Kubiya is a conversational AI-powered internal developer platform where we can consume DevOps services simply by conversing with their personal DevOps assistant, Kubi. Here in this blog, we will dive deep into the amazing contribution of Kubiya in the world of Development in DevOps through LLMs saving up a lot of time and money.
We have been witnessing an age of Artificial Intelligence where LLMs (Large language models) have been replacing and performing works much efficiently at huge scale which wasn't even possible to be thought about. Most of their tasks were limited to designing, chatbots, video editing, language models, web development and frontend. Kubiya extended this adaptability and efficiency to take over the DevOps domain as well.
Kubiya assigns an LLM chatbot named Kubi as a DevOps assistant for performing various roles to access resources from dozens of popular engineering tools. Simply ask Kubi to run CI jobs, list deployments, create and manage Kubernetes namespaces, create, update and query Jira tickets, update configuration files in Github, Gitlab or Bitbucket and much much more.
LLMs in DevOps
DevOps teams are overworked and understaffed. They would welcome any help in offloading mundane tasks so they can focus on higher priority tasks. ChatGPT can add great value as a virtual assistant for DevOps teams. It can perform tasks like incident detection and response, implementing IT risk policies, running diagnostics, and generating code.
Specifically for code generation, OpenAI released Codex, an LLM that translates human natural language into code. It can either generate actionable code from commands in human language or explain code in natural language for debugging. It can address tasks like auto-populating config files and templates, recommending better and cleaner code snippets, and pacing up the scaffolding of new assets.
ChatGPT, in essence, is an LLM powered by neural networks trained on a humongous data bank. This training allows it to predict word sequences and generate human-like responses. You can train these LLMs to solve specific programming challenges in your applications, establish best practices and IT policies, and ensure proper QA. The potential use cases for ChatGPT are wide and varied.
Kubiya contribution in DevOps through LLMs
Kubiya provides DevOps practitioners with a powerful toolset that can provide intent and action-based experiences to kickstart an automated workflow. At Kubiya we have trained various LLMs on our workflow structure which are now able to generate complex workflows in seconds. From creating Lambda functions to deploying K8s or pretty much any resource in AWS, Kubiya can do it all. This aids operations teams in creating workflows with little to no effort, and ensures security and customization at scale.
At the other end of the software delivery pipeline, developers can make requests for resources in English and Kubiya’s LLMs (using vector embeddings) are able to determine their intent and deploy the required resources in seconds to minutes. This is incredible when seen in action or experienced firsthand.
Kubiya’s AI platform — which perfectly mixes generative and conversational AI — can empower developers to have self-service access to resources they need to ship their code into production safely and predictably. It minimizes risk and the possibility of errors. In addition, it can also trigger a peer review before committing changes and send real-time alerts for proactive action when something goes wrong.
Kubiya.ai helps in automating platform that helps organizations streamline their DevOps processes, capture knowledge of operations and workflows, and extend those to end-users via conversational AI. The platform is designed to simplify complex processes by automating repetitive tasks and providing real-time insights into the performance of your IT infrastructure. Kubiya.ai combines the power of embedded large language models, machine learning, and natural language processing to create a platform that is easy to use and can be customized to meet the unique needs of any organization. If you were to prompt a ChatGPT command to create a doppelganger in its likeness but with domain specific expertise in DeVOps - Kubiya would be the result.
Kubi: The Conversational - AI of DevOps
With the release of new generation conversational AI, developer teams are able to perform their DevOps Tasks through normal conversation by Kubi. Kubi leverages a groundbreaking agent framework that democratizes the self-service of complex tasks, queries, and operations through simple conversations.
This innovation dramatically shifts the developer experience by affording every user their own personalized conversational-AI powered DevOps assistant, allowing seamless communication with their engineering platform in natural language, transforming the way developers and organizations work. The standout feature of Kubiya's next generation is the ability to chain together multiple purpose-built agents, each with domain specific knowledge and trained on fine-tuned LLMs, connected by a mental model, allowing it to execute complex end-to-end operations as if it were a DevOps engineer. This chain of thought closely mirrors the human brain's neural network, where different lobes work together to perform tasks.
