Build Projects · Guide
Build AI Projects: Hands-On Guides
Learn by building — RAG apps, tool-calling chatbots, agents, eval harnesses, model serving.
The fastest way to learn AI engineering is to build. This guide is a set of end-to-end projects: a RAG app with LangChain or LlamaIndex, a tool-calling chatbot, an agent with LangGraph, an evaluation harness with promptfoo, adding memory and observability to an agent, and serving models with vLLM or Ollama.
Generate your own lesson →What you'll learn
- Serve a Local LLM with Ollama
- Add Observability with Langfuse
- Build an Evaluation Harness with promptfoo
- Add Memory to an Agent
- Build a Document Q&A Bot
- Build a Tool-Calling Chatbot
- Build a RAG App with LlamaIndex
- Build an Agent with LangGraph
- Deploy an Open Model with vLLM
- Build a RAG App with LangChain
Lessons in this guide (10)
Serve a Local LLM with Ollama
Run a local model API and connect it to a simple app workflow.
Add Observability with Langfuse
Trace model calls, retrieval, tools, scores, and costs end to end.
Build an Evaluation Harness with promptfoo
Turn prompts and expected behavior into repeatable tests.
Add Memory to an Agent
Add thread state and long-term memory without confusing memory with facts.
Build a Document Q&A Bot
Assemble ingestion, retrieval, prompting, citations, and answer validation.
Build a Tool-Calling Chatbot
Define functions, execute calls safely, and return tool results to the model.
Build a RAG App with LlamaIndex
Load docs, index chunks, query with sources, and evaluate retrieval.
Build an Agent with LangGraph
Create a stateful tool-using agent with nodes, edges, and checkpoints.
Deploy an Open Model with vLLM
Serve an open model with batching, streaming, and production checks.
Build a RAG App with LangChain
Wire loaders, retrievers, prompts, and model calls into a grounded Q&A flow.
Frequently asked questions
How do I build a RAG app?
Ingest and chunk your documents, embed the chunks into a vector store, then at query time retrieve the top matches and pass them to the LLM as context with an instruction to answer only from the sources and cite them.
What's the best first AI project?
A document Q&A / RAG chatbot over a small set of your own docs. It touches embeddings, vector search, prompting, and grounding — the core skills — without needing to train anything.
How do I build an AI agent?
Start with an LLM, define a few typed tools it can call, and run a loop: send the prompt + tool schemas, execute any tool the model requests, feed the result back, and repeat until it returns a final answer.