Phase 1: Python + Terminal + Git Foundations
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 1 | Terminal | Git Bash/VS Code; pwd, ls, cd, mkdir, touch, cp, mv, rm; paths | 📚 Missing Semester – Shell ↗📚 freeCodeCamp Command Line ↗ | |
| session 2 | Python setup | Python install; VS Code; variables; strings; numbers; bool; print/type | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 3 | Operators & input | Arithmetic, comparison, logical operators; input; type conversion; f-strings | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 4 | Conditions | if/elif/else; Boolean logic; nested conditions | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 5 | Loops | for/while/range/break/continue; loop patterns | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 6 | Functions | def; parameters; return; scope; reusable functions | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 7 | Lists | Indexing, slicing, append/remove/pop; list loops | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 8 | Dictionaries | dicts; nested data; keys/items/get | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 9 | JSON | Parsing JSON; reading/writing JSON files | 📚 Real Python – Working with JSON ↗📚 Python json docs ↗ | |
| session 10 | Files | open/read/write/append; with; pathlib; directory traversal | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 11 | Exceptions | try/except; common errors; traceback reading; input validation | 📚 Real Python – Exceptions ↗📚 Python Errors docs ↗ | |
| session 12 | Mini project | Guess the Number; clean functions; validation README | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 13 | File project | Directory scanner + normalization + summary modular functions | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 14 | Packages/envs | pip; venv; requirements.txt; dependency isolation | 📚 Real Python – venv Guide ↗📚 Python Packaging Guide ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 15 | APIs | requests; GET; status codes; JSON; query params; error handling | 📚 Real Python – Requests ↗📚 Requests Docs ↗ | |
| session 16 | Git | init/status/add/commit; branches intro; .gitignore; README | 📚 Pro Git Book ↗📚 GitHub Skills ↗ |
Phase 2: GitHub, Testing, CI/CD & Professional Python
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 17 | GitHub | remote repos; push/pull/clone; professional README | 📚 Pro Git Book ↗📚 GitHub Skills ↗ | |
| session 18 | Branches | switch/checkout; merge; conflicts; pull requests | 📚 Learn Git Branching (interactive) ↗📚 Pro Git – Branching ↗ | |
| session 19 | pytest | assertions; test functions; fixtures basics; test utilities | 📚 pytest Docs ↗📚 Real Python – pytest ↗ | |
| session 20 | Code quality | PEP 8; naming; modules; project structure; requirements | 📚 Real Python – Code Quality ↗📚 Ruff Linter Docs ↗ | |
| session 21 | Environment security | env; python-dotenv; os.getenv; configuration separation | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 22 | GitHub Actions | YAML; workflow/jobs/steps/runners/triggers | 📚 GitHub Actions Docs ↗📚 GitHub Actions Quickstart ↗ | |
| session 23 | CI | Python setup; dependency install; run scripts/tests on push | 📚 GitHub Actions Docs ↗📚 GitHub Actions Quickstart ↗ | |
| session 24 | CI + pytest | Automated tests; failed tests block workflow; logs | 📚 GitHub Actions Docs ↗📚 GitHub Actions Quickstart ↗ | |
| session 25 | Secrets | GitHub encrypted secrets; secure environment variables | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 26 | Security hygiene | gitignore; secret leaks; rotation; safe logging | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 27 | Dependency security | pip-audit; vulnerability reports; dependency updates | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 28 | Debugging CI | Break YAML/tests/dependencies; diagnose logs | 📚 GitHub Actions Docs ↗📚 GitHub Actions Quickstart ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 29 | Professional repo | README; setup; usage; architecture diagram; screenshots | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ | |
