Creating a Slack Bot with Replit Assistant and Bolt (Part I)

Learn how to prompt Replit Assistant, an advanced AI-coding assistant, to create your first Slack bot with Bolt, a framework for building Slack apps with Python (or JavaScript). Part I covers forking a Slack bot project template, the anatomy of a basic Slack bot, personalization of Replit Assistant, and prompting techniques for Replit Assistant.

For many fully remote and hybrid workplaces, ideas, thoughts, and work circulate through the “digital headquarter” Slack. With tens of millions of daily active users and over seventy of the Fortune 100 using Slack, Slack has evolved from a simple messaging application to a collaborative, communication platform where teams can build custom workflows and integrations to automate everyday tasks, streamline operations, and bring context into conversations. To build an integration (a “Slack app”) like a Slack bot, developers can use Bolt, Slack’s official framework that offers a simple API for listening for and responding to messages, events, and shortcuts in a Slack workspace. Creating these integrations has become even more accessible with fully-featured, cloud-based, development environments like Replit. Using Replit Assistant, an AI assistant automatically handles everything from setup to coding to deployment, allowing you to focus on fleshing out the bot’s features at a product-level rather than wrestling with low-level implementation details in code and infrastructure.

This comprehensive guide will demonstrate how you can create a Slack bot from scratch with Replit Assistant and Bolt (for Python). Specifically, you will be building a Slack bot that monitors a Slack channel for the custom slash command 

 slash command with a query, the Slack bot will search through the connected Google account’s Google Drive documents and return a message that lists the relevant files (whose names match the query) back to the origin Slack channel. Additionally, if the Slack bot detects any activity that affects documents inside of the connected Google account’s Google Drive (e.g., new uploads, modified documents, etc.), then the Slack bot will send a notification to alert members of the Slack channel of such activity.

How do you get started with building a Slack bot on Replit?

To get started with building a Slack bot on Replit, first log into your Replit account. If you don’t already have a Replit account, then sign up for one - it’ll only take a few minutes. Then, visit the 

 and click the “Remix template” button.

Upon clicking the “Remix template” button, a modal pops up that asks you to enter the name and a description for this new project. In this case, let’s name it “Google Drive Notification Slack Bot” and provide the description “A Slack bot that sends notifications to a dedicated Slack channel anytime a team member uploads a new file/folder to, or deletes or edits an existing file/folder in a linked Google Drive account.” For privacy, select the default “Public” option (you can only choose the “Private” option if you are subscribed to the Replit Core plan). The “Public” option makes the project visible to anyone on the web, as well as allows them to fork (”remix”) your project, which is perfectly fine for this guide. Once all of the required fields have been filled out, click the “Use Template” button.

Replit redirects you to a new project with all of the template’s project files. Additionally, Replit provisions the project environment and installs the project dependencies. Feel free to follow along Replit’s onboarding steps to learn about the features available in the project workspace.

How do you create a basic Slack bot with Bolt for Python?

Creating a basic Slack bot with Bolt for Python requires just 12 lines of code. You'll need to:

The following simple implementation creates a Slack bot that listens for messages that mention it in the Slack channel the it is installed in. Anytime there’s the Slack bot is mentioned, the Slack bot responds with a message that greets the user who mentioned the Slack bot: “Hi there, @<USERNAME_OF_MESSAGE_SENDER>!”  

import logging
import os

from slack_bolt import App
from slack_bolt.adapter.socket_mode import SocketModeHandler

app = App(token=os.environ["SLACK_BOT_TOKEN"])
logging.basicConfig(level=logging.DEBUG)

@app.event("app_mention")
def event_test(event, say, logger):
  say(f"Hi there, <@{event['user']}>!")

  logger.info(event)

if __name__ == "__main__":
  SocketModeHandler(app, os.environ["SLACK_APP_TOKEN"]).start() 

This example can be expanded with additional event listeners, slash commands, or interactive components, which can be found in the 

How do you prompt Replit Assistant to create a Slack bot?

