Projects

Seven self-contained builds, from your first prompt to a coordinated team of agents.

#1 primer beginner Prompt Engineering

01 · Prompt Playground

Discover how a prompt's structure — system persona, user request, and grounding context — shapes a model's output.

system promptgroundingfew-shot
#2 primer beginner Semantic Search

02 · Embeddings & Vector Search

Turn text into vectors and rank documents by cosine similarity — the retrieval engine behind every RAG system.

embeddingscosine similaritytop-k
#3 primer beginner Function Calling

03 · Tool / Function Calling

Let the model decide when to call a tool, run it, and fold the result back into the answer — the loop that creates agents.

tool usefunction callingagent loop
#4 core intermediate RAG

04 · Retrieval-Augmented Generation (RAG)

Retrieve relevant context, then generate a grounded answer. The canonical pattern for trustworthy LLM answers.

retrieve-then-readgroundingcontext window
#5 core intermediate Agentic RAG

05 · Agentic RAG

Add a reasoning loop around retrieval: judge relevance, rewrite the query, and retrieve again before answering.

self-correctionquery rewritingrelevance grading
#6 core advanced Multi-Agent

06 · Multi-Agent System

Split a task across specialised agents — researcher, analyst, writer — that hand off to one another.

specialisationhandoffpipeline
#7 core advanced Agent Teams

07 · Agent Teams & Orchestration

A supervisor routes each task to the right specialised team, then reviews and merges the result.

supervisorroutingdelegation