Introduction

• playground  You can see the demo code on the playground.

Set up a fully functional Slack Agent powered by OpenAI’s GPT model quickly using the Agentica CLI. This agent lets you interact with Slack—sending messages, managing channels, and more—with natural language commands.

Quick CLI Setup

Launch the Agentica Setup Wizard with a single command:

npx agentica start slack-agent

The wizard guides you through:

• Installing required packages (e.g., [email protected])
• Choosing your package manager and project type
• Selecting the SLACK controller
• Entering your OPENAI_API_KEY

Once complete, Agentica automatically generates your code, creates a .env file, and installs all dependencies.

Generated Code Overview

The generated code looks like this:

import { Agentica } from "@agentica/core";
import typia from "typia";
import dotenv from "dotenv";
import { OpenAI } from "openai";
 
import { SlackService } from "@wrtnlabs/connector-slack";
 
dotenv.config();
 
export const agent = new Agentica({
  model: "chatgpt",
  vendor: {
    api: new OpenAI({
      apiKey: process.env.OPENAI_API_KEY!,
    }),
    model: "gpt-4o-mini",
  },
  controllers: [
    {
      name: "Slack Connector",
      protocol: "class",
      application: typia.llm.application<SlackService, "chatgpt">(),
      execute: new SlackService(),
    },
  ],
});
 
const main = async () => {
  console.log(await agent.conversate("What can you do?"));
};
 
main();

This code instantly sets up your Slack Agent to interact with Slack via the provided functions.

Slack API Setup

Before running your agent, configure your Slack API credentials:

1. Create a Slack App:

   • Visit Slack API: Applications  and create a new application.
   • Add the recommended scopes (e.g., channels:read, chat:write, users:read, etc.) to enable the functions used in this implementation.

2. Obtain Credentials:

   • After setting up your app, obtain your Secret Key (and other credentials if needed) and add it to your environment variables.

3. Set Up Environment Variables:

   • Create or update your .env file with:

   OPENAI_API_KEY=your-openai-api-key
   SLACK_SECRET_KEY=your-slack-secret-key

What This Does

With this configuration, the Slack Agent can:

• Interact with Slack: Use the SlackService connector to send messages, manage channels, and more.
• Leverage OpenAI’s GPT Model: Process natural language commands for intelligent interactions.
• Maintain Type Safety: With typia.
• Securely Manage Credentials: Using environment variables with dotenv.

Available Functions

For a complete list of available functions in SlackService, refer to the source code:
👉 SlackService.ts 

Appendix: Integrating Your Agent as a Slack Bot

To fully integrate your agent as a Slack bot that responds to mentions and events, follow these additional steps:

Complete Your Slack App Configuration

1. Event Subscriptions:

   • In your Slack app settings, enable Event Subscriptions.
   • Provide your Request URL. (Use a service like ngrok if testing locally.)
   • Ensure your server responds with the required challenge parameter for verification.

2. Subscribe to Bot Events:

   • Under Subscribe to Bot Events, add events such as app_mention to ensure your agent receives messages when mentioned.

3. Customize Bot Identity:

   • Optionally, update your bot’s display name and icon under App Home to personalize its presence in Slack.

Interacting with Your Slack Bot

Once integrated, you can interact with your agent by mentioning it in a channel:

@your_bot_name Send a welcome message to the #general channel.

Your agent will process the message using its Slack connector functions and respond accordingly.

Security Note:
This example is for demonstration purposes. Always handle your Slack API credentials securely and follow best practices in production environments.

Your AI-powered Slack Agent is now ready for automated, intelligent Slack interactions. Enjoy streamlining your Slack workflows! 🚀