| session 30 | Project hardening | Refactor mini projects; tests; error handling; logging | 📚 Python Official Tutorial ↗📚 Real Python ↗ | |
| session 31 | Project 1 release | Publish polished Python/API automation project with CI | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ |
Phase 3: Docker + SQL + Airflow/Data Engineering
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 32 | Docker theory | images/containers/daemon/registry; Docker Desktop + WSL2 | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 33 | Docker CLI | pull/run/ps/logs/exec/stop/rm; ports; volumes | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 34 | Dockerfile | FROM/WORKDIR/COPY/RUN/CMD; layers; dockerignore | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 35 | Containerize Python | build/tag/run; port mapping; logs | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 36 | Compose + env | compose.yaml; services; networking; env vars | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 37 | Data fundamentals | CSV/JSON; schemas; cleaning; records | 📚 SQLBolt (interactive) ↗📚 Mode SQL Tutorial ↗ | |
| session 38 | SQLite concepts | tables, rows, schema design; connecting from Python | 📚 SQLBolt (interactive) ↗📚 Mode SQL Tutorial ↗ | |
| session 39 | SQL | SELECT/WHERE/ORDER BY/INSERT/UPDATE/DELETE/JOIN/GROUP BY | 📚 SQLBolt (interactive) ↗📚 Mode SQL Tutorial ↗ | |
| session 40 | Airflow theory | DAG/task/scheduler/retries/dependencies/logs | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 41 | Airflow Docker | Run Airflow in Docker; UI exploration | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 42 | First DAG | DAG; schedule; task dependencies; TaskFlow | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 43 | Python tasks | PythonOperator/TaskFlow; logs; outputs | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 44 | Connections | Connections/Variables/credentials; secure config | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 45 | API pipeline | API → validate JSON → transform | 📚 Real Python – Requests ↗📚 Requests Docs ↗ | |
| session 46 | SQLite pipeline | Write/query data; simple schema | 📚 SQLBolt (interactive) ↗📚 Mode SQL Tutorial ↗ | |
| session 47 | Reliability | Retries; idempotency; logging; failure handling | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 48 | Dockerize pipeline | Package project + DAGs; reproducible setup | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 49 | Test pipeline | pytest transformations; separate business logic from orchestration | 📚 pytest Docs ↗📚 Real Python – pytest ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 50 | Integrated pipeline | API → transform → SQLite → Airflow → logs | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 51 | Production simulation | Break configs; recover; document runbook | 📚 Apache Airflow Tutorial ↗📚 Astronomer Learn Airflow ↗ | |
| session 52 | Project 2 release | Publish automated data pipeline with Docker/Airflow/GitHub | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ |
Phase 4: AI Foundations + LLM APIs + Prompt Engineering
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 53 | AI foundations | AI vs ML vs Deep Learning; core terminology | 📚 DeepLearning.AI – Generative AI for Everyone ↗📚 Google – Generative AI Concepts ↗ | |
| session 54 | Generative AI | GenAI concepts; use cases; limitations | 📚 DeepLearning.AI – Generative AI for Everyone ↗📚 Google – Generative AI Concepts ↗ | |
| session 55 | Model landscape | Open-source vs closed-source models; platform overview | 📚 DeepLearning.AI – Generative AI for Everyone ↗📚 Google – Generative AI Concepts ↗ | |
| session 56 | Responsible AI | Ethics; safety; hallucinations; responsible usage | 📚 Google Responsible AI Practices ↗📚 NIST AI Risk Management Framework ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 57 | Prompt anatomy | Role; instruction; input; output | 📚 Prompt Engineering Guide ↗📚 Anthropic Prompt Engineering Docs ↗ | |
| session 58 | Prompting | Zero-shot; few-shot; role-based prompting | 📚 Prompt Engineering Guide ↗📚 Anthropic Prompt Engineering Docs ↗ | |