I. Personalize Replit Assistant with a custom prompt.

To make Replit Assistant aware of the project context (in case it cannot be readily inferred from the project files) and provide better responses to your prompts, you can personalize Replit Assistant with a custom prompt, much like a system prompt.

In the left-side pane, under the “Assistant” tab, click on the gear icon on the upper right side of the pane. This brings up the Replit Assistant’s settings.

Under the “Assistant Prompt” section, click the gear icon next to the default prompt. In the modal that pops up, click on the “+ Add new prompt” button.

For this new prompt, title it “Bolt for Python Project.” For the prompt, enter in the following:

You are developing a Slack bot with this Bolt for Python project.

When providing code, focus on Slack app and Bolt-specific implementation details. Prioritize and use Bolt for Python features and APIs, when possible. 

Adapt your responses with respect to this context.

Once all of the required fields have been filled out, press the “Save” button.

Now you can select this prompt from the dropdown of available prompts that you can choose to personalize Replit Assistant with.

II. Give a concise, one-sentence description of the Slack bot.

In the prompt that’s provided to Replit Assistant, the first sentence should explicitly state that you want to create a Slack bot. Additionally, it should describe the Slack bot’s purpose and core functionality.

For example, for a Slack bot that sends notifications of Google Drive events to a Slack channel:

**Create a Slack bot that sends notifications to a dedicated Slack channel anytime a team member uploads a new folder/file to, or deletes or edits an existing folder/file in a linked Google Drive account.**


If you have trouble coming up with a concise, one-sentence description, then you can prompt Claude AI or ChatGPT with the following:

Give a concise description for the following task:

"<DESCRIPTION>"

 with the task you want to describe concisely, and copy and paste the description into Replit Assistant’s chat interface.

III. Provide a list of features the Slack bot should support.

After adding a one-sentence description of the Slack bot to the prompt, add a detailed list of any features that the Slack bot should support. The more items that describe how the Slack bot should behave, the more likely that Replit Assistant will generate exactly what you’re looking for. Being specific about functionality, user interactions, and expected behaviors helps Replit Assistant understand your vision and translate it into functional code.

Create a Slack bot that sends notifications to a dedicated Slack channel anytime a team member uploads a new file/folder to, or deletes or edits an existing file/folder in a linked Google Drive account.

**The Slack bot should support the following functionality:

1. The Slack bot posts a message to a Slack channel anytime an event occurs in the Google Drive account. The events to listen for include: file/folder creation, file/folder deletion, and file/folder modification/editing. The message that's sent to the Slack channel mentions the name of the file/folder, the event that occurred, and a link to the file/folder (no link if the file/folder was deleted). Prefix the name of the file/folder with an emoji that represents the type of resource it is - prefix a text-based file (e.g., PDFs, TXTs, DOCXs, etc.) with a document emoji, prefix an image-based file (e.g., PNGs, JPGs, etc.) with a picture emoji, and prefix a folder with a folder emoji.

2. When the user sends a slash command (`/search-drive`) that's followed by a string of text, the Slack bot will search the Google Drive account for a file/folder whose name best matches the query (the string of text). The Slack bot will post a message with a list of the files/folders whose names best matched the query, as well as links to them.**

IV. Specify technologies (e.g., languages, libraries, frameworks, tools, and APIs) to use and design principles to follow.

After adding a detailed list of features that the Slack bot should support to the prompt, enrich the prompt by mentioning any specific technologies that should be used and the design principles to follow. This ensures that Replit Assistant understands not just what to build, but how to build it according to your technical and design preferences. 

For example, for a Slack bot that sends notifications of Google Drive events to a Slack channel: 

Create a Slack bot that sends notifications to a dedicated Slack channel anytime a team member uploads a new file/folder to, or deletes or edits an existing file/folder in a linked Google Drive account.

