Last week I was presenting introductory session on Platform engineering and self-service portal. One interesting question was about to use of AI assisted platform engineering. Surely CoPilot and such tools are already making good noise in leaderships discussions. Do we have stock of tools and platforms who blends well in Generative AI as well as in platform engineering space focusing on developer experiences and platform engineering ?

When someone says AI Assisted, it opens up a vast range for me. Will you ever trust AI to configure your production, maybe not. Will you trust AI to build you architecture, maybe in an assistant role. But one thing I find really interesting about generative AI and that is reporting. Understanding complex logs and data structures and then putting up a conversational interface to that, will reduce a lot of efforts when you want to ingest reports. I am sure there are other use cases where it will be as useful, but I recently saw AI based reporting in https://facets.cloud and it looked like a really neat thing to have for our clients.

@Vivek Dwivedi 100% agree! in reporting this will make a huge impact

@mohit kalra Shameless plugin but i only do that since it directly responds to your question. Kubiya.ai uses LLMs to understand the context of devops requests and answer questions based on your knowledge systems, as well as generative AI and prompt engineering to create DevOps workflows and even run native queries. Outofdevops created this short overview:

My company has been trying out the utility of LLMs in the platform engineering space and our current takeaway is that yes, they have some utility, but they are not yet production ready. For example, using GPT4 to define a Terraform to deploy a containerized application on AWS is possible, and you can readily get a good starter template, but you will quickly discover that pieces are missing or deprecated commands and functions are being called. If you are comfortable creating a Terraform template on your own, GPT4 will absolutely save you time in getting a reasonable 'boilerplate' template pulled together, but you will still need to tune it to get it to do what you want. There is potential there, though I am not sure that the "chat" model is really the best interface for platform engineering tasks.