My idea is pretty simple – I want to bring scientific proof to the supplement shopping process.
Too many products are sold with exaggerated claims or without any science backing.
I am doing two things to fix it:
I am using LLMs to index all scientific papers that mention different supplements. I then extract insights from those papers in relation to the supplement and summarize on a matrix of effect type relative to the health outcome and effect size, e.g. https://pillser.com/health-outcomes/enhanced-disease-resista....
I then index all ingredients of every supplement on the market, and then based on the composition of the ingredients, I surface the relevant scientific evidence to back or dismiss any health claims, e.g. https://pillser.com/vitamins/vitamin-b1
People are able to search products (https://pillser.com/search) by their desired health outcomes, dietary restrictions, and other attributes important when shopping for supplements.
The business model of Pillser is the affiliate revenue from the outbound links that take people to Amazon, etc.
Pillser has several hundred regular users that use it to ask questions when researching supplements. However, otherwise, the unexpected challenge has been that getting news users is nearly impossible because ranking for related keywords on Google is nearly impossible. So the growth has mostly stalled.
It's been my life's dream to build something in intersection of my interests – nutrition and AI. So I am excited to have built a product that is serving users. However, I am also debating what's the path forward, as the original idea of building a free to use product that starts making money from a large scale of affiliate sales seems to be a foggy dream given the current Google trends.
Proud to share what I have accomplished and would also love your feedback for how to move forward.
Curious to see how it does, as it was something I considered building! The thing that put me off from doing it is that it is just too simple for existing platforms to add AI feature on top of their existing offerings.
Oh interesting! We've definitely seen that its not super easy to just add AI for relevance if you have a super diverse user base. Currently our customers are early stage b2b SaaS and we understand what their goals and use cases are. Therefore, adding something like relevance isn't so straightforward for a big player IMO.
But cool to hear you thought of building something similar! I think its a good sign that there is a need.
It's been 3 months in the making and a journey started with an exchange on HN. I couldn't be happier to share progress!
What is Pillser? Pillser aggregates data from thousands of research papers and about thousands of supplements, bridging the gap between scientific research and consumers. Our goal is to provide easy access to unbiased information on supplements and nutrition, empowering you to make informed health decisions.
Pillser Ask leverages the same data that powers Pillser, but also has access to sources like ods.od.nih.gov, nhs.uk, and a dozen more authoritative sources on nutrition. It can give personalized, evidence-based advice on nutrition and supplementation.
The chat is prompted to work with as little or as much information that you feel comfortable disclosing. However, the more variables that you tell the chat (like age, sex, body weight, etc.), the more of these variables are used to match Pillser's vast database of research papers (https://pillser.com/research-feed) to surface the most relevant insights.
In future, the personalization is going to be built into the product. I am working on a health card – you will be able to opt-in to creating a profile on Pillser that describes your age, sex, body weight, existing medical conditions, etc. and Pillser will automatically take these into consideration when you ask Pillser Ask a question.
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-disclosure
Pillser is a young project, just over 3 months in development, and I envision it as my life's work. The field of healthcare, nutrition, & 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-supplement-research-and-compa...
I don't know yet how exactly the project will evolve over the time. I just know that there is some intersection between people wanting to eat and live healthier and vast amounts of research, and that somehow successfully combining them can create something that people want.
Would love to hear your perspective on the project today and where your imagination takes you!
Very happy with Fly.io. My website Pillser runs on it and I never had issues with them. The cost per month us just under USD 100 for hosting 3 services, including the database.
