Healthcare is a complex and fragmented sector that has long been weighed down by legacy systems and regulations.

If that sounds like a recipe for innovation, you might want to get your ears checked.

The industry’s longstanding institutional inertia when it comes to modernizing not just the business of care but the administrative workflows and processes supporting it might be beginning to thaw.

The reason? The evolution of agentic artificial intelligence, which represents the latest, autonomous iteration of the buzzy software technology.

“We are in a unique time in history,” Autonomize AI CEO Ganesh Padmanabhan said during a discussion hosted by PYMNTS CEO Karen Webster. “Until large language models specifically came about, it was impossible to distill information out of complex medical clinical documentation and contextualize it for different workflows. Now it’s possible,”

Still, Webster noted, agentic AI has become the latest talking point regardless of its real-world results in critical areas.

“It used to be generative AI, now it’s agentic AI,” she said. “But this is still an emerging technology. Why is now the time for it to be applied in healthcare, given that a lot of the industry is still trying to get its arms around basic automation?”

“Healthcare is one of those industries with a lot of knowledge work,” Padmanabhan said. “Data is often created by humans for other humans to consume, which makes automation innately harder.”

At the heart of the problem in healthcare is an industry drowning in administrative burdens. In the United States, an estimated $1.5 trillion is spent on healthcare administration annually, a cost that contributes to delayed care, clinician burnout and poor patient experience.

Targeting the ‘Business of Care’ With Agentic AI

Rather than tackling every facet of healthcare at once, Autonomize AI, which closed a $28 million funding round last month, focuses on what Padmanabhan called the “business of care.” That includes the invisible scaffolding that supports how care is delivered, such as insurance approvals, quality reporting and patient communication.

“Our focus is on building AI assistants, copilots and agents to augment the workforce,” Padmanabhan said. “There are two people often forgotten in healthcare: the providers who deliver care, and the patients who receive it. We’re putting them both back at the center.”

One example is prior authorization, a complex and manual process in which doctors seek insurer approval for medical procedures. It often involves faxes, weeks-long delays, and endless reviews by nurses and doctors, ultimately leaving patients in limbo.

“This whole process takes days, if not weeks,” Padmanabhan said. “It’s very error-prone. We aim to automate the intake, parse the information in the medical records, adjudicate that against policies, and summarize it for a clinician to make a decision in minutes.”

As Webster noted of the pain point: “After a doctor has said, ‘I want you to see XYZ doctor,’ you assume that call is going to happen. And then it doesn’t. You have to chase it down. That burden falls back on the patient.”

Building Trust in a High-Stakes Environment

For healthcare businesses, unburdening clinicians from administrative tasks isn’t just about productivity but can be about purpose, too.

“There’s a 300,000-nurse shortage in the provider spectrum,” Padmanabhan said. “Most are working at health plans doing paperwork. We need to enable a transition for them to do what they’re meant to do, which is provide care at the point of care.”

Yet automating workflows in healthcare isn’t as easy as flipping a switch.

“This is a hard problem,” Padmanabhan said. “Healthcare data isn’t fully digitized. There are gaps in knowledge.”

Autonomize AI’s own solution is to deploy “copilots” that identify which parts of a workflow can be automated, and then orchestrate seamless handoffs between AI and human workers, he said. Over time, these systems learn and improve based on real-world use.

Trust is the linchpin.

Webster pointed out the risks of incorrect output.

“In a clinical setting, the ramifications of wrong can be quite significant,” she said. “How do you build in those checks and balances?”

“You’ve got to build trust through product,” Padmanabhan said. “Showing evidence, provenance and allowing clinicians to go back to the source data is crucial.”

The long-term vision of agentic AI in healthcare isn’t just about optimizing current processes; it’s about redefining success.

“We don’t do healthcare in this country. We do sick care,” Padmanabhan said. “We need to shift from measuring mortality rates to tracking how many preventative interventions reduced chronic disease.”

For all PYMNTS AI coverage, subscribe to the daily AI Newsletter.

Did you hate these annoying songs? Check out what new deep research AI tools can do.

It’s all well and good to tell people to get on ChatGPT, or Claude, or Gemini, and get their hands dirty using an AI model – but some people want more detail. They want to know how to use the best new tools in a more granular way.

Deep research is one of the newest and most impressive functions of today’s large language models. But most people haven’t heard of it yet, let alone used it.

Ethan Mollick is someone I associate with the vanguard of AI research. With former MIT connections, Mollick represents a leading voice in this field. So I was reading his latest blog post about different models, and how to use them.

Mollick breaks down the most useful models for Claud, ChatGPT and Google in the following categories: “chat,” “work” and “hard problems.”

Claude, he notes, is generally better for privacy, where you need to select for this in ChatGPT, and may compromise some functionality with Google.

Then Mollick embarks on a description of deep research capabilities that are baked into some of the newest models, but not yet available for free. This is so new that it’s still paywalled and rationed for paying users.

The Promise of Deep Research Functionality

Deep research is available from OpenAI, and from Google, and from Anthropic, too.

When you look at the unveiling of the research function, you see a lot of reports around February.

