The future of AI isn’t just about smarter models—it’s about building systems that can think, act, and adapt autonomously in production environments. Moving from experimental AI prototypes to scalable, reliable agentic systems presents unique challenges that most organizations are just beginning to understand.

I built a workload using AWS CDK, and the CodePipeline stopped working at the worst moment. It was right at the end of the sprint; we had done multiple deployments before. But at this moment, the moment you might recognize. When this last PR is released, we will have met our deadline! Kaboom, the pipeline stops working, and the reason for the failure is not related to the changes you made.

Have we given up on the least privileged principle? Personally, I am a big fan of it. But let’s be honest, it can also be tough to follow the principle strictly. With the rise of CDK, it became even harder.

Ingesting data into an OpenSearch cluster looks easy if you read the documentation. The truth is it is easy, but it all depends on how much you care about the data you are ingesting. Let me go one step back. Why do we even use OpenSearch? With the rise of AI, you also need a knowledge base. These knowledge bases can be hosted in OpenSearch. However, to use the OpenSearch database, you must also fill it out with data.

Have you ever been in a situation where you want to provision or configure things cross-stack? Splitting these into logical stacks is always good when dealing with more complex environments. I already shared this in one of my previous blogs. But this also introduces a different problem!

Securing an endpoint used to be hard. Nowadays, with the cloud, it’s quite easy. You only need to know how! Assume you have files on S3 that you like to share. You could make the object publicly available. This would allow your users to download the file using their browsers simply. If you need to scale it, you can add CloudFront. This would cache the content closer to your users, making sure that your users have the best performance. But what if you want to control who can download the file? For this, you will need authentication and authorization.