Study plans
Week-by-week plans through the library, built from the free resources and posts of Bashiri Smith and Melvin Vivas. Pick the one that fits your time. In the library app, the Study plans tab lets you tick items off; the ticks are saved in your browser and shared with the other tabs.
- 1-month plan: the fast track
Build one portfolio project in four weeks: an assistant over your own documents that grows from a prompted LLM call to RAG, evals and tools, and ends as a deployed, traced API while you start applying.
- 2-month plan: the standard path
Eight weeks on one capstone, an assistant that answers questions about your own documents, from the foundations through RAG, agents, evals and deployment to a portfolio case study and the job search.
- 3-month plan: the thorough path
Twelve weeks through all sixteen topics on one project, an assistant over documents you know, that grows from a single LLM call into an evaluated, guarded and deployed RAG agent with a small fine-tuned router.
- Week 1: Map the role and plan
- Week 2: How neural networks learn
- Week 3: LLM fundamentals and APIs
- Week 4: Prompts and coding agents
- Week 5: Embeddings and vector search
- Week 6: RAG that holds up
- Week 7: Agents, tools and MCP
- Week 8: Evals and guardrails
- Week 9: Ship, trace and control cost
- Week 10: Fine-tuning and system design
- Week 11: Portfolio week
- Week 12: Job search and trends
- 6-month plan: from the ground up
Twenty-four weeks for people starting with little programming: a month of software basics (Python, Git, SQL and APIs), then the 3-month plan's capstone, an assistant over documents you know, with extra weeks for a web front end, data pipelines, production RAG, agent frameworks, Docker, the cloud, Kubernetes, system design and forward-deployed work.
- Week 1: Map the role and plan
- Week 2: Python for AI work
- Week 3: Git, GitHub and SQL
- Week 4: APIs and a Python backend
- Week 5: How neural networks learn
- Week 6: LLM fundamentals and APIs
- Week 7: Prompts and coding agents
- Week 8: A web front end for AI apps
- Week 9: Data pipelines
- Week 10: Embeddings and vector search
- Week 11: RAG that holds up
- Week 12: Production RAG and RAG evaluation
- Week 13: Agents, tools and MCP
- Week 14: Agent frameworks: LangGraph and MCP servers
- Week 15: Evals and guardrails
- Week 16: Docker and CI/CD
- Week 17: Ship, trace and control cost
- Week 18: Cloud fundamentals and infrastructure as code
- Week 19: Kubernetes and monitoring
- Week 20: Fine-tuning and system design
- Week 21: System design: services, auth and scale
- Week 22: Forward-deployed engineering and talking to users
- Week 23: Portfolio week
- Week 24: Job search and trends