Patterns
Prompt Chaining in Python: A Runnable Claude Tutorial (2026)
A code-first prompt chaining tutorial: build a gated Python pipeline with the Claude API, add pure-Python and LLM gates, and fail fast before wasting tokens.
7 min read146
Author
Ren Okabe
Ren builds agent infrastructure and writes copy-paste tutorials for engineers shipping LLM tool-use systems.
MCP
How to Add an MCP Server to Claude Desktop (2026)
The exact claude_desktop_config.json setup to connect a local MCP server to Claude Desktop, verify it with the MCP Inspector, and fix a server that will not show up.
8 min read228
Evaluation
LLM as a Judge: Score AI Agent Outputs with Claude (2026)
A minimal, framework-free LLM-as-a-judge harness in Python on Claude: rubric design, pointwise and pairwise scoring, and fixes for position, verbosity, and self-preference bias.
7 min read253
Testing
AI Agent Testing: A Runnable Pytest and LLM-Judge Harness (2026)
You cannot unit-test an agent like a pure function. Build a two-layer pytest harness: deterministic tool-call assertions plus an LLM-as-judge grader, a frozen eval dataset, and a CI gate. Runnable Python, no eval framework required.
6 min read179
Patterns
Agentic Workflow Patterns in Python (2026)
Five reusable agentic workflow patterns, built from scratch in Python with runnable code and a start-simple rule.
5 min read174
From scratch
Self-Hosted AI App Builder: Run Your Own (2026)
A hands-on 2026 tutorial: stand up your own self-hosted, open-source AI app builder from the ai-app-builder-open repo, with one API key and code you fully own.
10 min read231
AI agents
Remote MCP Server Tutorial (2026): Serve Tools over Streamable HTTP
A runnable 2026 tutorial for turning a local MCP server into a remote one over Streamable HTTP. Serve tools with FastMCP, test the endpoint with curl and MCP Inspector, validate the Origin header, add a bearer token, then connect Claude. Covers the Mcp-Session-Id requirement and the DNS-rebinding gotcha the docs warn about but most walkthroughs skip.
8 min read272
AI agents
LangGraph Human-in-the-Loop (2026): Pause an Agent for Approval with interrupt()
A runnable LangGraph human-in-the-loop tutorial for 2026: pause an agent mid-run with interrupt(), review the proposed action, then approve, edit, or reject it with Command(resume=...). Includes the checkpointer requirement and the re-run-from-the-top gotcha that breaks most tutorials.
5 min read288
AI agents
How to Build an MCP Server in Python with FastMCP (2026)
A runnable 2026 tutorial: build a write-capable MCP server in Python with FastMCP and the official MCP SDK. Add tools with @mcp.tool(), back them with SQLite, test in the Inspector, and connect it to Claude for Desktop.
7 min read146
AI agents
AI Agent Web Search: Build a Web Search Agent in Python (2026)
A runnable 2026 tutorial: give an AI agent web search in Python with the Claude web_search server tool. Read citations, cap cost with max_uses, filter domains, and go multi turn.
6 min read142
From scratch
AI Agent Long-Term Memory in Python (2026): A Framework-Free Guide
A runnable 2026 tutorial: give a Claude agent long-term memory that survives across sessions using SQLite, embeddings, and cosine retrieval. No LangChain, FAISS, or vector database.
9 min read162
AI agents
LangGraph Tutorial: Build a Graph Agent in Python (2026)
A hands-on LangGraph tutorial for 2026: build the same tool-using AI agent two ways, with the five-line create_agent helper and as an explicit StateGraph you can customize. Fully runnable Python.
5 min read209