The Slack bot should support the following functionality:

1. The Slack bot posts a message to a Slack channel anytime an event occurs in the Google Drive account. The events to listen for, **via push notifications provided by the Google Drive API (use the `google-api-python-client` Python library)**, include: file/folder creation, file/folder deletion, and file/folder modification/editing. The message that's sent to the Slack channel mentions the name of the file/folder, the event that occurred, and a link to the file/folder (no link if the file/folder was deleted). Prefix the name of the file/folder with an emoji that represents the type of resource it is - prefix a text-based file (e.g., PDFs, TXTs, DOCXs, etc.) with a document emoji, prefix an image-based file (e.g., PNGs, JPGs, etc.) with a picture emoji, and prefix a folder with a folder emoji.

2. When the user sends a slash command (`/search-drive`) that's followed by a string of text, the Slack bot will search the Google Drive account for a file/folder whose name best matches the query (the string of text). The Slack bot will post a message with a list of the files/folders whose names best matched the query, as well as links to them.

**Implement the Slack bot with Python and Slack's official framework, Bolt for Python (`slack_bolt`).**

V. Enter the final prompt into Replit Assistant and build the initial prototype of the Discord bot.

Once the prompt has been finalized, enter the prompt into Replit Assistant. It will…

Once Replit Assistant finishes proposing all of the changes it would make to the project, you can either click the “Apply all” button or make suggestions to the proposal. Upon reviewing the proposal made by Replit Assistant, you will notice that, under the list of secrets that Replit Assistant wants to add to the Replit environment, Replit Assistant wants you to add a 

 file in the project with your Google service account’s private key. Since the project is publicly visible for those enrolled in the free tier, this is not an option for security reasons. Therefore, because Replit secrets (environment variables stored in Replit) are not exposed in publicly visible projects, you will want to instruct Replit Assistant to instead store the contents of the Google service account’s private key in a Replit secret.

Now that Replit Assistant has updated its proposal with this correct approach, click the “Apply” button to apply the proposed change.

However, you will notice that clicking the “Apply” button only applies the most recent proposed change of adding the Replit secrets 

. You will need to instruct Replit Assistant to apply the previous proposed changes, which included installing required dependencies like 

Replit Assistant will install the proposed dependencies and modify existing (and introduce new) project files accordingly.

Once completed, Replit Assistant will create a checkpoint. In the right-side pane, you can review the many changes made to 

, from creating a credentials instance and a resource for interacting with the Google Drive API to spinning up a Flask server with an endpoint for handling a Google Drive webhook (on a separate thread).

In the next part of this series (stay tuned!), you will learn how to obtain the necessary tokens and credentials for running the Slack bot. Plus, you will learn how to run a Slack bot with a Flask application (running on a separate thread) that listens for notifications about file changes in the connected Google account’s Google Drive via a webhook.

AUTHOR

Ken Chan

Set up a Django App to Respond to S3 Events on AWS Lambda

 I'm going to show you how to set up your Django app to respond to S3 events on AWS Lambda. The tool we're using to get Django running on AWS Lambda is 

. Follow along to see how responding to events works with this setup. ...

When running your Django app on AWS Lambda using Zappa, it's easy to send and receive events from 

Let's configure our Django with Zappa project to detect when new files are uploaded to an S3 bucket.

You'll need a Django project configured with Zappa. You can create a Django project, then follow the guide for 

Once your project is set up properly, log into the AWS console and create an S3 bucket with a unique name. The bucket won't need public access for this tutorial since we'll upload files directly using the AWS console. Once the bucket is ready, click on 'Properties' and record the 

At the root of your project, create a new file called 

. In this file, we'll add the handler function that will accept all our S3 events. When AWS invokes your function, two objects are passed in: the 

 contains metadata about the invocation, function, and execution environment.  

# aws_events.py

import json


def s3_bucket_event(event, context):
    print(
        "Received event: "
        + json.dumps(event, indent=2)
    )

Our event handler code above prints out the 

Finally, we need to tell Zappa to register our event handler function with AWS so that AWS can start sending events.

"events": [
    {
        "function": 
         "YOUR_APP_NAME_HERE
          .aws_events
          .s3_bucket_event",
        "event_source": {
            "arn": 
              "YOUR_S3_BUCKET_ARN_HERE",
            "events": [
                "s3:ObjectCreated:*"
            ]
        }
    }
]

With all the changes saved, go ahead and push these changes to the cloud.

