FWIW I know of a pharmacy network that's implementing AI. Not only does the AI make egregious errors like speaking in Spanish when the conversation is in English. It also has a limited context window for ground rules of 5000 tokens or less. So correcting all the various errors goes over the instructions limit. As a result if the implementation goes through it will be of poor quality. All I can think is that people with no technical expertise are making these decisions, it is easy for any techie to predict that AI of this level won't be capable.
Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
41–50 of 172 posts
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#42So - I run a company that does AI agents for pharmacy. We are at Series B now and growing well - series C in 9-12 months given growth. We just acquired a competitor of that vendor so very much an insider. First, The technology works, and it scales, but the whole bottleneck is domain expertise and implementation. These are expensive, and hard to scale. We hire pharmacists as project managers, that's how important doma…
> We have hundreds of pharmacies with us now and they mostly successful and happy How happy are their patients?
NPS typically improves because no one stays on hold for 20+ mins anymore.
People have no ideas have pharmacies work. Pharmacies don't control how much they pay for drug, or how much they get paid. The margins are terrible and you can't hire enough techs to answer the phone at peak call volume. So - most people experience are terrible as they wait on hold for a really long time.
EVEN if the AI is a little rough around the edges with relational calls, just solving for transactional calls with no hold is a massive win.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#43> wrong dosages, and missed prescription notifications.
BS. How is the AI touching that information?
Prescription notification is outbound communication. It’s almost a recorded message. A little text to speech if it is supposed to read the drug name.
Wrong dosages?? This must be handled by the “enroll a new scrip” functionality, right? So basically B2B doctor interaction. You let AI touch that? Aren’t the vast majority of the costs from customers not doctors? None of this makes sense.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#44So - I run a company that does AI agents for pharmacy. We are at Series B now and growing well - series C in 9-12 months given growth. We just acquired a competitor of that vendor so very much an insider. First, The technology works, and it scales, but the whole bottleneck is domain expertise and implementation. These are expensive, and hard to scale. We hire pharmacists as project managers, that's how important doma…
Make it so the parts that are done by AI are rock solid, until then, they shouldn't be near a customer and be done by humans. Resist the greed!
So you want him to make a piece of software that models a probability distribution rock solid.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#45As someone who's been doing AI call centres for a while, I'm not surprised. It's really, really hard to build voice AI that works. There are no open source solutions that work out of the box. But the biggest problem is ASR. WER is still atrocious even with SOTA models. When you add drug names and regional accents, it's a recipe for disaster.
Just curious, why are drug names such a disaster? Do LLMs not understand pronunciation keys?
Drug names are frequently BS loaded with strange consonants without singular pronunciation guidelines (sadly English isn't German) so humans already have a lot of variation in how things are pronounced - models then need to comprehend those variations, regional dialects (like those fuggin' ahs from Boston).
It ends up being quite a lot of variation.
As some examples: Wegovy, Ixempra, Qvar, Keflex
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#46I happened to be in Vermont last week and was unaware of this change. I heard complaints from three separate people unprompted. It was a total dumpster fire put on top of a critical service.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#47Pharmacy phone lines are a terrible first use case for voice AI. Older callers, drug names, insurance mess, zero patience. Automating "store hours" is fine. Automating refill exceptions is how you get this outcome.
We build text-based (e.g. SMS rather than voice) agents for various medical conversations (e.g. preparing people for complex appointments).
Our user base skews elderly. Going in, I was really skeptical about how much engagement and value we could provide to these older patients. I'm blown away how well it all turned out and how valuable it's been for our patients and client clinics.
For example, we were able to reduce no-shows for some high-cost appointments by 80%. Turns out that the reasons why people don't show up are a complicated and diffuse — everything form anxiety, to not speaking english, to being confused about how to get into the building — and properly configured LLM-based systems are really, really good at dealing with exactly this sort of problem.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#48This is my favorite AI customer service story: https://arstechnica.com/tech-policy/2024/02/air-canada-must-... > Air Canada essentially argued that “the chatbot is a separate legal entity that is responsible for its own actions”
LOL, pleased to read that Air Canada got smacked down.
Yeah, if I'm calling or chatting with a company, I expect them to stand by whatever commitments they make, and I will judge them harshly if they don't. This is true whether an AI or a human is speaking on the company's behalf.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#49So - I run a company that does AI agents for pharmacy. We are at Series B now and growing well - series C in 9-12 months given growth. We just acquired a competitor of that vendor so very much an insider. First, The technology works, and it scales, but the whole bottleneck is domain expertise and implementation. These are expensive, and hard to scale. We hire pharmacists as project managers, that's how important doma…
Please apologize for making the world a worse place and explain how you will close your company down.
Re: Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
#50So - I run a company that does AI agents for pharmacy. We are at Series B now and growing well - series C in 9-12 months given growth. We just acquired a competitor of that vendor so very much an insider. First, The technology works, and it scales, but the whole bottleneck is domain expertise and implementation. These are expensive, and hard to scale. We hire pharmacists as project managers, that's how important doma…
Good for you and wishing you more success. You probably going to be down voted as sentiment here in HN is going against AI due to the pressure on jobs, which is completely understandable from emotional point. People tend to compare AI to perfection for some reasons, which is not the case with humans. How many errors happened due to human phone operators? In the last few days there was an article where humans scored 66% on human evals.
I’ve been working with AI for years now and it’s not an easy task to get it right, but negative news go viral faster especially when it’s what people want to hear.