Community Learning Path

From LLM basics to agentic AI systems

A structured, step-by-step journey for software engineers — moving from fundamentals all the way to building production-grade, agentic AI applications.

40–50
Days Total
8
Phases
30+
Concepts
5+
Projects
Find your route

Choose the track that matches your level

Jump straight into the phases that matter most for you, or follow the full sequence from foundations to capstone projects.

🌱

Foundation Track

Start with LLM basics, prompting, and AI-assisted engineering workflows.

Phases 1–2 · Beginner
🛠️

Builder Track

Move into APIs, security, local models, context engineering, and RAG.

Phases 3–6 · Intermediate
🚀

Architect Track

Design agentic workflows and finish with portfolio-ready projects.

Phases 7–8 · Advanced
Status
Level
01
🕒 4–5 days Beginner
Fundamentals
0 / 13 tasks
🏗️

Build a solid foundation before touching any AI tooling. Everything advanced rests on what you learn here.

By the end of this phase, you will be able to:
  • Explain in plain language how an LLM turns a prompt into a response.
  • Write structured prompts using at least five distinct techniques.
  • Choose an appropriate model for a given task, cost, and privacy constraint.
Understanding LLMs

Learn what Large Language Models are and how they work. Grasping these concepts lets you write better prompts and control costs.

Key concepts
TokensContext WindowLLM InferenceReasoning Models vs LLMs
Prompt Engineering

Prompts are your primary interface with AI. Master these five techniques for dramatically better results.

Key concepts
Role-based promptingContext-based promptingFew-shot promptingShort promptingChain of thought
LLM Landscape

Know the types of models available so you can pick the right one for any task.

Key concepts
Frontier models (OpenAI, Anthropic, Google)Open-weight modelsCoding modelsLocal models
🏁
MilestoneYou can describe tokens, context windows, and inference to a colleague, and reliably improve an output by rewriting its prompt.
02
🕒 2–3 days Beginner
AI-Powered Engineering
0 / 6 tasks

Start using AI tools to enhance your daily engineering workflow — before you write a single line of AI code yourself.

By the end of this phase, you will be able to:
  • Use an AI coding assistant fluidly inside a real project.
  • Know the practical limits of today's coding agents.
  • Build one automated workflow that includes an AI step.
Chat & Coding Agents

Get hands-on with the everyday tools before going deeper.

Key concepts
ChatGPTGoogle GeminiGitHub CopilotClaude CodeVS Code AI
Workflow Automation

Learn how AI fits into automated, multi-step pipelines.

Key concepts
DAGsn8nsim.aiWebhooks
🏁
MilestoneYou have shipped at least one real change with an AI assistant and built one small automated workflow end-to-end.
03
🕒 3–4 days Intermediate
AI APIs & Security
0 / 8 tasks
🔐

Move from chat interfaces to programmatic access. Learn to call AI models like any other API — safely.

By the end of this phase, you will be able to:
  • Call an LLM API from the terminal and from code.
  • Keep API keys and rate limits secure by default.
  • Route requests across models to balance cost and capability.
API Interaction

The same request, two ways: raw HTTP and an SDK.

Key concepts
curlPython SDKmessages & rolessystem prompttemperature
Security & Optimization

Treat AI APIs like any other production dependency — cost and abuse matter.

Key concepts
Environment variablesRate limitingToken optimizationCaching
Model Routing

One endpoint, many models — choose per request.

Key concepts
OpenRouterCost vs capabilityFallback models
🏁
MilestoneYou can make authenticated API calls from code, with keys in environment variables and sane rate limits in place.
04
🕒 3–4 days Intermediate
Local Models
0 / 7 tasks
💻

Run open-source models on your own hardware. Gain privacy, reduce costs, and understand what's under the hood.

By the end of this phase, you will be able to:
  • Run an open-weight model locally and chat with it offline.
  • Explain weights and quantization in your own words.
  • Know when local models beat hosted APIs (and when they don't).
Tools to Know

The local-model ecosystem you'll actually use.

Key concepts
OllamaHugging FaceDocker Model Runner (DMR)LlamaDeepSeekQwen (low-param)
Core Concepts

Understand what's actually running on your machine.

Key concepts
Model weightsQuantizationGGUF formatFine-tuning
🏁
MilestoneYou have a model running locally via Ollama and can explain why a quantized GGUF file fits on your machine.
05
🕒 4–5 days Advanced
Context Engineering
0 / 8 tasks
🧩

Context is everything when working with large codebases (50,000+ lines). This phase teaches you how to manage what the AI knows and when.

By the end of this phase, you will be able to:
  • Feed only the most relevant context to a model.
  • Distinguish short-term, long-term, and semantic memory.
  • Connect a model to a tool using MCP.
Context Management

More context isn't better — the right context is.

Key concepts
Retrieval strategiesContext window limitsSummarization
Agent Memory Types

Agents need different kinds of memory for different jobs.

Key concepts
Short-term memoryLong-term memorySemantic memory
Model Context Protocol (MCP)

The open standard for connecting models to tools and data — “USB-C for AI”.

Key concepts
MCP architectureServers & clientsTools & resources
🏁
MilestoneYou've built a small MCP integration and can articulate a retrieval strategy for a large codebase.
06
🕒 ~1 week Advanced
RAG & Knowledge Systems
0 / 7 tasks
📚

Retrieval Augmented Generation (RAG) lets your AI work with private, organizational data that was never in its training set.

By the end of this phase, you will be able to:
  • Explain embeddings and similarity search.
  • Stand up a vector database and ingest documents.
  • Wire retrieval into an LLM query end-to-end.
Prerequisites — learn these first

RAG stands on three ideas. Get these before building.

Key concepts
Vector databasesEmbeddingsSimilarity search
Building a RAG Pipeline

Put the pieces together and test on real data.

Key concepts
ChunkingIngestionRetrievalGrounding
🏁
MilestoneYou've built a working RAG pipeline that answers questions over your own private documents.
07
🕒 5–7 days Advanced
Agentic AI
0 / 6 tasks
🤖

Go beyond single-model calls. Learn to orchestrate multiple specialized agents that collaborate to solve complex problems.

By the end of this phase, you will be able to:
  • Describe the roles agents play in a multi-agent system.
  • Implement hand-offs between agents.
  • Build and run a working multi-agent pipeline.
Multi-Agent Orchestration

Start small — two cooperating agents beat one giant prompt.

Key concepts
Planning agentsMemory agentsTask agentsHand-offs
Frameworks

Pick one framework and build something real with it.

Key concepts
CrewAILangChainLangGraphAutoGen (optional)
🏁
MilestoneYou've built a 2-agent pipeline where one agent's output reliably drives the next.
08
🕒 Capstone Final Stretch
End-to-End Projects
0 / 8 tasks
🚀

Reading and exercises are not enough. You cement everything by building real, integrated projects from scratch.

By the end of this phase, you will be able to:
  • Integrate multiple techniques (MCP, RAG, agents) into one project.
  • Work fluently inside an AI-assisted IDE.
  • Produce documented, portfolio-ready work.
Goal: Build 5+ Projects

Projects are where the learning becomes permanent.

Key concepts
MCPRAGAgentic orchestrationCursor IDE
Project Ideas to Start With

Pick one that excites you and ship it.

Key concepts
AI Kubernetes agentAI DevOps teamAI Ops monitoringPrivate knowledge chatbot (RAG)Multi-agent code reviewer
🏁
MilestoneYou've shipped 5+ documented projects, each combining at least two core techniques from this roadmap.
No matching phasesTry a different search term or clear your filters.