| session 59 | Advanced prompting | CoT; ToT; ReAct; self-consistency | 📚 Prompt Engineering Guide ↗📚 Anthropic Prompt Engineering Docs ↗ | |
| session 60 | Structured outputs | JSON parsing; streaming; batch outputs; error handling | 📚 Anthropic – Tool Use / Structured Output ↗📚 OpenAI – Structured Outputs Guide ↗ | |
| session 61 | Guardrails | Output validation; safety rules; schema validation | 📚 Anthropic – Tool Use / Structured Output ↗📚 OpenAI – Structured Outputs Guide ↗ | |
| session 62 | Memory & context | Conversation memory; context management | 📚 Anthropic API Docs ↗📚 OpenAI API Docs ↗ | |
| session 63 | LLM APIs | OpenAI/Gemini-style APIs; chat; embeddings; function calling | 📚 Anthropic API Docs ↗📚 OpenAI API Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 64 | API security | API keys; rate limits; environment variables; key management | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 65 | LLM evaluation | Accuracy; relevance; reliability; debugging outputs | 📚 DeepLearning.AI – Evaluating & Debugging GenAI ↗📚 Hugging Face Evaluate Docs ↗ | |
| session 66 | Tokens & context | Token usage; context windows; retries/timeouts | 📚 Hugging Face – Tokenizers Chapter ↗📚 Karpathy – Let’s Build the GPT Tokenizer ↗ | |
| session 67 | LLM mini project | Build a reliable structured-output assistant | 📚 Anthropic API Docs ↗📚 OpenAI API Docs ↗ |
Phase 5: NLP + Embeddings + Core RAG
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 68 | Text preprocessing | Cleaning; normalization; preprocessing pipelines | 📚 spaCy Course (interactive) ↗📚 Hugging Face NLP Course ↗ | |
| session 69 | Tokenization | Tokens; token boundaries; practical tokenization | 📚 Hugging Face – Tokenizers Chapter ↗📚 Karpathy – Let’s Build the GPT Tokenizer ↗ | |
| session 70 | Text representation | Vectorization; feature engineering | 📚 spaCy Course (interactive) ↗📚 Hugging Face NLP Course ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 71 | NER & POS | Named Entity Recognition; Part-of-Speech tagging | 📚 spaCy Course (interactive) ↗📚 Hugging Face NLP Course ↗ | |
| session 72 | Embeddings | Text to vectors; dimensions; semantic similarity | 📚 Sentence Transformers Docs ↗📚 Pinecone Learn – Embeddings ↗ | |
| session 73 | Semantic search | Embedding-based similarity and retrieval | 📚 Sentence Transformers Docs ↗📚 Pinecone Learn – Embeddings ↗ | |
| session 74 | RAG concepts | Hallucinations; retrieval; context; RAG architecture | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| session 75 | RAG workflow | Retrieval + generation workflow | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| session 76 | Data handling | Document loading; cleaning; chunking; indexing | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| session 77 | Chunking | Chunk size; overlap; metadata; IDs | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 78 | Vector databases | Vector stores; indexes/collections; distance | 📚 Pinecone Learn – Vector Databases ↗📚 Qdrant Docs ↗ | |
| session 79 | Upsert + search | Chunk → embed → upsert → top-k retrieval | 📚 Pinecone Learn – Vector Databases ↗📚 Qdrant Docs ↗ | |
| session 80 | Dense vs sparse | Dense retrieval; sparse retrieval; hybrid search | 📚 Pinecone Learn – Vector Databases ↗📚 Qdrant Docs ↗ | |
| session 81 | Multimodal embeddings | Text/image embeddings in vector databases | 📚 Sentence Transformers Docs ↗📚 Pinecone Learn – Embeddings ↗ | |
| session 82 | LlamaIndex RAG | Build a simple RAG pipeline with LlamaIndex | 📚 LlamaIndex Docs ↗📚 LlamaIndex RAG Guide ↗ | |
| session 83 | LangChain intro | Models; prompts; documents; retrievers | 📚 LangChain Docs ↗📚 LangChain Tutorials ↗ | |
| session 84 | Manual RAG | Retrieve context to LLM; inspect retrieved chunks | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 85 | RAG pipeline | End-to-end ingestion → retrieval → generation | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| session 86 | RAG project | Build RAG Knowledge Assistant | 📚 Pinecone Learn – RAG ↗📚 LangChain RAG Tutorial ↗ | |
