How can I be sure that the information shared with the tool is safe?
Report
@busmark_w_nika Tadata doesn't train on your data, and neither do our model providers. Each organization’s data is isolated, work runs in temporary containers, and credentials are deleted when you revoke a connection. Data is encrypted in transit and at rest, and we’ve passed Google’s CASA Tier 2 assessment.
The connectors part is awesome! I liked it depth, one of the most thought-through I've seen. good job folks!
Btw- can you share where does this different than Claude tags?
Report
@amit_aviram Tadata's focus is the quality of the finished work, we actually want you to read what it writes. it asks when context is missing, adapts to how your team works, and creates usable deliverables instead of dropping generic AI slop into Slack. We also never train on customer data.
Report
With the short and crisp answers, and ability to give instructions in Slack, feels more seamless than other Slack bots!
We believe people should be able to do more with AI without having to learn how to build agents.
You should be able to delegate to AI like a teammate: tell it what you need, give feedback, and let it figure out the rest.
That’s Tadata.
It lives in Slack and is especially good at sales work today. Lead finding is one of my favorite examples: I can describe exactly who I’m looking for and Tadata researches across our internal tools and harder-to-reach sources like LinkedIn or Google Maps. If the results aren't right, I just reply with what to change.
I’m not choosing data providers, wiring together tools, or building a research agent. I’m just delegating the job. Tadata puts the system together underneath.
And as I work with it, Tadata learns how my company works and builds shared context that makes future work better.
We came to this from the infrastructure side. Our team created FastAPI-MCP, which grew to 12K GitHub stars and 70M+ downloads. We knew how to give agents tools, but having access to tools is very different from having an AI teammate you can actually rely on.
So we’re excited to launch Tadata and hear what you think!
P.S. Yes, Tadata helped us with nearly every part of this launch ;)
the delegation pitch is appealing but what's the failure mode - if Tadata researches a lead and gets something confidently wrong (stale data, wrong company, a hallucinated detail), does it flag its own uncertainty, or does that just show up as a normal Slack message and get treated as ground truth by whoever asked?
Report
@galdayan Great question! If Tadata isn't certain it will ask the user and remember the preferences, when the answer is more complex than a simple slack message it'll create a deliverable like an attachment or a google doc/sheet where it can also detail things like process and level of confidence. like any AI agent, it can still be confidently wrong from time to time, we encourage users to read and validate results, just like you would with your human employees
minimalist phone: reduce your screentime
@busmark_w_nika Tadata doesn't train on your data, and neither do our model providers. Each organization’s data is isolated, work runs in temporary containers, and credentials are deleted when you revoke a connection. Data is encrypted in transit and at rest, and we’ve passed Google’s CASA Tier 2 assessment.
You can read more at https://tadata.com/security
That's a really nice tool tbh.
The connectors part is awesome! I liked it depth, one of the most thought-through I've seen. good job folks!
Btw- can you share where does this different than Claude tags?
@amit_aviram Tadata's focus is the quality of the finished work, we actually want you to read what it writes. it asks when context is missing, adapts to how your team works, and creates usable deliverables instead of dropping generic AI slop into Slack. We also never train on customer data.
With the short and crisp answers, and ability to give instructions in Slack, feels more seamless than other Slack bots!
Tadata
Hi everyone 👋 I’m Tori, co-founder of Tadata.
We believe people should be able to do more with AI without having to learn how to build agents.
You should be able to delegate to AI like a teammate: tell it what you need, give feedback, and let it figure out the rest.
That’s Tadata.
It lives in Slack and is especially good at sales work today. Lead finding is one of my favorite examples: I can describe exactly who I’m looking for and Tadata researches across our internal tools and harder-to-reach sources like LinkedIn or Google Maps. If the results aren't right, I just reply with what to change.
I’m not choosing data providers, wiring together tools, or building a research agent. I’m just delegating the job. Tadata puts the system together underneath.
And as I work with it, Tadata learns how my company works and builds shared context that makes future work better.
We came to this from the infrastructure side. Our team created FastAPI-MCP, which grew to 12K GitHub stars and 70M+ downloads. We knew how to give agents tools, but having access to tools is very different from having an AI teammate you can actually rely on.
So we’re excited to launch Tadata and hear what you think!
P.S. Yes, Tadata helped us with nearly every part of this launch ;)
Permit.io
Great positioning. Love to see fastapi-mcp progress into a slick product and a smooth experience. Good luck, team!
Dial
the delegation pitch is appealing but what's the failure mode - if Tadata researches a lead and gets something confidently wrong (stale data, wrong company, a hallucinated detail), does it flag its own uncertainty, or does that just show up as a normal Slack message and get treated as ground truth by whoever asked?
@galdayan Great question! If Tadata isn't certain it will ask the user and remember the preferences, when the answer is more complex than a simple slack message it'll create a deliverable like an attachment or a google doc/sheet where it can also detail things like process and level of confidence. like any AI agent, it can still be confidently wrong from time to time, we encourage users to read and validate results, just like you would with your human employees