct causal connection between Dude Product’s allegedly intentional misrepresentation and the actual property damage. The allegation is that Dude Wipes are falsely advertised as flushable and that to the contrary, flushing the product results in clogging and sewer damage. There are no allegations indicating that Dude Products intended this sort of damage by its advertisement or that such damage was a clearly foreseeable result.”

After that observation regarding intent, the court, as you would expect, had no problem concluding that the expected or intended exclusion did not apply.  In addition, the court easily dispensed – which didn’t surprise me – with the potential applicability of the impaired property exclusion.     

Incidentally, being the curious George-type that I am, I checked out the Dude Wipes website:  https://dudeproducts.com/.  It’s entertaining.  Trust me.  Further googling revealed that Dude Wipes was a Shark Tank company, with Mark Cuban putting in $300K for a 25% share of the company.  Shark Tank’s update website reports that the company’s lifetime revenue is over $120 million, with sales of up to $1.4 million per week. 

As we all know, the body of case law addressing the pollution exclusion is gargantuan.  But, as a Texas federal Magistrate Judge recently said in a Report and Recommendation in Atain Specialty Ins. Co. v. Triple PG Sand Development, No. 21-2122 (S.D. Tex. Feb. 28, 2023), that’s not where you look when determining whether the exclusion applies to a claim.

At issue in Triple PG was the applicability of the pollution exclusion to claims asserted against Triple PG, and dozens of other defendants, for damage caused by flooding in Houston, in 2017, from Hurricane Harvey.  It was alleged that Triple PG – engaged in the business if sand mining- “discharged ‘processed water, silt, sand, sediment, dirt, and other materials’ into Houston-area waterways and lowered their capacity—effectively displacing potential floodwater with discharge.”  In other words, the materials discharged by Triple PG allegedly caused flood control channels to have decreased volume.  As a result, they could not hold the water from the hurricane and overflowed.

The court noted that these materials were not expressly included in the policies’ definition of “pollutants” – the standard one that we’ve all seen many times.  However, the insurer pointed to cases where courts concluded that these materials were pollutants under substantially similar pollution exclusions.

But that, the court concluded, “would allow the tail to wag the dog,” and rejected the insurer’s reliance on these cases: “The Court cannot look to prior applications of pollution-exclusion clauses and then search the Underlying Lawsuits for mentions of the same materials. Rather, the Court must look to the specific factual allegations in the Underlying Lawsuits and then apply policy language and its plain meaning to those allegations.”

In other words, even if the asserted pollutants -- processed water, silt, sand, sediment, dirt – were found to be within the pollution exclusion in other cases, that was not the manner for determining if they were pollutants here.

Rather, examining the specific factual allegations in the suits, and applying it to the policy language, led to a determination that the pollution exclusion did not apply.  The court had several explanations for its conclusion -- some complex, quite fact-specific and beyond the scope here. 

However, an important part of the opinion, that led to the court’s decision, is as follows.  After examining some definitions of “contaminants,” the court concluded that, “[f]or these definitions to foreclose a duty to defend, the Underlying Lawsuits would need to complain that Triple PG released substances that rendered the waterways and lakes impure, either by mixing with the existing water or soiling or staining it upon contact. That is not what the Underlying Lawsuits allege. Instead, they allege the mere presence of the released substances reduced the capacity of the waterways, thereby exacerbating flooding during Hurricane Harvey.”

For this court, the outcome was not dictated by decisions where processed water, silt, sand, sediment and dirt were found to be within the pollution exclusion.  Rather, the issue was whether, under the circumstances at hand, the materials were acting as pollutants.

This is a tragic case.  And the possibility of coverage was thin.  But sometimes the effort is made.  Not surprisingly, it did not succeed.

Donald Bottoms owned Three D Plumbing.  The place of business contained an apartment.  On a night in April 2020, Bottoms and some friends spent time there socializing.  In the early morning hours, bottoms drove Nicole Wagner home.  According to Bottoms, Wagner refused to leave the vehicle.  Bottoms used a gun that he kept under the seat in an attempt to scare her out.  During a struggle or accident – unclear – Bottoms shot and killed Wagner.  Bottoms pled guilty to second degree manslaughter.

As part of a settlement agreement, Bottoms assigned his rights under a commercial general liability policy to Wagner’s estate and the issue of coverage made its way to a Kentucky appeals court.  While the applicability of the expected or intended exclusion was clearly going to be an issue, the court in Jones v. Acuity, No. 2021-0834 (Ky. Ct. App. Dec. 22, 2022) started with a more overarching question: Bottoms was only an insured “with respect to the conduct of a business.”  Was that requirement satisfied?