| session 87 | Project hardening | Tests; logging; citations/context display; README | 📚 Python Official Tutorial ↗📚 Real Python ↗ |
Phase 6: Advanced RAG + Evaluation
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 88 | Query rewriting | Rewrite user queries for better retrieval | 📚 LangChain – Query Analysis How-Tos ↗📚 LlamaIndex – Query Transformations ↗ | |
| session 89 | Multi-query retrieval | Generate multiple search queries; merge results | 📚 LangChain – Query Analysis How-Tos ↗📚 LlamaIndex – Query Transformations ↗ | |
| session 90 | Multi-hop retrieval | Retrieve across multiple reasoning steps | 📚 LangChain – Query Analysis How-Tos ↗📚 LlamaIndex – Query Transformations ↗ | |
| session 91 | Context optimization | Reduce irrelevant context; improve answer grounding | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 92 | Why basic RAG fails | Failure modes; retrieval errors; generation errors | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 93 | Self-RAG | Self-reflection and retrieval decisions | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 94 | Corrective RAG | Detect poor retrieval and correct the retrieval path | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 95 | Adaptive RAG | Route queries based on complexity | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 96 | Contextual retrieval | Improve chunks with surrounding context | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 97 | LOTR retrieval | Learn advanced retrieval composition patterns | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| session 98 | Fallback mechanisms | Graceful fallback when retrieval fails | 📚 LangChain – Advanced RAG How-Tos ↗📚 Pinecone Learn – RAG ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 99 | RAGAS fundamentals | Faithfulness; relevance; context recall; precision | 📚 RAGAS Docs ↗📚 LangSmith – Evaluation Docs ↗ | |
| session 100 | RAG evaluation | Build an evaluation dataset and scoring workflow | 📚 RAGAS Docs ↗📚 LangSmith – Evaluation Docs ↗ | |
| session 101 | RAG benchmarking | Compare chunking/retrieval strategies | 📚 RAGAS Docs ↗📚 LangSmith – Evaluation Docs ↗ | |
| session 102 | Advanced RAG project | Upgrade the RAG assistant with evaluation + fallbacks | 📚 RAGAS Docs ↗📚 LangSmith – Evaluation Docs ↗ |
Phase 7: Agents + Tool Calling + Orchestration
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 103 | Agent foundations | AI agents; agent architectures | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| session 104 | Agent types | Reflex; goal-based; utility-based; tool-based | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| session 105 | Reactive agents | Reactive design patterns and execution loops | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 106 | Tool calling | Tools; execution flows; prompting strategies | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| session 107 | ReAct agents | Reason + act loops; tool-using agents | 📚 LangGraph – Prebuilt ReAct Agent ↗📚 ReAct Paper (arXiv) ↗ | |
| session 108 | LangChain agents | Build tool-using workflows | 📚 LangChain Docs ↗📚 LangChain Tutorials ↗ | |
| session 109 | LangGraph | Stateful agent orchestration | 📚 LangGraph Docs ↗📚 LangChain Academy – LangGraph Course ↗ | |
| session 110 | Planning | Planning; reasoning; task decomposition | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| session 111 | Tool orchestration | Multiple tools; routing; execution control | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ | |
| session 112 | Multi-agent systems | Collaborative AI; agent roles | 📚 LangGraph – Multi-Agent Tutorials ↗📚 Anthropic – Building Effective Agents ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 113 | Agent coordination | Negotiation; consensus; coordination patterns | 📚 LangGraph – Multi-Agent Tutorials ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 114 | Framework comparison | LangChain; LlamaIndex; AutoGen; CrewAI; LangGraph | 📚 LangGraph – Multi-Agent Tutorials ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 115 | Hierarchical agents | Manager/worker and collaborative patterns | 📚 LangGraph – Multi-Agent Tutorials ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 116 | Goal-oriented systems | Goal-driven agent design | 📚 LangGraph – Multi-Agent Tutorials ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 117 | MCP | Model Context Protocol: servers; clients; tools; resources | 📚 Model Context Protocol Docs ↗📚 MCP Specification ↗ | |
