Skip to content
CodeStoa
AI

AI Engineering

Build and measure LLM apps: evaluation, LangChain, LangGraph, prompt engineering, MCP and Claude, explained step by step with code.

Subdomains
6
Published
1 of 1 topics
Reading time
4 min

Subdomain

LLM Application Evaluation

Measuring LLM app quality: test sets, metrics, LLM-as-judge and regression checks.

1/1
  1. 01

    LLM Evals: Why "It Looks Good" Isn't Enough

    LLM evals are systematic, repeatable tests that judge an LLM app against clear criteria. Learn why spot checks fail, how evals differ from classic tests, and the workflow to run them.

    Beginner4 min readOct 19, 2026 Video

Subdomain

LangChain

Composing LLM apps from models, prompts, tools and retrievers.

Coming soonSub-topics for LangChain are on the way.

Subdomain

LangGraph

Building stateful, multi-step agents as graphs.

Coming soonSub-topics for LangGraph are on the way.

Subdomain

Prompt Engineering

Writing prompts that get reliable, high-quality results from LLMs.

Coming soonSub-topics for Prompt Engineering are on the way.

Subdomain

MCP

The Model Context Protocol: connecting LLMs to tools and data.

Coming soonSub-topics for MCP are on the way.

Subdomain

Claude

Building with Claude: the API, tool use, agents and Claude Code.

Coming soonSub-topics for Claude are on the way.