In order to see the event details that our code prints out, let's activate the Zappa console log. You can do this by running:

This gets Zappa to show you what your Django project is printing. Leave it up and running and remember you can exit anytime by pressing 

Head back over to your AWS console and find your S3 bucket page. Under the 

 tab, find the upload button. Go ahead and upload a file. Any file will do, but it's best to send a smaller one for expediency.

After a few seconds, you should see in the terminal window the full event information from S3. It should look something like the following:

[1622565816462] [DEBUG] 
2021-06-01T16:43:36.462Z 21aefbe9-0f48-
438e-b62d-9657be31e99c 
Zappa Event: {'Records': [{
'eventVersion': '2.1', 
'eventSource': 'aws:s3', 'awsRegion': 
'us-east-1', 'eventTime': 
'2021-06-01T16:43:28.948Z', 'eventName':
'ObjectCreated:Put', 'userIdentity': 
{'principalId': 
'AWS:AIDAQ5B2WBSQXTDZ3SBP6'},  
{'s3SchemaVersion': '1.0', 
'configurationId': 
'newline-zappa-course-dev:aws_events
.s3_bucket_event', 
'bucket': 
{'name': 'newline-upload-bucket', 
'ownerIdentity': 
{'principalId': 'A3BGW0C0R9XGAY'}, 
'arn': 
'arn:aws:s3:::newline-upload-bucket'}, 
'object': {'key': 'testfile.jpg', 
'size': 264671, 'eTag': 
'7792fa0fcecf407e15bd79099d8ba88c', 
'sequencer': '0060B663B63D9DD2ED'}}}]}
[1622565816463] Received event: {
[1622565816463] "Records": [
[1622565816463] {
[1622565816463] "eventVersion": 
"2.1",
[1622565816463] "eventSource": 
"aws:s3",
[1622565816463] "awsRegion": 
"us-east-1",
[1622565816463] "eventTime": 
"2021-06-01T16:43:28.948Z",
[1622565816463] "eventName": 
"ObjectCreated:Put",
[1622565816463] "userIdentity": {
[1622565816463] "principalId": 
"AWS:AIDAQ5D2WBSQXTDZ3SBP6"
[1622565816463] },
[1622565816463] "configurationId": 
"newline-zappa-course-dev:
 aws_events.s3_bucket_event",
[1622565816463] "bucket": {
[1622565816463] "name": 
"newline-upload-bucket",
[1622565816463] "ownerIdentity": {
[1622565816463] "principalId": 
"A3DGW0C0R9XGAY"
[1622565816463] },
[1622565816463] "arn": 
"arn:aws:s3:::newline-upload-bucket"
[1622565816463] },
[1622565816463] "object": {
[1622565816463] "key": "testfile.jpg",
[1622565816463] "size": 264671,

A few things to note here. The filename is 

. Of course, your file and bucket will be named differently. Also note the formatting is a little wonky, but still readable.

You can try uploading a few more files. Maybe try two or three at once. You'll see each upload handled by your Django project as independent events.

At this point, we have many options. Maybe your app will create a thumbnail if an image was uploaded. Or scan a document for keywords. Alternatively, your app might send an email to the client that uploaded the file confirming the receipt of the file.

To dive in even more into setting up your Python apps to run serverless on AWS Lambda, check out our latest course,

The newline Guide to Serverless Django with Zappa. 

Learn

The newline Guide to Building Your First GraphQL Server with Node and TypeScript

Teach

Amelia Wattenberger

Author of Fullstack D3

Community

Tutorials on Python

Creating a Slack Bot with Replit Assistant and Bolt (Part I)

Set up a Django App to Respond to S3 Events on AWS Lambda

This has been a really good investment!

Advance your career with newline Pro.

Email Newsletter

Popular Topics

Masterclasses

Tutorials

Fullstack React with TypeScript