Skip to main content

ChatGPT just launched on Slack — here’s how to use it

Using ChatGPT in Slack.
Image used with permission by copyright holder

The OpenAI ChatGPT chatbot is now available within the Slack communications platform, making it easier to ask the helpful tool questions or to retrieve information for you. It's in beta, for now, so you'll need to join the waitlist, but if you're already on it, or just want to get ready for when you're given approval, here's how to use ChatGPT on Slack.

Recommended Videos

Difficulty

Easy

Duration

10 minutes

How to sign up for ChatGPT on Slack

Since Slack's ChatGPT application is still in development, it's still considered a beta feature, so you'll have to sign up for the waitlist. Once given approval, you can then start using it within your own Slack workspace.

Step 1: Sign up for the ChatGPT app for Slack waitlist, here.

Step 2: You'll have a better chance of being accepted if you're part of a larger organization, or have some specific use in mind, but personal use is fine too.

Using ChatGPT in Slack.
Image used with permission by copyright holder

How to summarize conversations with ChatGPT on Slack

One of the most useful functions of ChatGPT on Slack is in summarizing conversations, so you can get up to speed with what's been discussed quickly and easily.

Step 1: Open your Slack app or the Slack web app, and select the workspace you want to access. Log in if necessary.

Step 2: Select the channel from the left-hand menu that you want to summarize, and then find the specific conversation thread, if needed.

Step 3: Hover over the conversation so that the reaction menu appears, then select the three-dot menu icon for more options.

Step 4: Select Summarize thread ChatGPT. ChatGPT will then give you a custom-written response that summarizes what has been said in the conversation so far.

How to draft responses with ChatGPT for Slack

ChatGPT can also be used to draft responses to questions or queries you receive.

Step 1: Open your Slack app or the Slack web app, and select the workspace you want to access. Login if necessary.

Step 2: Select the channel or person from the left-hand menu who you received a question from.

Step 3: Hover over the conversation so that the reaction menu appears, then select the three-dot menu icon for more options.

Step 4: Select Draft reply ChatGPT and ChatGPT will create a response for you. You can then edit it and send it when ready.

How to ask ChatGPT questions in Slack

ChatGPT's conversational chatbot is also built into the Slack app, and can answer all the same questions as the Bing and Edge integration.

Step 1: Open your Slack app or the Slack web app, and select the workspace you want to access. Log in if necessary.

Step 2: From the left-hand menu, select the ChatGPT application.

Step 3: Write your question as if you were talking to one of your colleagues, then send the message and wait for the response. It should come fairly quickly.

Jon Martindale
Jon Martindale is a freelance evergreen writer and occasional section coordinator, covering how to guides, best-of lists, and…
How to jailbreak DeepSeek: get around restrictions and censorship
Phone running Deepseek on a laptop keyboard.

DeepSeek is the hot new AI chatbot that has the world abuzz for its capabilities and efficiency of operation -- it reportedly cost just a few million dollars to train, rather than the billions of OpenAI's ChatGPT and its contemporaries. But as sophisticated as DeepSeek is, it's not perfect. Like ChatGPT before it, DeepSeek can be jailbroken, allowing users to bypass content restrictions to have it talk about topics the developers would rather it didn't.

Read more
How DeepSeek flipped the tech world on its head overnight
The DeepSeek website.

DeepSeek, the chatbot made by a Chinese startup that seemingly dethroned ChatGPT, is taking the world by storm. It's currently the number one topic all over the news, and a lot has happened in the past 24 hours. Among other highlights, Nvidia's stock plummeted as a response to DeepSeek; President Donald Trump commented on the new AI; Mark Zuckerberg is assembling a team to find an answer to DeepSeek. Below, we'll cover all the latest news you need to know about DeepSeek.
Nvidia gets hit by the rise of DeepSeek

Although ChatGPT is the chatbot that quickly lost its public favorite status with the rise of DeepSeek, Nvidia is the company that suffered the greatest losses. In fact, Nvidia's market loss following the launch of DeepSeek's large language model (LLM) marks the greatest one-day stock market drop in history, says Forbes. Nvidia lost nearly $600 billion as a result of the Chinese company behind DeepSeek revealing just how cheap the new LLM is to develop in comparison to rivals from Anthropic, Meta, or OpenAI.

Read more
DeepSeek: everything you need to know about the AI that dethroned ChatGPT
robot hand in point space

A year-old startup out of China is taking the AI industry by storm after releasing a chatbot which rivals the performance of ChatGPT while using a fraction of the power, cooling, and training expense of what OpenAI, Google, and Anthropic's systems demand. Here's everything you need to know about Deepseek's V3 and R1 models and why the company could fundamentally upend America's AI ambitions.
What is DeepSeek?
DeepSeek (technically, "Hangzhou DeepSeek Artificial Intelligence Basic Technology Research Co., Ltd.") is a Chinese AI startup that was originally founded as an AI lab for its parent company, High-Flyer, in April, 2023. That May, DeepSeek was spun off into its own company (with High-Flyer remaining on as an investor) and also released its DeepSeek-V2 model. V2 offered performance on par with other leading Chinese AI firms, such as ByteDance, Tencent, and Baidu, but at a much lower operating cost.

The company followed up with the release of V3 in December 2024. V3 is a 671 billion-parameter model that reportedly took less than 2 months to train. What's more, according to a recent analysis from Jeffries, DeepSeek's “training cost of only US$5.6m (assuming $2/H800 hour rental cost). That is less than 10% of the cost of Meta’s Llama.” That's a tiny fraction of the hundreds of millions to billions of dollars that US firms like Google, Microsoft, xAI, and OpenAI have spent training their models.

Read more