| session 118 | A2A | Agent-to-Agent communication concepts | 📚 A2A Protocol Docs ↗📚 A2A GitHub Project ↗ | |
| session 119 | Agentic RAG | Autonomous retrieval + reasoning pipelines | 📚 LlamaIndex – Agentic RAG Guide ↗📚 LangGraph – Agentic RAG Tutorial ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 120 | Single vs multi-agent RAG | Architecture tradeoffs | 📚 LlamaIndex – Agentic RAG Guide ↗📚 LangGraph – Agentic RAG Tutorial ↗ | |
| session 121 | Tracing | Agent debugging; tracing; monitoring with LangSmith-style workflows | 📚 LangSmith Docs ↗📚 OpenTelemetry Docs ↗ | |
| session 122 | Performance | Latency; performance; cost optimization | 📚 LangSmith Docs ↗📚 OpenTelemetry Docs ↗ | |
| session 123 | Agent project | Build Secure AI Automation Agent | 📚 Anthropic – Building Effective Agents ↗📚 LangGraph Docs ↗ |
Phase 8: AI Application Engineering + Deployment
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 124 | HTTP fundamentals | GET/POST/PUT/DELETE; status codes; JSON | 📚 FastAPI Official Docs ↗📚 FastAPI Tutorial – User Guide ↗ | |
| session 125 | FastAPI | Routes; request/response models; Pydantic | 📚 FastAPI Official Docs ↗📚 FastAPI Tutorial – User Guide ↗ | |
| session 126 | Swagger/OpenAPI | API documentation and testing | 📚 FastAPI Official Docs ↗📚 FastAPI Tutorial – User Guide ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 127 | AI service layer | Wrap RAG/agent code as an HTTP service | 📚 FastAPI Official Docs ↗📚 FastAPI Tutorial – User Guide ↗ | |
| session 128 | Frontend integration | Gradio and Streamlit basics | 📚 Streamlit Docs ↗📚 Gradio Docs ↗ | |
| session 129 | UX for LLM apps | LLM UI/UX basics; useful interaction patterns | 📚 Streamlit Docs ↗📚 Gradio Docs ↗ | |
| session 130 | API security | Environment variables; authentication concepts; rate limiting | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 131 | Docker AI apps | Dockerize an AI application | 📚 Docker Get Started ↗📚 Docker Curriculum ↗ | |
| session 132 | CI/CD for AI | GitHub Actions pipeline for tests and deployment | 📚 GitHub Actions Docs ↗📚 GitHub Actions Quickstart ↗ | |
| session 133 | Cloud deployment | Deploy Dockerized FastAPI AI app | 📚 Kubernetes Basics Tutorial ↗📚 Full Stack Deep Learning ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 134 | Kubernetes basics | Pods; deployments; services; scaling concepts | 📚 Kubernetes Basics Tutorial ↗📚 Full Stack Deep Learning ↗ | |
| session 135 | Microservices | Modular AI systems and service boundaries | 📚 Kubernetes Basics Tutorial ↗📚 Full Stack Deep Learning ↗ | |
| session 136 | LLM orchestration | FastAPI for LLM orchestration and LangChain-style servers | 📚 FastAPI Official Docs ↗📚 FastAPI Tutorial – User Guide ↗ | |
| session 137 | Logging | Structured logs; errors; request tracing | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| session 138 | Monitoring | Application metrics; latency; failures | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| session 139 | LLMOps | Production AI workflows; evaluation and release discipline | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| session 140 | Prompt versioning | Version prompts; compare performance | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 141 | Tracing & performance | Trace model calls; monitor latency/cost | 📚 LangSmith Docs ↗📚 OpenTelemetry Docs ↗ | |
| session 142 | LLMOps platforms | Langfuse; MLflow; LangGraph-oriented workflows | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| session 143 | Observability | Prometheus/Grafana concepts for AI systems | 📚 DeepLearning.AI – LLMOps ↗📚 LangSmith Observability Docs ↗ | |
