Completed two courses from AMD AI Academy: AI Agents 101: Building AI Agents with MCP and Open-Source Inference AI Agents 201: Design to Deployment: A Guide to Multi-Agent Systems A good, hands-on course on Building AI Agents with MCP and Open Source Inference. Course uses vLLM, Qwen3, Pydantic-AI, and MCP. The best part is, you get a fast AMD GPU for free to do the exercises. You can join AMD AI Developer Program here – https://www.amd.com/en/developer/ai-dev-program.html
-
-
I recently worked on an AI project that was quite unusual. It was about analyzing the past, present, and future of a person’s life. Yes, you guessed it right. Astrology. More specifically, this project focused on Vedic Astrology using the Kerala system. As someone who builds AI systems for a living, and being someone who loves solving challenging problems, I was excited. Modern AI tools make it incredibly easy to spin up apps quickly. But here is the reality check. The whole concept of “vibe coding” is still evolving, especially when it comes to complex data analysis, probabilistic workflows, and…
-
AI agents are often described as autonomous, adaptive, and intelligent. This can create the impression that they automatically learn from every interaction and continuously improve on their own. In reality, most AI agents do not learn automatically. They must be explicitly designed, configured, or programmed to learn. Understanding this distinction is critical when building real-world AI systems. Key Takeaways: Contrary to popular belief, AI agents do not automatically learn from interactions. Once deployed, their internal models are “frozen” unless explicitly engineered otherwise. An agent remembering your name or past context is simply data retrieval (eg. RAG), not learning. True learning…
-
I have been hearing about CrewAI for a while, and today I decided to spend some time exploring it. I must say, it genuinely impressed me. Within a minute, I was able to create a simple Vedic Astrologer agent. If you are curious, watch this video I recorded: While most of us are already aware that AI tools significantly reduce development time, what stood out to me here is something deeper. These tools are also transforming how AI systems themselves are built. The ability to download the generated code and customize it further makes the experience even more powerful. By…
-
List of Agentic AI Patterns and Architectures. This is still an evolving field, so the list is updated as of 04-Jan-2026.
-
List of RAG (Retrieval-Augmented Generation) Patterns. This is still an evolving field, so the list is updated as of 04-Jan-2026.
-
1. Download Ollama from https://ollama.com/download 2. To download and run the model, use the command: ollama run qwen2.5:72b 3. Once model download is completed, just type your prompts! Meanwhile, my poor GPU Next, here is a bonus. Access the model from a LangChain python script. Your Ollama service is already running at http://localhost:11434/ Install dependencies: pip install langchain-ollama Create a test_client.py program: from langchain_ollama import ChatOllama from langchain_core.prompts import ChatPromptTemplate from langchain_core.output_parsers import StrOutputParser import time # 1. Configuration # We use the specific model tag you pulled in Ollama MODEL_TAG = “qwen2.5:72b” print(f”— Connecting to Local Ollama ({MODEL_TAG}) —“)…
-
The modern software architect is often bottlenecked not by a lack of knowledge, but by the sheer volume of context they must maintain. Scalability constraints, compliance guardrails, cloud service limits, and legacy entanglements create a cognitive burden that makes pure design difficult. Read my new article on – How AI is redefining the Application Architecture Design process – https://www.linkedin.com/pulse/how-ai-redefining-system-design-process-praveen-zohtc
-
Navigating the fast-evolving world of LLMs requires more than just innovation, it demands discipline. In my latest piece, A Sanity Guide to Version Control for LLMs, I break down practical strategies to bring order, traceability, and confidence to AI development workflows. From managing model iterations to ensuring reproducibility, this guide offers a structured approach to keep experimentation aligned with enterprise needs. Read my full article here – https://www.linkedin.com/pulse/sanity-guide-version-control-llms-praveen-nair-pmp-architect-irpgc/
-
Read my latest article on agentic AI adoption in Platform Engineering on Medium. https://ninethsense1.medium.com/platform-engineering-2-0-the-rise-of-ai-native-devops-5b6c9510decc?sk=eadef43fd8cf604c21105ff055d9aead We spent years asking developers to care about infrastructure, aka follow the DevOps culture. AI-Native Platform Engineering now effectively says, “Actually, forget it. The AI handles the infrastructure now! You just focus on code”