What does OpenAI’s ChatGPT know about managing application environments?

Date Posted: 01.10.23
Read Time: 10 min

We couldn’t resist.

After seeing the recent hype around OpenAI’s ChatGPT—a conversational AI model that responds to user-submitted prompts—the marketing team at Quali decided we had to give it a shot.

So we posed some of the most common questions and problems our users face with building and managing application environments.

Here are the responses we received, and our grade on how successful the answers were:

Question: Explain challenges in orchestrating an application environment containing a Terraform script, a Helm Chart, and a Kubernetes manifest

ChatGPT’s response:

Orchestrating an application environment that contains a Terraform script, a Helm chart, and a Kubernetes manifest can be challenging for several reasons.

First, all of these tools have different syntaxes and configuration file formats, which can make it difficult to manage and maintain the overall environment.

In addition, each of these tools has its own specific set of dependencies and requirements, which can make it challenging to ensure that the environment is set up and configured correctly.

Furthermore, managing and updating the environment over time can be difficult, as changes made with one tool may affect the others and require careful coordination to avoid conflicts or errors.

Finally, troubleshooting issues in the environment can be challenging, as it may require expertise with multiple tools and a deep understanding of the interactions between them.

Our grade: A-

The robots break down the technical differences between the tools effectively.

What the robots could never understand is the pain and frustration of trying to build and maintain environments that rely on these.

As more environments require assets across technologies, those responsible for maintaining and delivering those environments will struggle to respond to changes.

This skills gap—which we’ve documented extensively—is what causes the bottlenecks, delays, and shadow IT that can hold large development teams back.

That’s why we tell our users to automate the configuration of these environments.

Which brings us to our next question for ChatGTP.

Question: How can I automate my IaC infrastructure?

ChatGPT’s response:

There are several ways to automate the deployment and management of infrastructure using Infrastructure as Code (IaC) tools such as Terraform.

One way to automate IaC infrastructure is to use a continuous integration and deployment (CI/CD) pipeline. This involves setting up a series of automated steps that are triggered whenever changes are made to the IaC code. For example, whenever a change is pushed to a Git repository, a CI/CD pipeline can be used to automatically build, test, and deploy the updated infrastructure.

Finally, many cloud providers offer their own automation tools for deploying and managing infrastructure. For example, AWS offers the CloudFormation service, which allows you to automate the creation and management of AWS resources using IaC templates. Azure offers the Azure Resource Manager, which allows you to automate the deployment and management of Azure resources using IaC templates.

Our grade: B-

Technically the robots answered the question, but they fell short of explaining automation for complete environments based on IaC infrastructure.

Our users find that application environments increasingly rely on environments that span multiple IaC scripts, tools, and technologies. What happens when your environment needs multiple AWS and Azure services?

We tell our users to automate the configuration of those IaC assets regardless of the technology behind them and make those environments repeatable.

This allows our users to automate the deployment of their complex multi-asset environments within their CI/CD pipelines, with the assurance that those environments reflect the latest updates to their IaC infrastructure.

In short, IaC automation today is about more than just automating the individual IaC assets—it’s about how people use those assets and make them work together.

Question: Application infrastructure vs. application environments: What’s the difference?

ChatGPT’s response:

Application infrastructure refers to the underlying physical or virtual hardware and systems that support an application, such as servers, storage, and networks. It also includes the software and tools that are used to manage and maintain this hardware, such as operating systems, virtualization software, and monitoring tools.

In contrast, an application environment refers to the specific configuration of an application and its dependencies in a given context. This includes the specific versions of the application, any supporting libraries or frameworks, and any other components or services that the application requires in order to run.

For example, an application infrastructure might consist of a cluster of virtual machines running on a cloud platform, with a load balancer and a database. The application environment for this infrastructure might include a specific version of the application code, a particular web server, and a specific version of the database.

The main difference between application infrastructure and application environments is that the former is concerned with the underlying hardware and systems that support the application, while the latter is focused on the specific configuration of the application and its dependencies.

Our grade: B+

The only thing holding this description back from an A rating is that it doesn’t address enough about how people work with application infrastructure and environments.

Frankly, we just did it better.

But I guess you can’t always ask a robot to do a human’s job.

Additional Resources