So how do you access this kind of result?

I found a recent post about this from the “OpenAI cookbook” in June, where the poster talks about downloading a Python SDK, and API work.

It turns out, though, that you can select “deep research” in the prompt section of ChatGPT 4.5, if you are a paying Plus or Pro user, and get your deep research report that way.

Asking for Deep Research from ChatGPT 4.5

I wanted to try this for myself, so based on what I was experiencing in the moment, I centered on compiling a report of the most annoying songs from 1990 through 2025.

My query: “please create a report on the most annoying music from 1990 until 2025, segmented annually.”

Simple, right?

First, ChatGPT asked me to clarify a few basic questions:

“To create a detailed report on the ‘most annoying music’ from 1990 to 2025, could you please clarify a few things:

1. What do you mean by ‘annoying’? Are you referring to songs widely criticized, overplayed, polarizing, or based on listener polls or memes?
2. Should the list be global or focus on a specific region (e.g., U.S., UK, etc.)?
3. Do you want one song per year, or multiple per year if applicable?
4. Would you like the report to include explanations or cultural context for each selection?”

And I answered:

“1. all of the above 2. US-based 3. multiple songs per year 4. Yes.”

“Thanks!” GPT responded. “I’ll compile a U.S.-focused report covering the most widely criticized, overplayed, or culturally mocked songs from 1990 to 2025. This will include multiple songs per year, along with context explaining why they were considered annoying—drawing from music critics, listener polls, memes, radio overplay complaints, and public opinion.”

Then the report started. Indeed, it took more than 10 minutes to compile, with CoT displays like “searching ‘Rico Suave’: worst song’ and ‘looking for Macarena.’

Check Out GPT’s Chain of Thought

Actually, here are some of the interesting CoT notes the system provided while doing research on dozens of sites (it spent a lot of time reading the Guardian!)

I’m mapping out recent headlines and thought pieces, like those from Global News and the Guardian, all noting “Baby Shark” as the most annoying song. Hm, that’s interesting.

I’m preparing the list of most annoying songs from 1993-1995, considering “What’s Up,” “Cotton Eye Joe,” “Macarena,” and “Wonderwall.” However, I’m thinking through the inclusion of other notable tracks like “Rico Suave” for earlier years.

(There’s that ‘Rico Suave’ song again.)

I’m mapping out the hits and misses of 2001-2006, with 2005’s viral sensations like “Crazy Frog” and “Photograph” by Nickelback taking center stage. Hm, that’s interesting—these tracks seem to evoke strong reactions.

(Note how the model is actually ‘taking notes’ while researching, giving us little bits of personality along with the actual meat of the report.)

Here’s a funny comparison:

I’m comparing the impact of Nickelback’s “Rockstar” in 2006 to Soulja Boy’s “Crank That” in 2007. The former was widely criticized, while the latter was loved by many, raising questions about musical taste over time.

A research-based note:

I’m digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.

I’m evaluating hits like Meghan Trainor’s “All About That Bass” (2014) and Tyga’s “Stimulated” (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.

I’m digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.

I’m evaluating hits like Meghan Trainor’s “All About That Bass” (2014) and Tyga’s “Stimulated” (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.

And then there was this:

“Noticing the challenge of time limitations, I’m figuring out how to balance inclusion of pivotal examples against the need for conciseness.”

So the model is actually trying to triage its work. This is next-level stuff.

Finally, GPT appeared to wrap up, dotting its I’s and crossing its Ts:

“I’m checking to see if the ‘Achy Breaky’ song contains any references to anthropomorphic sharks.”

Eventually, I got the full report. It ranges dozens of pages, and provides great coverage of over a quarter century of horrible, terrible music. A few standouts, with years:

1990

• “Ice Ice Baby” – Vanilla Ice (1990): This hip-hop crossover hit became a pop culture punchline due to its cheesy lyrics and ubiquitous play. While it was initially a chart-topping success, critics later lambasted it; Spinner magazine ranked it the second-worst song in history, and Blender ranked it fifthen.wikipedia.org. A Houston Press critic even dubbed it the worst song ever by a Texas artist, claiming it “set back the cause of white people in hip-hop by a decade”en.wikipedia.org. Its overexposure turned the once-popular anthem into an annoyance for many listenerscraftyourhappyplace.com.
• “Rico Suave” – Gerardo (1990): A bilingual novelty rap track that peaked in 1991, “Rico Suave” was a one-hit wonder often cited on “worst song” lists. Its goofy, exaggerated Latin lover persona and repetitive chorus wore thin quickly. Blender magazine’s infamous list of the “50 Worst Songs Ever” placed “Rico Suave” among its ranks (in the high 30s), and retrospective pop culture forums frequently hold it up as an example of early ’90s pop cringeculturecrossfire.comforums.thefashionspot.com. The song’s catchphrase chorus (and its shirtless music video) made it memorable, but also widely mocked in the years since.

1994

• “Cotton Eye Joe” – Rednex (1994): This techno-hoedown remix of an old folk tune became a staple at sports games and parties – much to many people’s annoyance. With its frenetic fiddle loops and the grating “If it hadn’t been for Cotton Eye Joe” chorus, the track wears thin fast. CBS News put it at #1 on a “Worst Songs from Jock Jams” list, calling it an “unholy hybrid of country-fried fiddle kitsch and relentless hi-NRG drums”en.wikipedia.org. A Toronto Star critic dubbed it the worst song of the ’90s, describing it as “straight drivel”en.wikipedia.org. Even wrestler-turned-rocker Chris Jericho said it’s one of his least favorite songs ever – naming it alongside “Mambo No. 5” on his personal worst listen.wikipedia.org. Despite its party ubiquity, few ever actually wanted an “EDM-hillbilly” mashup like thisen.wikipedia.org.

1997

• “Barbie Girl” – Aqua (1997): This novelty dance-pop hit was simultaneously a global chart-topper and a critical punching bag. Its bouncy, plastic sound and exaggerated vocals (“Come on Barbie, let’s go party!”) made it a staple of late-’90s radio and kids’ parties, but also an irritant to many. Rolling Stone readers voted it the worst song of the ’90sen.wikipedia.org, and NME put it atop their worst-single list as wellen.wikipedia.org. While Aqua intended it as satire, the song was widely mocked; it even sparked a lawsuit from Mattel for tarnishing the Barbie brand. Decades later, it remains a guilty pleasure earworm that routinely tops “most annoying” song listscraftyourhappyplace.com.

Fast-forward a bit:

2013

• “The Fox (What Does the Fox Say?)” – Ylvis (2013): An absurdist novelty song by a Norwegian comedy duo, “The Fox” unexpectedly became a global viral hit in late 2013. Its EDM-lite beat and litany of animal sounds (ring-ding-ding, wa-pa-pa-pow!) made it the “Macarena” of the YouTube era – funny at first, then torturous on repeat. Kids loved the silliness, while parents and many others quickly tired of it. The song was essentially one long joke about animal noises, and once the joke wore off, what remained was an insanely repetitive chorus of nonsense. Rolling Stone readers later voted it one of the most annoying songs of the 2010s, and USA Today called it “the year’s most aggravating meme song.” Like other meme hits, it got played at school events and even on radio as a curiosity, amplifying the annoyance for those who never wanted to hear “Hatee-hatee-hatee-ho!” again. Ylvis intended it as a parody of EDM pop – ironically achieving exactly the kind of ubiquitous earworm they were spoofing, to the annoyance of millions.
• “Baby Shark” (global viral hit – charted 2018/2019): {See 2016 above.} In 2018, “Baby Shark” finally chomped its way onto international music charts (hitting the US Top 40 by early 2019)theguardian.comtheguardian.com. This was the year the song truly went pandemic, crossing from kids’ YouTube into mainstream consciousness. By the fall of 2018, articles were calling it “the year’s most annoying song” outrighttheguardian.com. Parents everywhere pleaded for mercy from the doo-doo-doos. The Guardian wryly noted how even people who hadn’t heard it knew of it through cultural osmosis – often via tales of toddlers playing it on endless repeat, driving their families madtheguardian.com. Once it hit the radio and dance remixes appeared, there was no escape. “Baby Shark” in 2018 exemplified how a simple children’s ditty could unite millions in shared, head-throbbing frustration. (Fun fact: that year a viral social post joked that the Geneva Convention should classify repeated “Baby Shark” play as a form of torture – a sentiment many a worn-out babysitter would second.)globalnews.catheguardian.com

2023

• “Peaches” – Jack Black (Bowser) (2023): Featured in The Super Mario Bros. Movie, this over-the-top piano ballad sung by Jack Black (in character as Bowser) became a TikTok smash and even entered the Billboard Hot 100. It’s intentionally comedic – Bowser professing love for Princess Peach with a dramatic “Peaches, Peaches, Peaches” chorus. Kids and gamers found it hilarious and catchy; others quickly found it grating (especially if they hadn’t seen the movie context). The chorus is essentially one word (peaches) repeated incessantly with operatic bombast. Within weeks, clips of people annoyed by their friends or children endlessly singing “Peaches” popped up online. Though short, the song’s earworm power is strong. One AV Club article quipped that it’s the kind of novelty song “destined to annoy parents everywhere while their offspring replay it 1,000 times.” It’s a fresh example of how a song can go viral and charm its way into your brain – and then, thanks to sheer overuse, make you never want to hear the word “peach” again (sorry, Georgia).

Some Thoughts on Voice Mode

Let’s move back to the blog post: after delving into the above stuff, Mollick also covers the verbal capabilities of new systems that really change the interface. As he notes, you can talk to these models while you’re in the car, or on a walk, or anywhere that you have the space and time.

I think verbal communication is going to finally make LLM responses “real” to us. And that’s all I have to say about that – for now.

I think all of this is deeply informing to people who want to be practical about LLM use. The deep research function in particular is something people will be learning about as time goes on. How many of us will figure it out before something new comes along that makes it obsolete?

In any case, this was an excellent guide to how to make the most of AI in today’s environment.