I built Bloomberry which specializes in just this. You can pass in a company domain and it returns a list of technologies/products we detect that org uses (especially backend/backoffice ones like devops, security, CRMs like Hubspot). I think this fits your use case.
Alternatively, you can pass in a specific technology (ie Github) and we return companies we detected that use it. But this is more for prospecting, not enrichment.
Agreed that Builtwith, in general isnt as good for this. Its more for finding out what technologies a website uses, not what they are using on the backend.
I dont think our API costs an arm/leg, but you should give it a try to see how well it works for your use case.
Also, in terms of hallucinations, you might want to consider giving more context to it. So instead of just telling the LLM the domain/company only, scrape their website, get all the javascript and XHR calls it makes, and find any job postings, then pass ALL of that to the LLM. The more data it has, the more it can extract. If you just give it a company website, it's just going to make stuff up. That's my 2 cents if you insist on going the LLM route. Or just tell it to scrape more stuff (which will cost more tho)
See the reply up above. You can't just expect LLMs to give you good answers if you're not providing lots of context to it. Also, make sure you give it guardrails. Like say you can't only infer it from the JS scripts on their website, external AJAX calls, job postings posted directly on their website, their Github profile, and engineering blog... Otherwise you're gonna get lots of made up stuff :)
I built Bloomberry which specializes in just this. You can pass in a company domain and it returns a list of technologies/products we detect that org uses (especially backend/backoffice ones like devops, security, CRMs like Hubspot). I think this fits your use case.
Alternatively, you can pass in a specific technology (ie Github) and we return companies we detected that use it. But this is more for prospecting, not enrichment.
Agreed that Builtwith, in general isnt as good for this. Its more for finding out what technologies a website uses, not what they are using on the backend.
I dont think our API costs an arm/leg, but you should give it a try to see how well it works for your use case.
https://bloomberry.com
Also, in terms of hallucinations, you might want to consider giving more context to it. So instead of just telling the LLM the domain/company only, scrape their website, get all the javascript and XHR calls it makes, and find any job postings, then pass ALL of that to the LLM. The more data it has, the more it can extract. If you just give it a company website, it's just going to make stuff up. That's my 2 cents if you insist on going the LLM route. Or just tell it to scrape more stuff (which will cost more tho)
Just give the page to chatgpt and ask what they use. Give them as much info as you can.
I have tried that but 1) it hallucinated a lot of technologies as I mentioned and 2) it only detects the front end stuff not backend
See the reply up above. You can't just expect LLMs to give you good answers if you're not providing lots of context to it. Also, make sure you give it guardrails. Like say you can't only infer it from the JS scripts on their website, external AJAX calls, job postings posted directly on their website, their Github profile, and engineering blog... Otherwise you're gonna get lots of made up stuff :)