| session 144 | Live deployment demo | Deploy and showcase an AI application | 📚 Kubernetes Basics Tutorial ↗📚 Full Stack Deep Learning ↗ |
Phase 9: Machine Learning + Deep Learning Foundations
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 145 | ML foundations | Linear regression; logistic regression | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| session 146 | Perceptrons | Perceptrons; multi-layer perceptrons | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| session 147 | Loss functions | Loss functions; activation functions | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 148 | Gradient descent | Optimization; gradient descent | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| session 149 | Backpropagation | Backpropagation and training workflow | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| session 150 | Deep neural networks | DNN architecture and training concepts | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ | |
| session 151 | CNNs | CNNs for computer vision applications | 📚 CS231n – CNNs ↗📚 colah’s blog – Understanding LSTMs ↗ | |
| session 152 | RNNs | RNNs for sequential data | 📚 CS231n – CNNs ↗📚 colah’s blog – Understanding LSTMs ↗ | |
| session 153 | LSTMs | LSTMs; sequence modeling | 📚 CS231n – CNNs ↗📚 colah’s blog – Understanding LSTMs ↗ | |
| session 154 | Transformer motivation | RNN limitations; rise of Transformers | 📚 The Illustrated Transformer ↗📚 Karpathy – Let’s Build GPT ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 155 | Attention | Query; Key; Value; attention mechanism | 📚 The Illustrated Transformer ↗📚 Karpathy – Let’s Build GPT ↗ | |
| session 156 | Transformer architecture | Encoder/decoder concepts; Transformer blocks | 📚 The Illustrated Transformer ↗📚 Karpathy – Let’s Build GPT ↗ | |
| session 157 | Pretraining vs fine-tuning | How LLM training stages differ | 📚 Hugging Face LLM Course ↗📚 Hugging Face – Fine-tuning a Pretrained Model ↗ | |
| session 158 | Transfer learning | Transfer learning concepts and applications | 📚 Hugging Face LLM Course ↗📚 Hugging Face – Fine-tuning a Pretrained Model ↗ | |
| session 159 | GANs | Introduction to GANs | 📚 Hugging Face Diffusion Course ↗📚 Diffusion Models Explainer ↗ | |
| session 160 | Diffusion | Diffusion model fundamentals | 📚 Hugging Face Diffusion Course ↗📚 Diffusion Models Explainer ↗ | |
| session 161 | Image generation | Modern image generation systems | 📚 Hugging Face Diffusion Course ↗📚 Diffusion Models Explainer ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 162 | ML mini project | Train/evaluate a small ML model and document results | 📚 DeepLearning.AI – Deep Learning Specialization ↗📚 CS231n Course Notes ↗ |
Phase 10: Fine-Tuning + Efficient Model Inference
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 163 | Fine-tuning | Fine-tuning and domain adaptation | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 164 | Fine-tuning vs RAG | When to use each approach | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 165 | Hybrid workflows | RAG + fine-tuning | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 166 | SLM vs LLM | Choosing smaller vs larger models | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 167 | Model selection | LLaMA; Mistral; Phi and model-selection criteria | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 168 | DAPT | Domain-Adaptive Pre-Training concepts | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 169 | Dataset preparation | Instruction datasets; formatting; labeling | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 170 | Preference datasets | Alpaca-style datasets; preference data | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 171 | Data quality | Cleaning; formatting; labeling best practices | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 172 | PEFT | Parameter-efficient fine-tuning concepts | 📚 Sebastian Raschka – LoRA/QLoRA Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 173 | LoRA | Low-Rank Adaptation | 📚 Sebastian Raschka – LoRA/QLoRA Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 174 | QLoRA | Quantized LoRA workflows | 📚 Sebastian Raschka – LoRA/QLoRA Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 175 | Hugging Face + PEFT | Fine-tuning pipeline concepts | 📚 Sebastian Raschka – LoRA/QLoRA Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 176 | Trainer API | Configurations and training workflows | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 177 | Preference optimization | DPO; ORPO; KTO concepts | 📚 Hugging Face – DPO/TRL Docs ↗📚 Hugging Face LLM Course – Alignment ↗ | |