These are some of the targeted advantages brought to the community by the awesome team of Kubiya:
Seamless Onboarding
The Kubiya team built a new seamless onboarding experience allowing you to get setup in minutes. Simply install Kubiya in their Slack workspace, accept the invitation to join, install the Kubiya CLI runner, and deploy actions.
Workless workflows
Our users spoke and we listened! Our next generation conversations don’t require pre-built workflows. You can customize the actions using simple python or use our native actions. Want to query any of your engineering platforms? Native queries don’t even require actions - Just ask and Kubi will construct any query on the fly!
Intelligent Agent - Kubi
Next Gen has the ability to chain together multiple purpose-built agents, each with domain specific knowledge and trained on fine-tuned LLMs, connected by a mental model, allowing it to execute complex end-to-end operations as if it were a DevOps engineer. This chain of thought closely mirrors the human brain's neural network, where different lobes work together to perform tasks. As a result, Kubi has memory and the ability to context switch all in the flow of a natural conversation. And to ensure Kubi feels part of the team, we have now added the ability for him to respond in public channels.
Events Based Actions:
Platforms can now also ask Kubi to trigger actions by using webhooks in response to an event. This opens up a new set of use cases including Kubi's ability to respond to incidents from your monitoring tools, such as the need to scale up a deployment, or the need to fulfill a Jira ticket once it's approved.
Support for multiple clusters
As of today, if multiple runners are set up, any Kubernetes based conversations will now automatically ask the user to choose a cluster to run the action on. This means you can create a separation between various clusters, provide a different set of permissions to each cluster and query and action multiple clusters in your network.
Terraform support and Pro profiles:
Administrations can create various profiles and give users access to other profiles, which includes co-pilot to different platforms or capabilities. Each profile runs in a new container.
As part of the Pro experience Kubi can now detect Terraform modules, create new PRs or alternatively clone those repos, identify and updates the variables.tf file and do terraform init and terraform plan.
But Kubi can do more than that: It can also create new Terraform to provision new resources using Infrastructure-as-Code (IaC) and do other Terraform actions such as destroy previously created resources.
Integrations to BigBucket, GitLab and ArgoCD support:
Kubiya adds integrations for ArgoCD, BitBucket, and GitLab.
ArgoCD - deploy images, restart applications, check or update deployment status, define configurations
BitBucket - work with issues, repositories, edit configuration files, run/stop pipeline.
GitLab - access commits, merge, retrieve Dora metrics, get logs, list repositories
This conversation AI will not only improve the overall developer experience and increase adoption of the IDP in your organization, but due to it's ability to self-serve resources complete with a human-like interaction of an assistant, results in more productivity and less context switching, resulting in better productivity.
Installing Kubiya.ai:
Installing the Slack App
Add the Kubiya app to your Slack workspace:
Clicking on the Add to Slack button above will prompt you to approve Kubiya’s access to your workspace:
Features of the Slack integration
Immediacy: Engage with Kubiya directly within your established communication channels on Slack and manage all kinds of cloud resources with a blink of an eye.
Efficiency: All native integrations can be easily connected right from Slack.
Collaboration: Enhance collective decision-making by sharing and debating Kubiya’s insights within your team’s Slack channels.
After adding to Slack, you should be redirected to this page, indicating that the onboarding process succeeded:
You should see the newly installed Kubiya app in your Slack workspace — with a message waiting for you to enable your first integrations:
Manage Kubi as your new DevOps team
Think of Kubiya as your DevOps teammate that can enable your team to simplify complex operations through human-like conversations. Although it features ChatGPT-like functionality, Kubiya goes beyond that, actually implementing and making changes to production clusters. It simultaneously delivers a self-service experience for developers while reducing the burden on the Ops team — all the while ensuring a simple and secure DevOps workflow automation.
Get connected with the community and get latest updates and events announcements: https://www.uptime.kubiya.ai/
Soon, I will be sharing more detailed features and releases of Kubiya.ai and other tools integrating different Tech Stacks like DevOps, Machine Learning, LLMs, CloudNative and a lot more.....
If you like my Article then please react to it and connect with me on Twitter if you are also a tech enthusiast. I would love to collaborate with people and share the experience of tech😄😄.
My Twitter Profile: