Drydock.si
Submit a tool

// guides · tutorials

Tutorials

This topic holds the Drydock tutorials on AI agents and the infrastructure behind them: longer builds that take you from an empty project to a working result, with the code and commands shown in full. Each tutorial names the versions it was written against and links to the official documentation for every library it uses.

There are 7 guides here, published from Oct 05, 2026 to Nov 13, 2026. The tools they cover most often are Model Context Protocol, LangGraph and Claude Code.

How to choose: start with the tutorial that matches the framework you already use, since most of the work carries over. Check the versions near the top before you copy any code, because newer releases can rename functions or settings. Shorter tasks are covered in the how to guides, which are linked from each tutorial.

  1. 9 min readListen

    Build an MCP Server to Manage Cisco Devices

    How to build an MCP server to manage Cisco devices in Python with Netmiko: read only show tools, a guarded config tool, and when Cisco's own servers fit better.

  2. 8 min readListen

    How to Use Tavily in LangChain: Step by Step

    How to use Tavily in LangChain: install langchain-tavily, set your API key, add TavilySearch to create_agent, pin costly settings and handle errors the agent sees.

  3. 10 min readListen

    Vercel AI SDK Guide: Build an Agent With AI SDK 7

    The Vercel AI SDK is a free, open source TypeScript toolkit for LLM apps and agents. AI SDK 7 changes, a tested ToolLoopAgent, streaming UI, MCP and costs.

    · updated

  4. 9 min readListen

    How to Build a RAG Pipeline with LangGraph

    How to build a RAG pipeline with LangGraph: index your docs, wire retrieve and generate nodes, add a grading loop with a retry cap, then turn it into an agent.

    · updated

  5. 10 min readListen

    How to Build an AI Agent from Scratch in Python

    How to build an AI agent from scratch in Python: a tool loop, safe file tools, approvals, a step cap and memory in about 125 lines, on OpenAI or Ollama.

  6. 10 min readListen

    Agent Skills Guide: How to Write a SKILL.md

    Agent skills explained: how SKILL.md works, where Claude Code, Codex, Cursor, Copilot and Gemini CLI load skills, how they differ from MCP, plus a template.

    · updated

  7. 9 min readListen

    How to Build an MCP Server in Python (2026 Guide)

    Build a working MCP server in Python with the official SDK 2.x and the stateless 2026-07-28 spec, then connect it to Claude Code, Cursor, and VS Code hosts.

    · updated

All 100 guides →