Building agentic software?

Keep reading… I am posting content here that will help you learn about Generative AI, agentic AI and software engineering in general. But before you proceed, you need to remember..

Machines don’t learn and software don’t think! It’s all math.Know more…

In my opinion, crafting agentic software depends mainly on five maturity areas

✅ Understanding the problem statement
✅ Creating agent personas with clear objectives
✅ Writing clever prompts Know more…
✅ Developing simple and effective workflows
✅ Retrospect, and own what you build (You build it, you run it)

To build your (or your team’s) capabilities in Generative and agentic AI what do you need to do?

✅ Stop thinking that AI is the answer to all your problems
✅ Be part of, or develop an excellent engineering culture
✅ Collaborate, experiment and learn; understand what others are doing
✅ Move from jargon-driven development to value-driven development
✅ Learn about Python, async programming, APIs, one database and unit testing (best if you learn integration testing as well)
✅ Start small; build a simple chat bot and experiment with prompts
✅ Before jumping into agents, start with a simple RAG workflow
✅ Learn vector databases, text embedding, chunking and tool usage
✅ Learn different RAG techniqies, logging and monitoring
✅ Understand the economics of cloud computing
✅ Build a system with two agents that interact with each other
✅ Learn structured output and guardrails
✅ Learn agentic workflow patterns
✅ Add more agents, experiment and learn


⚠️ While this website is a work and progess and I will update the content continuously, and each of the items above is eventually going to become a post.

📣 Meanwhile don’t forget to check the 💎 AI Gems page and my software engineering blogs!