It seems difficult to see how it could be.  The estate made these arguments:

“[T]he events leading up to the shooting included the promotion of Three D Plumbing and the ‘building of goodwill,’ thereby falling under the umbrella of actions taken ‘with respect to the conduct of a business.’ To support this contention, Jones [the estate] presented an affidavit from a former Three D Plumbing client who stated (1) that she hired Bottoms after attending a social gathering at Bottoms’s apartment, and (2) that Bottoms frequently promoted his plumbing business at such events.

“Additionally, Jones submitted a photograph of Bottoms, Wagner, and three other people ‘poised in a luxury bathtub in Bottoms’[s] place of business during the social gathering.”

Acuity, with help from Bottoms, who did not want to see coverage afforded, argued that “Bottoms stated in his affidavit that the events leading up to the shooting were not business related; the plumbing client affidavit was irrelevant because she was not present on the night in question; and the undated photograph does not equate to conducting plumbing business.”

The court sided with the insurer:

“The client affidavit was not from someone present with Wagner and/or Bottoms on April 18 or 19; thus, it was not based upon any personal knowledge of the events leading up to the shooting. Further, text messages between Bottoms and Wagner on that fateful evening do not reference plumbing. Bottoms asserted in his affidavit that none of his activities of April 18 and 19 ‘were related in any way to my occupation or business as plumber.’ Instead, he stated that the evening was ‘for purely personal, social, and nonbusiness reasons.’ Jones was unable to link Bottoms’s plumbing business to the shooting - a shooting which occurred in Bottoms’s vehicle while it was parked in Wagner’s driveway after a night of socializing. Further, while the photograph did technically show a bathtub and part of a faucet, that alone does not correlate to conducting plumbing business. Stated another way, just because a chicken has wings does not mean it can fly.” (emphasis in original).

Incidentally, while not necessary to have reached the issue -- based on this conclusion -- the court went on to state that, with Bottoms having pled guilty to second degree manslaughter, i.e., wanton manslaughter, the expected or intended exclusion applied.
      
Tragic case for sure.  While there were some interesting facts concerning the “conduct of a business” argument, the conclusion was unsurprising.

I love dog bite cases – coverage and otherwise.  I’ve discussed many in CO over the years and have written several articles about them.  I even did an article in June 2000, for The Wall Street Journal, on the occasion of the 200th anniversary of the first-ever dog bite judicial decision. 

[I never told my wife about piece.  Is she knew that I had time to research an article like that, I’d never again be able to claim that I didn’t have time to clean out the attic.]

In Rolinc v. Williams, No. 111518 (Ohio Ct. App. Feb. 2, 2023), an Ohio appeals court addressed the availability of coverage, under a homeowner’s policy, for injuries sustained by Todd Rolinc on account of an August 2020 attack by Mallory, a pit bull mix, and Beastro, a bulldog.         

Now, go back two months.  In June 2020, the duo of Mallory and Beastro attacked Tootsie, a Welsh terrier owned by Debra Shufran. Shufran, believing that the attack on Tootsie was an isolated incident, did not file a police report.  But now, after witnessing Mallory and Beastro’s attack on Rolinc, Shufran filed a police report concerning the earlier attack on Tootsie.

Rolinc filed suit against Nicoy Williams, Mallory and Beastro’s mom.  She sought coverage under a homeowner’s policy issued by Nationwide.  Coverage litigation arose over the potential applicability of a dog bite exclusion, which precluded coverage for “‘bodily injury arising out of...(e) Any dog with a prior history of attacking or biting * * * person(s) or animal(s), as established through insurance claim records, or through records of local public safety, law enforcement or other similar regulatory agency.” (emphasis added).

Here's the interesting part.  Nationwide argued that the exclusion applied.  After all, prior to the attack on Rolinc, Mallory and Beastro had attacked Tootsie -- and there was a police report of the incident.

But the trial court disagreed.  And so did the appeals court.  While Mallory and Beastro’s attack on Tootsie took place before their attack on Rolinc, and there was a police report on the Tootsie attack, there was no police report of the attack on Tootsie at the time of the attack on Rolinc:

“On August 2, 2020, which is the date Beastro attacked and bit Rolinc , Beastro did not have an ‘established’ prior history of attacking or biting a person or animal.  In fact, the August 5, 2022 police report of the incident with Rolinc is the first ‘established’ history of Beastro attacking or biting a person or animal.  In applying [citation omitted], we find that the August 5, 2022 police report [concerning Tootsie] is irrelevant to a determination of whether Beastro had a prior established history of biting or attacking.”

