FDE-2.01-AI & Agents

You'll receive a comprehensive, hosted-ready PDF guide that demystifies what an LLM actually is (next-token prediction, tokens, context windows) and teaches the single mental model, the Agent Loop: perceive, think, act, repeat; underneath every AI agent you'll ever encounter, complete with 10+ Mermaid diagrams, a fully working hand-built agent in Python, a hard-guardrail mindset from day one, and three progressively harder hands-on exercises with clear success criteria. It's built specifically for learners heading toward Forward Deployed Engineering and agentic AI roles, framing every concept — tokens, roles, tool use, iteration limits — in terms of the real judgment calls FDEs make when deciding whether a client problem actually needs an agent or just a well-crafted prompt.

Who it's for: absolute beginners to agentic AI with only basic programming fundamentals, and early-career developers who've used ChatGPT or Claude but have never built anything that "acts" on its own.

Why it's valuable: most AI agent content jumps straight into a framework's API without ever explaining the loop underneath — this guide teaches the loop itself, framework-free, so you can read and debug any agent implementation afterwards instead of being stuck when the abstraction breaks. This guide gets you from "I talk to ChatGPT" to "I built and understand a working agent" in a single focused sitting, at a fraction of the cost of comparable courses.

🚀 Getting Started (Day 1):

1. Complete the Setup & Installation section — Python + the Anthropic SDK + a free Anthropic API key — this takes about 15 minutes
2. Run the one-line verification script to confirm your setup works end-to-end
3. Read Sections 1–7 (Introduction through the Agent Loop) before touching any code

🛠️ Tools You'll Need:

• Python 3.10+ (installation covered for Windows, macOS, and Ubuntu/Linux in the guide)
• A free Anthropic API account and API key (console.anthropic.com)
• The anthropic Python package (pip install anthropic)
• Optional: VS Code or any text editor for writing .py files
• Note: the hands-on exercises use Claude Haiku, the lowest-cost model tier — expect to spend well under ₹10 in actual API usage across all three exercise tiers

📚 How to Practice:

• Work through the 3-tier hands-on exercises in Section 12 in order — guided walkthrough, then independent practice, then the mini-capstone
• Each exercise includes exactly how to verify you succeeded — don't skip that step
• Keep a terminal and code editor open while reading; this guide is meant to be coded along with, not just read

💰 Value Proposition: Why ₹25 is Unbeatable

Market Comparison:

• Udemy "AI Agents / LangChain" courses: ₹499-1199
• Coursera Generative AI Specialisations: ₹5,000–15,000
• AI Bootcamp "Agents" modules: ₹15,000–50,000+
• 1-on-1 AI consulting/mentoring: ₹2,000–5,000/hour
• This guide: ₹25 (one-time)

What You're Saving:

• ⏰ 10+ hours of piecing together the "what is an agent, really" mental model from scattered blog posts and framework quickstarts
• 💸 ₹2,800+ versus the cheapest paid alternative
• 🎯 A single focused sitting instead of a multi-week course
• ✅ A framework-free mental model you won't find in library-first tutorials — so you can debug any agent framework afterwards

ROI Example: An ungoverned agent shipped without a hard iteration cap — the guardrail this guide treats as core material, not a footnote — can run away and rack up real API cost in minutes. Your ₹25 pays for itself the first time it stops you from shipping an agent with no stopping condition.