Skip to main content

Slack GPT: attend meetings, summarize messages, and more

Sick of attending all those work meetings every day? Slack could soon take care of them for you by sending its own chatbot to summarize what happened. That’s because Slack owner Salesforce has just introduced its own artificial intelligence (AI) tool called Slack GPT, and it could help make your workload a little easier to manage.

According to Slack and Salesforce, Slack GPT aims to bring AI to your day-to-day tasks. That might mean helping you adjust the tone of your messages to suit a certain audience, or automatically drafting emails to send to prospective clients.

A mockup image of Slack's Slack GPT chatbot, showing the Einstein GPT tool suggesting a new sales opportunity.
Salesforce / Slack

This news follows the announcement that Microsoft is bringing ChatGPT to its Teams chat app, and means Slack is joining the deluge of apps racing to integrate AI into their feature sets. So how exactly will Slack GPT work, and what will you be able to do with it?

What will Slack GPT do and how will it work?

A mockup image of Slack's Slack GPT chatbot, showing an option to shorten, elaborate or change the tone of a selected message.
Image used with permission by copyright holder

According to Slack, you’ll be able to do a range of different things with Slack GPT. For one thing, it will summarize message threads that you may have missed, saving you the hassle of having to read through every comment. Salesforce says it will even be able to attend huddles on your behalf and then create a quick recap with all the key points. That could save you the time of manually catching up if you can’t attend in person.

Slack GPT will also help you send the perfect message without having to overthink what you need to say. A quick demo in Slack’s press release shows a user highlighting a paragraph, then choosing from three options: “shorten,” “elaborate,” and “change tone.” After clicking the first option, the message is truncated and still perfectly readable.

If you want to create your own AI prompts, you’ll be able to do that with a tool called Workflow Builder. According to Slack: “Later this year, you’ll be able to instantly bring generative AI into your automated processes in Slack, without a single line of code. With Workflow Builder, our built-in no-code automation tool, you’ll be able to add generative AI prompts as one of the steps in your workflow.”

Finally, Salesforce is aiming to integrate Slack GPT with its own products and features. One idea is to take data about a new lead provided by Salesforce’s Sales Cloud, then automatically create a draft message to send to that lead using Slack GPT.

Slack GPT will let you integrate a large language model (LLM) chatbot from a third party, such as OpenAI’s ChatGPT or Anthropic’s Claude. Salesforce says these chatbots will not be trained on any data fed to them while using Slack. Alternatively, you can import your own custom LLM.

What else is in the pipeline?

Slack can integrate with various apps, and it’ll soon be getting a new one called Einstein GPT. This “lets you surface AI-powered customer insights from trusted Salesforce Customer 360 data and Data Cloud,” according to Slack.

In the future, Einstein GPT might be able to “auto-generate case summaries using relevant data from Service Cloud and your Slack channel,” Slack’s press release states. “Now, case summaries could not only capture data from service tickets, but knowledge from the team who resolved the case too.”

When will Slack GPT be available?

A mockup image of Slack's Slack GPT chatbot, showing a user creating a workflow using Slack GPT's Workflow Builder tool.
Image used with permission by copyright holder

Slack GPT’s features are rolling out piece by piece. Claude is available in Slack right now, while ChatGPT for Slack is in beta. Workflow Builder is coming this summer.

“Slack GPT native AI capabilities and the Einstein GPT app for Slack are in development,” Slack says, and there are no launch dates yet for those features.

Editors' Recommendations

Alex Blake
In ancient times, people like Alex would have been shunned for their nerdy ways and strange opinions on cheese. Today, he…
Why Llama 3 is changing everything in the world of AI
Meta AI on mobile and desktop web interface.

In the world of AI, you've no doubt heard about what OpenAI and Google have been up to. And now, Meta's Llama LLM (large language model) is becoming an increasingly important player in the game, especially with its open-source nature. Meta recently made a big splash with the launch of its Llama 3 AI model, and it's shaken up the field dramatically.

The reasons why are multiple and varied. It's free to use, it has a wide user base, and yes, it's open source, to name but a few. Here's why Llama 3 is taking the AI industry by storm and may shape its future for some time to come.
Llama 3 is really good
We can debate until the cows come home about how useful AIs like ChatGPT and Llama 3 are in the real world -- they're not bad at teaching you board game rules -- but the few benchmarks we have for how capable these AI are give Llama 3 a distinct advantage.

Read more
The best ChatGPT plug-ins you can use
OpenAI's website open on a MacBook, showing ChatGPT plugins.

ChatGPT is an amazing tool, and when they were introduced, plug-ins made it even better. But as of March 2024, they're no longer available as part of ChatGPT, having since been replaced by Custom GPTs, which you can make yourself. Or you can use one of the many amazing options from other developers, AI fans, and prompt engineers.

Interested in learning about how to make the best custom GPT for you? We have a guide for that. If you're more interested in the best custom GPTs available now, we have a guide for that too.

Read more
Apple finally has a way to defeat ChatGPT
A MacBook and iPhone in shadow on a surface.

OpenAI needs to watch out because Apple may finally be jumping on the AI bandwagon, and the news doesn't bode well for ChatGPT. Apple is reportedly working on a large language model (LLM) referred to as ReALM, which stands for Reference Resolution As Language Modeling. Made to give Siri a boost and help it understand context, the model comes in four variants, and Apple claims that even its smallest model performs on a similar level to OpenAI's ChatGPT.

This tantalizing bit of information comes from an Apple research paper, first shared by Windows Central, and it appears to be an early peek into what Apple has been cooking for a while now. ReALM is Apple's own LLM that was reportedly made to enhance Siri's capabilities; these improvements include a greater ability to understand context in a conversation.

Read more