Muhammad Mikael

Hey everyone,

I'm building an AI tool that helps HubSpot sales teams save time by cutting down the manual work after sales emails and customer conversations.

It is an AI layer that would be used as a HubSpot sidecard (extension). It can connect to your Gmail and can read sales emails, filter out noise, detect new leads vs follow-ups and turn each one into an approval card showing the extracted info (name, email, phone, company, position, deal-value warm/cold score) with source sentence, summary and next steps, you can approve/reject it on a field level and when you save the contact into hubspot it also automatically saves notes with user in HubSpot and creates reminders. it flags the promises made, silent deals and gives daily summary.

I'm still developing so please tell me what you think about the idea and how can I improve it if needed ?

Genuinely curious how bad this problem is for other people, or if it's just me.

I track roughly how much time I lose every week just copying stuff out of emails into HubSpot names, companies, deal details, next steps. It's not hard, it's just constant, and half the time I forget to log something until it's too late to actually follow up on it.

I ended up building a small AI tool for myself that reads sales emails and call notes and pulls that info out automatically, with the source sentence and a confidence score attached , with overall analytics so I'm not just trusting a black box. Still rough, still learning what actually matters day to day.

But I'm more interested in the general question here: for people who use a CRM daily, is manual data entry actually a real pain point for you, or have you already solved it some other way (Zapier, native integrations, just a good habit of logging right after every call)? Would love to hear how others handle this.