Welcome! I'm Shreya, a data professional, and I started this blog to document my journey into AI and share every lesson, failure, and breakthrough I encounter along the way.
For my first post, I want to start where I actually started — with two courses that gave me a solid foundation: Claude 101 and AI Fluency: Framework and Foundations. Here's what I learned from each.
Claude 101: Getting Comfortable with AI as a Daily Tool
This course was all about building a working relationship with Claude — from the basics to real, practical use.
Meet Claude
I started with the fundamentals: what Claude actually is, having my first real conversation with it, and learning how to get better result. I also got a walkthrough of the Claude desktop app — Chat, Cowork, and Code — and how each one fits a different kind of work.
Organizing your work and knowledge
This section shifted from "chatting" to actually working with Claude. I learned about Projects for organizing ongoing work, Artifacts for creating documents and content I could iterate on, and Skills for handling more specialized, repeatable tasks.
Expanding Claude's reach
Here's where things got interesting — connecting Claude to my own tools, using enterprise search to pull in relevant context, and using Research mode for deeper, multi-step investigations instead of one-off questions.
AI Fluency: Framework and Foundations — Thinking About AI, Not Just Using It
If Claude 101 was about the how, this course was about the why and when. It introduced a framework for thinking clearly about working with AI, rather than just using it reactively.
The AI Fluency Framework
The course opened with a simple but important question: why do we even need "AI fluency" as a skill? Then it introduced the 4D Framework, which became the backbone of everything that followed.
Deep Dive: What is Generative AI?
Before jumping into technique, the course grounded me in the fundamentals of generative AI — how it works, and just as importantly, its capabilities and limitations. Knowing what AI is bad at turned out to be as useful as knowing what it's good at.
The 4Ds, one at a time:
Delegation — deciding what to hand off to AI versus what to keep doing myself, including how this applies to project planning.
Description — the art of clearly communicating what I actually want, which unlocked a lot of the "better results" mentioned back in Claude 101.
Discernment — critically evaluating AI outputs instead of accepting them at face value.
Diligence — the responsibility part: using AI thoughtfully, ethically, and with an awareness of consequences.
Deep Dive: Effective prompting techniques
This tied Description and Discernment together with concrete techniques for getting more reliable, higher-quality outputs.
The Description-Discernment loop
Probably my favorite concept from the whole course — treating AI collaboration as an iterative loop rather than a one-shot request. Describe, evaluate, refine, repeat.
🎓 Certifications Earned
- ✅
What's Next
This is just the first entry. Next up, I want to start applying these concepts to real projects — combining my data background with what I'm learning about AI collaboration.
If you're on a similar path, let's connect — I'd love to learn alongside you! Find me on LinkedIn.
SOCIAL SHARE CARD GENERATOR