For the past couple of years, like many other software developers, I have fully integrated generative AI into my development toolkit. I want to share my journey and my experience with the different tools that have shaped my workflow.
Early Days: ChatGPT and the Beginning of a New Age 🔗When ChatGPT launched in late 2022, the reaction was immediate. We tried it, we were horrified it would take our jobs, and I decided I didn’t want that anxiety.
As IT professionals, we live in a world of text. From source code and markup to configuration files and terabytes of logs, our days are spent creating, reading, and manipulating text in its many forms—JSON, XML, CSV, and beyond.
In the last decade, our toolkits have become incredibly sophisticated. We lean heavily on powerful GUI editors like VS Code and, more recently, on LLMs to handle even minor text processing jobs.
Over the past few months, I’ve been learning and building AI Agents / LLM-driven automation workflows.
I learned a lot - some exciting, some challenging and I decided to document my learnings in this blog.
LLM Workflows and Agentic Automation is Backend Engineering with Extra Steps 🔗Yep! Maybe I’ll ruffle some feathers, but building AI agents is very much a backend / automation pipeline-driven process. The same basic principles apply — and that’s actually a good thing.