| session 178 | Quantization | Efficient inference; quantization tradeoffs | 📚 Hugging Face Quantization Docs ↗📚 vLLM Docs ↗ | |
| session 179 | Model formats | GGUF; AWQ; model compression | 📚 Hugging Face Quantization Docs ↗📚 vLLM Docs ↗ | |
| session 180 | Serving models | vLLM and Ollama serving concepts | 📚 vLLM Docs ↗📚 Ollama GitHub ↗ | |
| session 181 | Evaluation | Accuracy; F1; BLEU; ROUGE | 📚 EleutherAI – LM Evaluation Harness ↗📚 Hugging Face Evaluate Docs ↗ | |
| session 182 | Benchmarking | Fine-tuning performance comparison | 📚 EleutherAI – LM Evaluation Harness ↗📚 Hugging Face Evaluate Docs ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 183 | Cost estimation | Training/inference resource estimation and optimization | 📚 EleutherAI – LM Evaluation Harness ↗📚 Hugging Face Evaluate Docs ↗ |
Phase 11: AI Coding Agents + Advanced Engineering
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 184 | AI coding agents | Run AI coding agents across terminal; IDEs; cloud; GitHub | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 185 | Model selection | Choose/switch models for different tasks | 📚 Hugging Face Fine-tuning Guide ↗📚 Hugging Face PEFT Docs ↗ | |
| session 186 | Reasoning modes | Optimize workflows with different reasoning levels | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 187 | Agent permissions | Read-only; auto; full access concepts | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 188 | AI terminals | AI-powered commands; workflows; planning | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 189 | Persistent project memory | AGENTS.md; PLANS.md; context files | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 190 | MCP for development | Connect external tools/services through MCP | 📚 Model Context Protocol Docs ↗📚 Claude Code – MCP Docs ↗ | |
| session 191 | Skills | Create reusable AI development skills | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 192 | Subagents | Delegate focused work to subagents | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 193 | AI testing | Automate testing with coding agents | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 194 | AI code review | Automate code reviews and feedback | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 195 | AI CI/CD | Automate CI/CD and GitHub workflows | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 196 | Multi-agent coding | Orchestrate multiple coding agents | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 197 | Hooks & tools | Extend agents with hooks and custom tools | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 198 | Human-in-the-loop | Approval; review; quality-control processes | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 199 | AI security | Hallucinations; prompt injection; permissions; safe tooling | 📚 OWASP Top Ten ↗📚 OWASP Cheat Sheet Series ↗ | |
| session 200 | Reliable workflows | Guardrails; validation; failure recovery | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 201 | Production automation | Deploy reliable, scalable and secure AI-assisted workflows | 📚 Claude Code Docs ↗📚 Anthropic – Building Effective Agents ↗ | |
| session 202 | Capstone architecture | Combine agents + RAG + APIs + deployment | 📚 Made With ML – MLOps Course ↗📚 The Twelve-Factor App ↗ | |
| session 203 | Capstone build | Implement the full production-style system | 📚 Made With ML – MLOps Course ↗📚 The Twelve-Factor App ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 204 | Capstone release | README; architecture; tests; demo; limitations; live URL | 📚 Made With ML – MLOps Course ↗📚 The Twelve-Factor App ↗ |
