SpamLabs

Description

The idea of the project was at first to create a API for validating email addresses to determine whether they are legitimate or they are fake/disposable. After some initial reachout to potential customers to validate it, I reached the conclusion that the demand for such a solution was not there.

Then, an initial pivot happened: from the conversations I outlined a certain complaint that was somewhat common among the contacted people: getting bombarded by unsolicited emails attempting to sell them all kinds of products and services (mainly SEO and outsourcing services). The pivot for SpamLabs was toward the direction of an email filter for blocking such content. After some iterations on the implementation using OpenAI, I managed to get a working solution where only the AI API costs were ~10€ per month in the average case, so the smallest plan ended up being ~20€. After some more outreach with this new solution I saw that the demand isn't there either for this new approach: these emails were at most a mild annoyance which was fixed with a few seconds of time investment each day. The value was nowhere near the 20€ prince point I was asking.

Related posts

SpamLabs: Tech stack does matter

For the indie hackers out there that say that tech stack doesn’t matter, I say: it actually matters. But not in the way you’d think. It doesn’t matter for the success of the company because some stacks are flashier or more optimized for performance. It matters for development speed. If

Vlad CălinVlad Calin

SpamLabs: We are live!

We launched and we’re ready to go! Although there are a million things I would still want to do, I bit the bullet and made launched the MVP of SpamLabs: an API that tells whether a user is spammy or not based on the email address and generated content. As

Vlad CălinVlad Calin

Getting more out of ChatGPT when developing SpamLabs

Recently I began exploring the idea of integrating ChatGPT into SpamLabs in order to build it into an unsolicited message blocker. To do that, the initial idea was to ask ChatGPT in a prompt something in the lines of is the following message a cold email? respond “yes” or “no”

Vlad CălinVlad Calin

SpamLabs: Back to the drawing board

The initial outreach to gather feedback about an API that validates email addresses based on various analysis (DNS analysis being the main one) didn’t turn out the way I hoped. Sent about 40 cold emails about gathering feedback to gauge the interest in such a service. Although the sample is

Vlad CălinVlad Calin

SpamLabs: Some more validation done (or not?)

After recently pivoted the direction of SpamLabs from being an email address analyzer API to a spam filter targeting cold emails, I decided to continue validating this new approach. The problem is real, I am dealing with it myself: on my work email I am getting some annoying cold emails,

Vlad CălinVlad Calin

SpamLabs: Shutdown!

Time to shut down this project! After a few weeks of actively trying to validate this idea, which included a slight direction pivot (in the same problem space), I was not able to definitely confirm the demand. I got some verbal encouraging posts from some indie hackers, but it was

Vlad CălinVlad Calin