EN / RU / 🤖
← Back to essays
· Essay · 1 min

Issues with Pet Projects and AI Email Processor

I've realized that the main problem with my Pet projects is that they remain in the shadows.

<p>I've realized that the main problem with my Pet projects is that even if they do “take off,” they remain in the shadows because I don’t talk about them at all, and as a result, they don’t go beyond MVP – this needs to change.</p>

<p>One of the projects I’m working on in my free time is an AI email processor. I’ve tried different solutions (from <a href="https://fyxer.com/">https://fyxer.com/</a>; to <a href="https://superhuman.com/">https://superhuman.com/</a>;) and found that they are all very superficial. The attempt to simply overlay a prompt leads either to a complete lack of flexibility or to a drop in quality.</p>

<p>I decided to combine a deterministic approach (if/else) with the use of LLM.</p>

<p>Minimum task (which is already more or less solved): sorting emails into folders (notifications, emails related to kids, everything about AI, etc.)</p>

<p>Maximum task:</p>
<ul>
<li>to understand where actions are expected from me, but it’s not spam “reply if you’re interested”</li>
<li>to automatically respond to standard requests (or at least create drafts)</li>
<li>to launch some external processes</li>
<li>to summarize all emails in the folder once a week (convenient for subscriptions)</li>
</ul>

<p>Would you like such a thing in your email? What else should it be able to do besides what has already been described?</p>

<p>#ai #agi #startup #idea #personal_assistant #email</p>

<p><a href="https://t.me/+OvImEUmA7W5mYTRi">————————— Мысли Рвачева —————————</a></p>

Issues with Pet Projects and AI Email Processor — illustration