Guides by level
Advanced guides
APIs, MCP, retrieval, and evals for developers and AI engineers. Every term is explained the first time it shows up.
11 guides
AdvancedClaudeBuilding
Call the Claude API in Python and cut costs with prompt caching
Get an API key, make your first Claude Messages API call in Python, then add prompt caching so repeated long prompts cost less and run faster.
About 30 minutes using Claude Console, Claude API docs
AdvancedClaudeBuilding
Build your first MCP server in Python and use it in Claude Desktop
Write a small Model Context Protocol server with the official Python SDK, expose a tool, and connect it to Claude Desktop so Claude can call it.
About 35 minutes using MCP docs, Claude Desktop
AdvancedGrokBuilding
Build a simple RAG pipeline with the xAI Grok API
Answer questions from your own documents: split them into chunks, retrieve the best matches, and have Grok answer with citations via the xAI API.
About 40 minutes using xAI API docs, xAI Console
AdvancedGeneralBuilding
Write simple evals to test your LLM app before you ship changes
Build a small eval set, score outputs with code checks and an LLM grader, and rerun it after every prompt or model change to catch regressions.
About 40 minutes using Claude API docs, OpenAI API docs
AdvancedClaudeBuilding
Get started with Claude Code: fix a bug from your terminal
Install Claude Code, sign in, have it explain your project, plan and fix a real bug, and save project rules in CLAUDE.md so the next session starts smarter.
About 25 minutes using Claude Code quickstart, Claude Code setup, Permission modes, CLAUDE.md and memory
AdvancedAgentsBuilding
The Software Factory pattern: how a ticket becomes a reviewed PR
A spec-driven, test-driven production line for AI coding agents: spec, then tests, then code, then validate, then review, then merge. An overview of the whole pattern.
About 15 minutes using AGENTS.md format, Model Context Protocol
AdvancedAgentsBuilding
Write an AGENTS.md Factory Manager that defines your whole SDLC
Turn AGENTS.md into the Factory Manager: one file that defines the spec-first, test-first production line, its gates, the artifacts each stage leaves, and what agents may never do.
About 30 minutes using AGENTS.md format
AdvancedAgentsBuilding
Create global sub-agents for every station of the Software Factory
Write reusable sub-agents for planning, exploring, research, coding, validation, tracker updates, code review, and PR fixes, each with one job and a compact handoff.
About 35 minutes using Claude Code sub-agents, AGENTS.md format
AdvancedAgentsBuilding
Connect Jira through the Atlassian MCP so tickets flow through the factory
Hook the Software Factory to Jira with Atlassian's Rovo MCP server: read a ticket, then post living Plan, Test Results, Execution Summary, and Handoff comments.
About 25 minutes using Atlassian Rovo MCP Server, Getting started guide
AdvancedAgentsBuilding
Read and write PR comments with the GitLab and Bitbucket MCP servers
Let the factory's review agents post a structured code and security review, fix findings one at a time, and record a disposition on GitLab or Bitbucket, never merging.
About 30 minutes using GitLab MCP server, Atlassian Rovo MCP (Bitbucket Cloud)
AdvancedAgentsBuilding
The developer's new job: review the factory's artifacts before you merge
In the Software Factory, the developer is the final gate. A checklist for reviewing the spec trail, test evidence, review comments, and disposition report before merging.
About 15 minutes using AGENTS.md format