Genie, our AI Analyst, can already tell you what changed in your numbers. It's never been able to tell you why, because the why almost never lives in Databox.
Revenue drops 8%, and the real reason is a stalled deal in HubSpot, a pricing objection buried in a Slack thread, or a support ticket nobody flagged. Right now, finding that out means leaving your dashboard, opening three other tools, and piecing it together yourself. Every time.
Next week, we're launching MCP Connectors. Connect your CRM, Slack, support desk, or any MCP server, and your AI Analyst gets that same context, right inside the conversation. Ask why a number moved, and it points to the actual deal or thread behind it, not just the number.
What happens when the available data is incomplete or does not clearly explain a performance change?
Can teams create different report formats for executives managers and individual departments?
The business context layer seems important because numbers without context can easily lead to the wrong conclusion. How is that context added and maintained over time?
hey, pulling context right from CRM into the AI sounds pretty sweet. i might actually remember to check this when trying to figure out why our lead activity went quiet again. or i'll totally get distracted. either way, solid feature.
Databox
@therayess Thanks, Ammar! Getting distracted is exactly the problem we want to solve. You shouldn't have to remember to go digging. When lead activity drops, the context is already there when you ask, so it takes one question instead of an afternoon of detective work.
First thing I'm connecting is our call recorder. I spend a lot of time listening to customer calls for product feedback, and most of it ends up in transcripts that can be hard to parse. With it connected, I want to build a product feedback dataset in Databox and give it to our GTM teams so they can:
tailor the offer for each customer based on what similar customers told us they needed
see which objections keep coming up, and which answers actually moved deals forward
spot when competitors get mentioned and what people compare us on
find out why deals are won or lost from what was said on the calls, not just the CRM reason field
prep for a call by checking what customers in the same industry cared about most
Sales, CS and product all working from the same view of what customers actually say is the part I'm most excited about.
Excited for all the ways we can go with this - it's almost unlimited in the amount of use cases.
Databox
@zan_perkovic Love this, Žan. The win/loss one stands out most for me. The CRM reason field usually says "price" or nothing at all, and the real reason is buried somewhere in a call. Putting what customers actually said next to the deal data should give GTM a much more honest picture.
Would be great to see this once it's running. If you share how you set it up, it could turn into a template for other teams.
Dash to Cart
honestly, the fact that you can just plug it into any MCP server you want and it figures it out is kinda nuts. like i could see myself setting it up once and then forgetting how it even works, which is my favorite setup tbh.
Databox
@soonkoon Ha, that's the dream setup, Soon. Add the server URL, sign in, and you're done. After that, the AI Analyst works out when to use it on its own. The only reason to come back is if you want to change what it can access.
Databox
I like that the approach is safe. Read access now, write access later, same connection not a separate thing bolted on after. When write tools are unlocked (updating a deal, sending a message) it'll just be an extension of what's already connected.