Big Claude Tag fan, and see this being an incredibly accessible way to set up without relying on Anthropic and being model-agnostic and eventually can run on local models my company is using.
Does Tadata require me to tag it or will it be able to decide when to jump in?
@zach_gold Exactly. This way you can use open source models and have your company knowledge and how-to stored in a model-agnostic way.
Model providers are naturally incentivized to keep every task on their own models and encourage higher token usage, even when another model is a better fit for the task. At Tadata, our incentive is simply to get you the best result for the cost.
Right now you have to tag Tadata for it to jump in. Or DM it directly.
@tori_seidenstein Makes a ton of sense, especially the encouraging higher token usage! Curious if a future feature could be team can configure thinking to use more expensive models then cheaper ones on execution. Overall, super cool product!
@zach_gold Yes, 100%. We believe that in the future, we'll just need the expensive model to do the hard work of figuring out the task for the first time, and then can use something cheaper (or even deterministic code) for future runs.
Report
@zach_gold you need to tag Tadata for it to join a conversation, that's an explicit decision based on other experiences to avoid spamming the workspace. when we feel confident that Tadata can join the conversation without creating noise we'll add that option
@a_c26 Both are AI employees that live in Slack but have a different feel that is the culmination of a bunch of different product decisions. Tadata is designed to be very concise for example, like an employee that gives you the bottom line up front.
Tadata also excels out of the box in go-to-market tasks that require lots of web data.
It also doesn't introduce itself to your colleagues without permission, which is the biggest thing Viktor has been critiqued for.
And yes, you can connect it to Shopify!
Report
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?
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.
I saw that you guys have a slide labeled "No Slop". Really interesting because I find that AI agents typically are too verbose. On Tadata, can we control how verbose it is?
@matteo8p By default, all Tadata responses will be concise. If you ask for something that requires detail to convey the value (e.g. a research report or a big list of leads) that will be given to you in an artifact format -- a markdown file or CSV for example.
We're looking at how to control writing style and verbosity though for cases where the task is writing. For example, how does Tadata craft a follow-up email for Sam that matches Sam's style, and a follow-up email for Devin that matches Devin's style?
So, good question!
Report
With the short and crisp answers, and ability to give instructions in Slack, feels more seamless than other Slack bots!
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.
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 ;)
Portal
Big Claude Tag fan, and see this being an incredibly accessible way to set up without relying on Anthropic and being model-agnostic and eventually can run on local models my company is using.
Does Tadata require me to tag it or will it be able to decide when to jump in?
Tadata
@zach_gold Exactly. This way you can use open source models and have your company knowledge and how-to stored in a model-agnostic way.
Model providers are naturally incentivized to keep every task on their own models and encourage higher token usage, even when another model is a better fit for the task. At Tadata, our incentive is simply to get you the best result for the cost.
Right now you have to tag Tadata for it to jump in. Or DM it directly.
Portal
@tori_seidenstein Makes a ton of sense, especially the encouraging higher token usage! Curious if a future feature could be team can configure thinking to use more expensive models then cheaper ones on execution. Overall, super cool product!
Tadata
@zach_gold Yes, 100%. We believe that in the future, we'll just need the expensive model to do the hard work of figuring out the task for the first time, and then can use something cheaper (or even deterministic code) for future runs.
@zach_gold you need to tag Tadata for it to join a conversation, that's an explicit decision based on other experiences to avoid spamming the workspace. when we feel confident that Tadata can join the conversation without creating noise we'll add that option
Portal
@itay_shemer1 Makes a ton of sense to start with!
Hi @tori_seidenstein How does Tadata, compare to Viktor for example? Also can I connect it to Shopify?
Tadata
@a_c26 Both are AI employees that live in Slack but have a different feel that is the culmination of a bunch of different product decisions. Tadata is designed to be very concise for example, like an employee that gives you the bottom line up front.
Tadata also excels out of the box in go-to-market tasks that require lots of web data.
It also doesn't introduce itself to your colleagues without permission, which is the biggest thing Viktor has been critiqued for.
And yes, you can connect it to Shopify!
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.
@itay_shemer1 sounds cool.
Adapt
I saw that you guys have a slide labeled "No Slop". Really interesting because I find that AI agents typically are too verbose. On Tadata, can we control how verbose it is?
Tadata
@matteo8p By default, all Tadata responses will be concise. If you ask for something that requires detail to convey the value (e.g. a research report or a big list of leads) that will be given to you in an artifact format -- a markdown file or CSV for example.
We're looking at how to control writing style and verbosity though for cases where the task is writing. For example, how does Tadata craft a follow-up email for Sam that matches Sam's style, and a follow-up email for Devin that matches Devin's style?
So, good question!
With the short and crisp answers, and ability to give instructions in Slack, feels more seamless than other Slack bots!
Tadata
@jisha_kambo1 Thank you!
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
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 ;)