Tatendaz

Langchain Fde Curriculum — AI skill for Claude Code

AI community

A 6-phase, deliverable-driven curriculum for building and shipping production-grade AI agents on the LangChain / LangGraph / LangSmith stack — as a forward-deployed-engineering service.

How to install Langchain Fde Curriculum

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Tatendaz/langchain-fde-curriculum and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Langchain Fde Curriculum does

A 6-phase, deliverable-driven curriculum for building and shipping production-grade AI agents on the LangChain / LangGraph / LangSmith stack — as a forward-deployed-engineering service.

Alternatives in AI

  • macOS App Skills — AI coding agent skills for building, shipping, and maintaining native macOS apps 657 ★
  • Module Feature — Add a new feature (model + service + controller + views + routes + tests) to an existing module 407 ★
  • Claude Hub — by Claude Did This - A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered c 393 ★

README

Production-Grade AI Agents — An FDE Curriculum

Seven phases, seven shipped artifacts, and a mastery gate for each one. Go from *"I use LLMs"* to *"I can design, evaluate, and ship production agents on the LangChain / LangGraph / LangSmith stack — and deliver them as a service."*

[![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-blue.svg?logo=python&logoColor=white)](pyproject.toml) [![LangChain 1.x](https://img.shields.io/badge/LangChain-1.x-1C3C3C.svg?logo=langchain&logoColor=white)](https://docs.langchain.com/oss/python/langchain/overview) [![LangGraph 1.x](https://img.shields.io/badge/LangGraph-1.x-1C3C3C.svg)](https://docs.langchain.com/oss/python/langgraph/overview) [![LangSmith](https://img.shields.io/badge/observability-LangSmith-1C3C3C.svg)](https://smith.langchain.com) [![uv](https://img.shields.io/badge/packaged%20with-uv-DE5FE9.svg?logo=uv&logoColor=white)](https://docs.astral.sh/uv/) [![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](LICENSE)

**Time:** ~60–70 focused hours · 8 weeks at ~8–9 hrs/week · **hard cap: 2 months** **Cost:** ~$0 on the default path — local [Ollama](https://ollama.com) models + LangSmith's free tier ([the one exception](#what-it-costs-to-run)) **You finish with:** a deployed, evaluated, monitored capstone agent + a case study + a demo video — a portfolio that answers the question every FDE interview and client call comes down to: *"How do you know it works?"*

flowchart LR
    P0["0 · Traced hello world"] -->|gate| P1["1 · First agent"]
    P1 -->|gate| P2["2 · LangGraph + HITL"]
    P2 -->|gate| P3["3 · RAG, memory, MCP"]
    P3 -->|gate| P4["4 · Evals + CI"]
    P4 -->|gate| P5["5 · Deploy + harden"]
    P5 -->|gate| P6["6 · Capstone + FDE drills"]

Why this curriculum exists

The LangChain ecosystem moves fast, so this curriculum optimizes for **durable skills** — agent architecture, evaluation, observability, productionization — over memorizing today's API sur