🔥Building a Slack Bot with AI Capabilities - From Scratch! Part 1/4: Slack App and Events🔥

aka, "can an AI do my work for me please?"

This blog series focuses on presenting complex DevOps projects as simple and approachable via plain language and lots of pictures. You can do it!

This article is part of a series of articles, because 1 article would be absolutely massive with all parts.

• Part 1 (this article): Covers how to build a slack bot in websocket mode

• Part 2: How to deploy an AWS Bedrock AI resource and connect to it to ask a request locally from your terminal with python3

• Part 3: We’ll connect our slack bot with Bedrock locally using python3 with ngrok so slack users can have conversations with AI

• Part 4: How to convert your local script to an event-driven serverless, cloud-based app in AWS Lambda

Hey all!

I have been chatting with AIs daily - GitHub Copilot is fantastic for writing code, and ChatGPT is great for initial ideas (and therapy?!) and writing things from templates, like a lot of my “there is a new post” on LinkedIn. Sure, they hallucinate sometimes, but most of the information I get from them are fantastic.

However, at work, we are banned from using general purpose AIs. We’re in the healthcare space, so uploading any data to ChatGPT is not only out of compliance, it could be criminally illegal. So that’s a bit scary.

However, AI is powerful. I want to bring it in house!

In this walk-through we’ll build a Slack App that we’ll run locally on our computer in socket mode, and when folks message it, it’ll relay that question to GitHub models, which is using AWS Bedrock general intelligence, to respond. The response is posted right into slack in whichever room the request came from!

This will be part of a series where we build out a general intelligence AI bot that can integrate with other data stores, customizations, and help contextualize messages in slack.

Primarily, I want to build a generally intelligent bot that can assist folks with understanding logs, contextualizing any information across the slack instance. In the future, I plan to add other data sources for additional contextualization of logs, and working towards automating some of the DevOps and SRE functions at work.

Lets go build it!