Helping you make informed decisions about your health. Access unbiased, science-backed insights on thousands of products. Make informed health decisions with personalized guidance and the latest research, all in one easy-to-use platform.
Hi Product Hunt! 👋
I’m excited to introduce Pillser Ask, an AI assistant designed to help you make informed decisions about supplements.
What is Pillser? Pillser aggregates data from thousands of research papers and supplements, bridging the gap between scientific research and consumers. Our goal is to provide easy access to unbiased information on supplements, empowering you to make informed health decisions.
Pillser Ask leverages the same data that powers Pillser. Whether you're looking to understand the benefits of a specific ingredient, have questions about a particular supplement, or seek evidence-based information, Pillser Ask is here to help.
A few necessary disclaimers:
Pillser generates revenue through affiliate marketing. We earn a small commission on sales made through our website, but we do not promote any specific product or brand. This ensures we provide unbiased information and insights without the influence of advertising. Full disclosure: https://pillser.com/affiliate-di...
Pillser is a young project, just over 3 months in development, and I envision it as my life's work. The field of healthcare & supplements is incredibly complex and nuanced, and I believe AI will play a critical role in making it more accessible. However, in this early stage of Pillser, I am still learning how to best utilize the data that powers it. I am putting a lot of effort into making sure that the information provided is accurate, but mistakes are bound to happen, and I am always open to feedback and suggestions. Learn more: https://pillser.com/ai-powered-s...
I'd love to hear your feedback and suggestions to make Pillser even better.
Check out the assistant at https://pillser.com/ask and let me know what you think!
Follow me along in my journey on X @lilouartz.
Thank you for your support!
@max_savonin1 I answer some of these questions in other comments (see answer to @kyrylosilin), but just to give more depth to the previous comment: Pillser is tasked to identify information that allows advice personalization (like sex, age, weight, etc), but it does not actively probe for that information. That's intentional, as I wanted people to only reveal information that they feel comfortable sharing, or that they think is relevant. However, once that information is mentioned, then for the duration of the chat, it will be always included when searching for research papers. The more of the variables that are known, the more personalized the advice will be.
Let's chat further about potentially working together! Join Pillser's Discord
Just tried it and got an error:
Unable to decode turbo-stream response from URL: https://pillser.com/ask.data
Something broke. We're working on it, but in the meantime, try reloading the page. If that doesn't work, come back later.
Error ID: fd49ed8c4f904d9b9b9575645c320149
Hey @chrismessina , Thanks for reporting. Looks like the error happened exactly when a deployment was happening. If you try again, it will work as expected!
@sol_orwell Thank you Sol, you are an inspiration! Examine has played a big role in my life shaping how I approach personal health care, nutrition and supplementation. It has been without a doubt a big inspiration for Pillser.
Glad to see an unbiased, fact-based review of pure ingredients ignoring brand names, etc. Anything to help people make healthier decisions in a win in my book, good job.
By the way, if you happen to be a Hacker News user, I've posted there too today. If you share excitement about this project, please share it in the hacker news thread as well! https://news.ycombinator.com/sho...
Some of you are really stress testing what this chat agent is capable of and I greatly appreciate it! 😂
Privacy and security has been a big concern in this project since the very start, as I am dealing with potentially very sensitive information. A lot of care has gone into ensuring that every fathomable edge case is covered. It is therefore fun to see these efforts paying off.
How does the AI ensure the information provided is up-to-date and accurate? Also, can users ask about potential interactions between different supplements and medications?
P.S. Sorry that your launch wasn't featured 😔
@kyrylosilin At the low level, it is a business secret. But at the high-level, I talk about it here https://pillser.com/ai-powered-s.... In short, it is a layered approach of several AI models being tasked to independently arrive to the same conclusion. The assumption here is that one model can be wrong, but it becomes increasingly less likely that all models would make the same interpretation mistake. Data is being regularly reevaluated as new models are released and also as new research studies are added. Today, the system is not perfect by any means (I am not consciously aware of any mistakes, but wouldn't bet that in that huge dataset there aren't any), but my believe is that unlike similar human efforts, Pillser's approach can be developed to be near perfect in the long-term due to incremental improvements to models and the orchestration of data integrity validation.
@ankit_singh71 I am not a big wearable health devices person and therefore probably lack some of the imagination necessary to imagine what such integration could look like. What do you have in mind?
There are many plans, but the primary focus at the moment is to keep enriching the depth of research insights, and find better ways to connect research with health outcomes and health conditions. I want someone who has a specific health condition and wants to work on a very specific health outcome know exactly which supplements can have the most effect. In the sea of blog posts and tens of thousands of research papers, there is really no way for every day person to do that today.
I love that Pillser aggregates data from thousands of research papers to provide unbiased insights. How does Pillser compare to other supplement information platforms like Examine.com or Labdoor in terms of data comprehensiveness and user experience?
@eugenie_thompson Pillser covers all types of supplements, including vitamins, minerals, probiotics, etc. But you can also ask broad questions about nutrition, because the dataset that Pillser utilizes has a lot of overlapping data with nutrition research.