PMM Search is a tiny search engine focused on product marketing.
It only indexes blogs, newsletters, and social posts from growth and marketing operators in B2B. Because of that, questions like “What should a homepage contain?” or “What is an SQL?” will get proper answers related to marketing and sales.
To do that, I’ve used Google’s Programmable Search Engine, which lets you define a set of websites where the search should be performed.
After you ask it a question (or enter a search query) it retrieves the top most important pages, processes them using Firefox “Reader mode” to extract the text, and then asks ChatGPT to summarize them.
The ChatGPT prompt looks something like this:
Based on the following sources what is the correct answer to “How to do X”
1. …
2. …
3. …
The code for querying ChatGPT and processing the results is based on Mckay Wrigley’s open-source clone of Perplexity AI.
I’ll soon launch the app but need to work out how many tokens are in the goldilocks zone. I’ll also release the code so you could build your own tiny search engine soon—being a hobbyist I have impostor syndrome and just need to clean it up a bit.
I’ll keep you updated. Just leave your email here.