I’m not sure how often this situation arises in the context of medical professional liability policies.   But, if it’s with any frequency, insurers that write policies in this area should look at their forms to determine if there is an unintended opening to coverage that should be stitched up.

Fetemeh Shahriani visited an Urgent Care and Dr. Moosa Heikali gave her an injection for pain in her knee.  An infection ensued, causing permanent damage to the knee.  At the time of the injection, Dr. Heikali’s medical license had been suspended.

Shahriani filed suit against several parties, including Dr. Heikali and Dr. Bahram Tabibian, the CEO and director of Urgent Care.  His medical license had also been suspended at the time of the incident.  Ass an aside, Dr. Heikali and Dr. Tabibian were also the subject of a criminal prosecution for violating the California Business and Professions Code for the unlicensed practice of medicine.

At issue in General Star Indem. Co. v. F and M Radiology Medical Center, No. 22-2233 (C.D. Calif. Jan. 13, 2023) was coverage for the defendants under a General Star Miscellaneous Health Care Professional Liability policy. The professional liability policy excluded physicians as insureds.

Among other issues before the court was “insured status” and the potential applicability of the Licensure exclusion, which precluded coverage for claims arising out of a “medical incident” -- which was satisfied here -- involving an insured, which occurs during the time that the insured’s professional license had been suspended or revoked.

The court concluded that, on two grounds, it was unable to grant the insurer’s motion for summary judgment.  The issue with respect to Dr. Heikali, the one who administered the injection and did so while his medical license had been suspended, is most interesting.

First, even though the policy excludes physicians as an insureds, Dr. Heikali, the court concluded, may have been an insured, as he may have been working in his capacity as a medical assistant when he gave the injection.  

Second, if Dr. Heikali was working in his capacity as a medical assistant, then the Licensure exclusion may not apply.  The court noted that medical assistants may administer the injection at issue here.  Second, the court observed that the policy was silent on whether the Licensure exclusion applies when the insured is operating in a capacity for which a license would not be required.

So, to summarize, it paid – literally – for a physician to have a suspended license.  Here, it landed insured status that otherwise wasn’t there, and took the now-insured outside the scope of an exclusion designed to preclude coverage for just the situation he faced.  Something isn’t right here.

Those who handle pollution exclusion cases are aware of Indiana’s unique treatment of the issue.  

In 1996, the Supreme Court of Indiana, in Am. States Ins. Co. v. Kiger, held that, for the pollution exclusion to apply, the pollutant at issue must be explicitly stated.  Based on this, the court held that the pollution exclusion did not preclude coverage for claims for damages caused by the discharge of petroleum from an underground storage tank at a gas station.  

At issue in Indiana Farmers Mutual Inc. Co. v. Homeworks Management Corp., No. 22A-1232 (Ind. App. Ct. Dec. 21, 2022) was coverage for landlords/property owners for bodily injury suffered by tenants caused by exposure to lead paint dust. 

The insurer argued that its lead exclusion applied.  The insured, obviously knowing that it had an uphill battle, tried to give the policy’s lead exclusion the Kiger treatment.  It argued that “because [Indiana Farmers] chose to define ‘lead’ as anything that has lead in it, without any specificity, the exclusion is ambiguous and unenforceable.’  They emphasize the language in the Lead Exclusion that ‘[s]uch claims may include but are not limited to (emphasis added by court) those arising out of or resulting, in whole or in part, from’ certain situations, contend that the Lead Exclusion is expansive, ambiguous, and vague, and assert that Indiana Farmers could have explicitly limited the exclusion to ‘lead paint’ or ‘respirable lead compounds.’” 

As the insured saw it, the lead exclusion is so broad that “an insurer could exclude coverage for an accidental discharge of a firearm if the bullet contains lead, a hammer containing lead falling on a guest’s foot, or the death of an individual caused from smoke inhalation during a fire of a home containing lead.”

But the Indiana appeal courts rejected this effort to Kigerize the lead exclusion.  The general problem that Indiana courts have had with the pollution exclusion, the court pointed out, was the breadth of the definition of “pollutants” -- “any solid, liquid, gaseous or thermal irritant or contaminant, including smoke, vapor, soot, fumes, acids, alkalis, chemicals and waste.”

However, the Homeworks court concluded that the lead exclusion here did not suffer this same flaw: “[T]he Lead Exclusion did not use the general term ‘pollutants.’ Rather, it specifically mentioned lead. We conclude that the term ‘lead’ under the Lead Exclusion is unambiguous and does not contravene public policy or the case law regarding a general pollution exclusion.”