LESSON 02 / 215·2 min readFoundation

Priority key

ReferenceReference guide

Words made simple

A few useful meanings before you read the explanation.

API: A way for one piece of software to ask another for data or an action. A claims API might return the current status of a claim.
LLM: A model trained to work with language. It can write or summarize text, but its answer still needs checking against reliable information.
Embedding: A list of numbers that represents the meaning of some content. Similar meanings can produce nearby lists of numbers.

More words from this lesson

Vector: An ordered list of numbers. An embedding is a vector used to represent content for tasks such as similarity search.
RAG: Find relevant information first, then give it to a model to help answer the question. The answer is only as reliable as the information and checks used.
Structured output: An answer organized into specified fields, such as claimId and status, instead of only free-form text.
Tool calling: The model proposes using a named function and supplies its inputs. Application code checks permissions and runs the function.
Agent: An application that uses a model to choose its next action within defined limits. It can use tools and continue through several steps.

Priority	Topics
🔴 MUST KNOW	LLM APIs, prompting, structured outputs, tool calling, embeddings, vector search, RAG, LangChain, LangGraph, agents, MCP, Python basics, FastAPI, MERN integration, security, guardrails, evaluation, observability
🟠 SHOULD KNOW	Microsoft Agent Framework, OpenAI Agents SDK, multi-agent systems, orchestration, Temporal, Redis/BullMQ, memory, hybrid search, reranking, agentic RAG, gateways, routing, cost optimization
🟡 GOOD TO KNOW	Multimodal applications, voice agents, local LLMs, Ollama, Hugging Face
🟢 ADVANCED	Fine-tuning, LoRA, QLoRA, vLLM, GPU optimization

PAUSE & RECALL