AI Engineering Practice

Build the parts of an AI application yourself: prompts and evaluation, retrieval, memory and context, and agents that call tools.

6 paths · 66 challenges

More soon
agentic-full-stack-web-development
4 challenges · 1 module
DjangoDjango.Net.NetMernMernReactReactSpringbootSpringboot
The Agent-Ready Repository
memory-context
10 challenges · 2 modules
linux-cliLinux CLI
Context Management
ai-agents
23 challenges · 4 modules
linux-cliLinux CLI
Tool Calling & Agent Loop
More soon
mcp
5 challenges · 1 module
linux-cliLinux CLI
Server Tools, Resources & Prompts
prompt-engineering
12 challenges · 2 modules
Linux CLILinux CLI
Prompt Engineering
More soon
rag
12 challenges · 2 modules
python-312Python 3.13
Embeddings & Vector Search

From the blog

1
Model Context Protocol Update: Stateless MCP Is HereModel Context Protocol’s latest update replaces session-bound transport with a stateless core, MRTR, routing headers, and sharper migration boundaries.

Frequently asked questions

3

Which paths are in this category?

6 paths: Agentic Full-Stack Web Development (4 challenges), AI Context & Memory Engineering (10 challenges), Build an AI Agent From Scratch (23 challenges), Model Context Protocol (MCP) (5 challenges), Prompting & Evaluation (12 challenges) and Retrieval-Augmented Generation (RAG) (12 challenges).

How many challenges are there?

66 challenges across 12 modules.

Do I need to install anything?

No. Every challenge runs in a browser-based IDE with everything already set up, and your code is graded automatically against a test suite.

We use cookies that are necessary to run Staffcoder, and optional analytics cookies to see which pages get used. Analytics stays off unless you accept. Read our Cookie Policy.