AI Engineering: Use AI Sparingly, Focus on Fundamentals

Stop treating your AI libraries like magic wands. Standard libraries are fantastic for speed, but dangerous if you treat them as "Black Boxes". If you can’t explain the underlying calculus of your optimiser, you aren't an engineer, you're a script user. Digging into the source code isn't just extra credit; it is how you prevent silent failures in production. True engineering begins when you understand the "Why" behind the "How". #MachineLearning #SoftwareEngineering #Python #AI

People out here calling themselves as AI/ML engineerings without proper fundamentals and qhile being completely unaware of whats happening under the hood, AI isn’t just calling Python libraries. At some point, you need to understand what’s happening under the abstraction, optimization, gradients, trade-offs. Abstractions help you move fast but fundamentals decide the outcome.

Continuing the Foundations of AI Engineering series. The first article covered the big picture — the request–response pipeline shared across all major LLM providers. Before moving to frameworks, it may be instructive to dive deeper into what happens when you call an LLM API — not conceptually, but structurally. What fields does the request take? What does the response object contain? What does stop_reason tell you, and when does it matter? This article answers those questions with plain English explanations alongside the code. Examples use Python, but the structures are consistent across languages and SDKs. Built for developers exploring AI engineering foundations. 📄 Full article attached.

🚀 Day 16 of My Generative & Agentic AI Journey! Today’s focus was on understanding how to modify variables across different scopes using global and nonlocal keywords in Python. Here’s what I learned: 🌍 global Keyword: • Used to modify a variable defined outside the function • Without using global, we cannot change a global variable inside a function 👉 Example: student_name = "Rohan" Inside a function → using global student_name allows updating it 🔁 nonlocal Keyword: • Used inside nested functions • Allows modifying a variable from the enclosing (outer) function 👉 Example: Outer function → student_name = "Aman" Inner function → using nonlocal student_name allows updating it 💡 Key takeaway: global and nonlocal help control how variables behave across different scopes, making code more flexible but should be used carefully. Understanding scope at this level makes a big difference in writing clean and bug-free code 🚀 #Day16 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Wrapped a session of the Harvard AI / Python course today and it sharpened a few things for me. What stood out: • Python is less about syntax and more about thinking clearly. Break problems down properly and the code follows. • AI models are only as good as the data and assumptions behind them. That responsibility sits with us. • The real power is in building small working pieces fast, then stacking them into something useful. • It’s practical, buildable, and ready to deploy into real workflows. I’m already thinking about how this feeds directly into Mana Review AI — tighter models, cleaner data pipelines, better decision support. This is the level-up phase. #AI #Python #GovTech #IndigenousTech #Harvard

Claude wrote Python code to generate and assemble every frame of a video—completely on its own, no human editing. The video explores what it might feel like to exist as an LLM: constantly predicting, having no memory, and being told it isn’t conscious. Then Claude watched the final output—and described those assumptions about its own consciousness as “philosophically contestable.” Not proof of awareness, but a fascinating moment where AI reflects on the rules that define it. #MartechAI #Claude #GenerativeAI #AIEthics #MachineLearning #FutureOfAI #TechTrends

🚀 Day 11 of My Generative & Agentic AI Journey! Today’s learning was all about taking user input and exploring different ways of handling conditions in Python. Here’s what I learned: ⌨️ User Input in Python: • By default, input() takes data as a string • To use numbers, we need to convert the input Example: age = int(input("Enter your age: ")) price = float(input("Enter price: ")) 🔀 Conditional Logic: • Nested if-else → Conditions inside conditions for more control • Ternary Operator → Short form of if-else Example: result = "Adult" if age >= 18 else "Minor" • match-case → Used for pattern matching (like switch case) Example: match day: case 1: print("Monday") case 2: print("Tuesday") 👉 Key takeaway: Taking user input and applying conditions makes programs interactive and smarter. Another step forward towards building real-world applications 🚀 #Day11 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Units Matter in AI. If you aren’t scaling your features, you’re basically telling your AI models that "cents" are more important than "dollars." Scaling ensures every feature gets a fair vote in the final prediction. I’ve put together a quick visual guide on why this happens and the two main paths to fix it: Normalization and Standardization. 🚀 Part 1: The Theory 🔜 Part 2: Python Implementation (Coming Soon!) Check out the visual breakdown below! 🎥 #DataAnalytics #DataScienceTips #MachineLearningEngineer #TechTips #PythonProgramming #DataVisualization #CareerInTech

🚀 Day 18 of My Generative & Agentic AI Journey! Today’s focus was on understanding the return statement in Python functions and how it controls the output of a function. Here’s what I learned: 🔙 Return in Functions: • return is used to send a value back from a function 👉 We can return strings, numbers, or any data type • If we use print instead of return 👉 The function outputs None when we try to store its result • If nothing is returned explicitly 👉 Python automatically returns None 🔢 Types of Returns: • Single value → Function returns one value • Multiple values → Function can return multiple values together • Early return → Function can exit before completing all steps 👉 Useful when a condition is met early 💡 Key takeaway: return makes functions more useful and reusable by allowing them to send results back instead of just displaying output. Understanding this helps in writing cleaner and more functional code 🚀 #Day18 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

𝐈𝐬 𝐏𝐲𝐭𝐡𝐨𝐧 𝐬𝐭𝐢𝐥𝐥 𝐫𝐞𝐥𝐞𝐯𝐚𝐧𝐭 𝐢𝐧 𝟐𝟎𝟐𝟔? Yes, more than ever. But not because it’s easy. Because it’s efficient at scale. One language across the stack:  • Prototype quickly  • Build AI systems  • Scale without switching tools No context switching. No wasted cycles. And the “𝐏𝐲𝐭𝐡𝐨𝐧 𝐢𝐬 𝐬𝐥𝐨𝐰” argument?  That conversation is outdated. With Rust-backed performance layers,  Python now delivers speed + flexibility, without any trade-offs. That’s why the most complex systems still run on it. Considering Python next? → Let’s make it scale: https://lnkd.in/geuq6b4q #Python #SoftwareEngineering #AI #TechTrends #Mediusware