Learn LLM Path
The step-by-step roadmap from LLM fundamentals to reliable agentic AI. Ten connected pillars, curated resources, and a clear next step every time you return.
Ten pillars. One sequence.
Each pillar closes a different gap, then hands you the concepts needed for the next.
Transformer & LLM Internals
explain how an LLM works end-to-end without deep math. 3Blue1Brown chapters are the visual gold standard - watch in order
LLM App Fundamentals
go from "I can call an API" to "I can ship an LLM feature." Ed Donner's course (Ollama-first, laptop-friendly) is strongest here
RAG (Basic → Advanced → Eval)
build RAG that works in production. Biggest hidden gap - basic tutorials stop at "embed + top-k," real systems need hybrid search, reranking, evaluation
Fine-Tuning (LoRA/QLoRA)
know when NOT to fine-tune, and how LoRA/QLoRA make it cheap. Optional for most app work - but a common interview topic
Agents & Design Patterns
understand agents from first principles (vendor-neutral) before frameworks. Andrew Ng's course is the backbone
Context Engineering & Memory
the #1 skill for reliable agents in 2025-26, and almost always missing from course lists
Frameworks
fluency in the tools that implement the patterns. Fix vocabulary first, then go deep on LangGraph (the one interviewers ask about most)
Model Context Protocol (MCP)
understand, build, AND secure MCP. Intro videos cover why/architecture but skip client-side primitives and the entire MCP security attack class
Evals & Observability
stop guess-and-tweak. Evaluation-driven development is the single biggest predictor of agent-building success (per Andrew Ng)
Security (Full OWASP Top-10 for LLM)
know all ten risks, not just prompt injection. This is the biggest single-video gap - one injection video leaves 9 risks uncovered
Who this roadmap is for
- Beginners with basic Python who want structure instead of another hype thread.
- Career switchers who need an honest path from zero to job-ready.
- Working developers closing the gap between chatbot demos and reliable agents.
Close the gaps that demos hide.
Evals and security are first-class pillars here, with quiz gates that keep weak spots from quietly following you forward.
Beginners with basic Python, career switchers who want structure, and developers turning chatbot experiments into reliable agents.
Frequently asked questions
Is Learn LLM Path really free?
Yes — every pillar and resource is browsable with no account; sign in only to save progress.
Do I need math or machine learning background?
No — just basic Python and curiosity.
How long does the roadmap take?
About 17 weeks at 1–1.5 hrs/weekday, ~30% faster full-time.
What makes this different from other AI roadmaps?
Most curricula cover 1 of the 10 OWASP Top 10 for LLM risks; this roadmap covers all ten, with evals and security as first-class, quiz-gated pillars.