Phase 12: DSA + System Design + Interviews + Career
| Done | Topic | Focus | Study in Detail | Learning Resources |
|---|---|---|---|---|
| session 205 | Big-O | Time/space complexity; common patterns | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 206 | Arrays | Array operations; traversal; searching | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 207 | Strings | String patterns; frequency maps | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 208 | Hashmaps | Hashing; lookup; counting | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 209 | Two pointers | Pattern recognition and practice | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 210 | Sliding window | Fixed and variable windows | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 211 | Recursion | Base cases; recursive problem solving | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 212 | DSA practice | 8–10 easy problems across core patterns | 📚 NeetCode (structured practice) ↗📚 freeCodeCamp – Big-O Notation ↗ | |
| session 213 | System design | Services; APIs; databases; scaling basics | 📚 System Design Primer ↗📚 ByteByteGo – System Design Blog ↗ | |
| session 214 | Scale RAG | Design a RAG chatbot for 10k users | 📚 System Design Primer ↗📚 ByteByteGo – System Design Blog ↗ | |
| session 215 | Architecture explanation | Explain tradeoffs; bottlenecks; reliability | 📚 System Design Primer ↗📚 ByteByteGo – System Design Blog ↗ | |
| session 216 | Behavioral interviews | STAR framework; five project stories | 📚 Tech Interview Handbook – Behavioral ↗📚 Chip Huyen – ML Interviews Book ↗ | |
| session 217 | GenAI interview 1 | RAG vs fine-tuning; embeddings; hallucination | 📚 Tech Interview Handbook – Behavioral ↗📚 Chip Huyen – ML Interviews Book ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. | |||
| session 218 | GenAI interview 2 | Prompt injection; agents; tool calling; evaluation | 📚 Tech Interview Handbook – Behavioral ↗📚 Chip Huyen – ML Interviews Book ↗ | |
| session 219 | GenAI interview 3 | Deployment; Docker; CI/CD; observability | 📚 Tech Interview Handbook – Behavioral ↗📚 Chip Huyen – ML Interviews Book ↗ | |
| session 220 | Portfolio | Polish GitHub; READMEs; architecture diagrams | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ | |
| session 221 | LinkedIn/networking | Profile positioning; outreach; networking | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ | |
| session 222 | Portfolio site | Build a portfolio site with live project links | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ | |
| session 223 | Mock interview | Technical + behavioral mock interview | 📚 Tech Interview Handbook – Behavioral ↗📚 Chip Huyen – ML Interviews Book ↗ | |
| session 224 | Final showcase | Present projects; live deployment; next-step plan | 📚 freeCodeCamp – Developer Portfolio Guide ↗📚 GitHub – Personalizing Your Profile ↗ | |
| 🌿 Rest / Catch-up | No new material. Re-run code from memory, fix anything broken, catch up on lagging work, or rest. |
📚 How to Use the Free Resources
Open the resource attached to each session, study the relevant section, then immediately build the session's task. Most links are official documentation, free interactive courses, or free open-source learning material. Some platforms may offer optional paid extras; the linked learning material itself is intended to be free.
1. Learn
Use the linked tutorial/course section.
Use the linked tutorial/course section.
2. Build
Write the code yourself—don't just watch.
Write the code yourself—don't just watch.
3. Prove
Commit the work to GitHub and add it to the portfolio.
Commit the work to GitHub and add it to the portfolio.
Portfolio Finish Line
1. Python/API Automation
2. Docker + Airflow Data Pipeline
3. RAG Knowledge Assistant
4. Secure AI Automation Agent
5. Advanced RAG Evaluation Project
6. Production GenAI Capstone
The combined curriculum deliberately starts with the original job-ready foundations, then layers advanced GenAI engineering topics from the second course instead of replacing the fundamentals.