I’ve been thinking a lot about how to help my family, friends, and colleagues use LLMs to power their work. (As I’ve written about here, and more recently here with lots of tips on prompting and effectively using LLMs for different kinds of projects). 

Scott has been on the same page, especially thinking about how to help colleagues use LLMs effectively, but taking a slightly different approach: he built a Slackbot (a bot for Slack) which uses GPT-3.5 and GPT-4 to answer questions. This uses the API of GPT but presents it to the user in Slack instead of having to use ChatGPT as the chat interface. So, it’s a LLM chatbot, different than ChatGPT (because it’s a different chat interface), but uses the same AI (GPT-3.5 and GPT-4 from OpenAI). You could implement the same idea (a chat-based bot in Slack) using different AIs/LLMs, of course.

Using a slack-based bot for an LLM achieves a couple of things:

1. More people can try GPT-4 and compare it to GPT-3.5 to get a taste for prompting and responses, without having to pay $20/month for a ChatGPT Pro account to get access to GPT-4.
2. If you spend a lot of time in Slack for work, you don’t have to switch windows to access GPT.
3. If your employer doesn’t want you to use the ChatGPT consumer product for work due to security concerns, but is more comfortable with OpenAI’s confidentiality guarantees for their API, a Slack bot interface provides a more secure alternative.
4. You can see “in public” how other people in your Slack workspace are using it, and learn from their prompts and interactions new tricks and ideas (in addition to reading my long post here with lots of tips and suggestions).
5. You can privately (in DM by yourself) talk to the bot and ask it your “dumb” questions (which aren’t dumb), and you can reason through things at your own speed or learn how to do things that you haven’t done before, and do so in private just like if you had your own ChatGPT account. It doesn’t burn social capital or take other people’s time, which you can save for more nuanced questions.

Scott has implemented it for work, but also came up with another fun use for it: we created a family-focused Slack channel for kids in our lives (we have ten (!) nieces and nephews – you can see how I used GPT to help with special custom books for some of them recently) so their parents and they can access GPT in a safe environment, too. ChatGPT (and OpenAI’s GPT API) have some reasonable safeguards in it already to protect kids, but more usefully we want to be able to provide custom instructions to keep it always at a kid-focused level. Plus this way we can share the experience with them, too.

I asked the bot to summarize itself for a lay audience not familiar with the project, and this was the output:

### Summary of the SlackAskBot

The SlackAskBot is a smart assistant designed to operate within Slack, a popular communication platform used by teams for messaging and collaboration. Imagine having a helpful robot in your group chats or direct messages that can understand your questions and provide informative responses. That’s what the SlackAskBot does. It’s like adding a knowledgeable team member to your Slack workspace who is always ready to assist.

#### How It Works:

1. **Integration with Slack:**

– The bot is integrated into Slack, meaning it can read messages in channels it’s added to or when directly messaged. It’s like inviting a friend into your group chat who can listen and respond to conversations.

2. **Understanding Messages:**

– When you type a message that includes the bot (either by mentioning it with an @ symbol in a channel or by sending it a direct message), the bot pays attention. It’s designed to understand that you’re talking to it and that you’re expecting some form of response.

3. **Processing Your Requests:**

– Once the bot receives a message, it doesn’t just look at the latest message you’ve sent. It considers the context by looking at the conversation history. This way, it can provide responses that make sense within the ongoing discussion. It’s akin to a human joining a conversation, where understanding the previous discussion points is crucial for making relevant comments.

4. **Generating Responses:**

– The bot uses a powerful language model (think of it as a very advanced AI that understands and generates human-like text) to come up with responses to your messages. It’s as if the bot thinks about what you’ve asked and then crafts a reply that aims to be helpful and informative.

5. **Interacting Back:**

– After thinking through your message and generating a response, the bot then sends this response back into the Slack channel or direct message. You’ll see its reply just like you would from any other team member, providing the information or assistance you requested.

6. **Special Features:**

– The bot is designed with specific settings for different channels or direct messages. This means it can tailor its responses based on where it’s talking. For example, it might respond differently in a casual chat compared to a more formal project discussion channel.

7. **Respecting Privacy and Permissions:**

– The bot is programmed to respect Slack’s rules and the privacy of your conversations. It only listens and responds to messages where it’s explicitly mentioned or directly messaged, ensuring that it doesn’t intrude on private discussions.

#### In Summary:

The SlackAskBot acts as a virtual assistant within your Slack workspace, ready to provide information and answers to your questions. It’s designed to understand the context of conversations, generate helpful responses, and interact with users in a way that enhances team communication and productivity. Whether you’re asking for quick facts, seeking advice on a project, or just interacting for fun, the SlackAskBot is there to make your Slack experience more informative and engaging.

—
The SlackAskBot is open source – you can check out the code and instructions for how to implement it in your own Slack environment in the repository here.