---
title: "LangGraph: Explicit State Graphs for Production AI Workflows"
description: "Aleksandr Filippov builds production AI systems on LangGraph — compiled state graphs with conditional routing, checkpointed state across turns, middleware, and human-in-the-loop interrupt-and-resume — from a shipped localization workflow and a retrieval pipeline to a configurable agent runtime."
date: "2026-08-27T07:00:00Z"
last_updated: "2026-08-28"
build_time: "2026-08-28T03:11:43Z"
skill_name: "LangGraph"
skill_description: "Compiled LangGraph state graphs with conditional routing in shipped systems, plus checkpointed state, middleware, and human-in-the-loop interrupts — built and tested — feeding an agent platform in development where agents are stored configurations."
skill_category: ["ai-engineering","ai-platforms-agents"]
since: "2025-02-21"
last_used: "2026-08-28"
related_skills: ["artificial-intelligence","llm-engineering","python","rag-enterprise-search","mcp","fastapi"]
related_projects: ["aila","air-api","managed-agent-platform","mcp-context-server"]
related_experience: ["ai-product-manager-at-spotware"]
keywords: ["LangGraph","LangChain","State Graph","Agent Orchestration","Conditional Routing","Checkpointing","Human-in-the-Loop","Interrupt and Resume","Multi-Agent Systems","Agent Runtime","LangSmith","Python"]
license: "https://creativecommons.org/licenses/by/4.0/"
canonical: "https://www.alexfeel.info/skills/langgraph/"
---

I reach for LangGraph when a workflow deserves to be **a graph you can read instead of a prompt you can only hope about**. Two shipped systems run on it. A localization workflow moves every request through explicit nodes — parse, extract terminology, retrieve approved terms and translation memory, translate, optionally proofread, write back to the stores — so each step can be observed, skipped, or improved on its own. A retrieval platform compiles a `StateGraph` where language detection, query decomposition, multi-rewrite expansion, ensemble retrieval, reranking, and parent-document resolution are separate nodes with **conditional edges** — a query already in the corpus language skips translation, a simple one skips decomposition — and every model-calling node validates structured output and carries a fallback. Both have moved with the framework: the pipeline runs on the current LangChain/LangGraph v1 ecosystem, migrated as the interfaces changed rather than pinned to where they started.

Past the pipeline work sits the agent side of the framework: **checkpointed state across conversation turns, middleware for summarization and task planning, and a human-in-the-loop interrupt-and-resume path** — built and tested, ready for the first tool that should require a person's approval before it acts. That research led directly into the agent platform I am building now, where agents run as LangGraph graphs on a self-hosted Agent Protocol server, PostgreSQL holds threads and checkpoints, and any team's agent is a stored, strictly typed configuration rather than a separate codebase. LangSmith tracing runs over the production graphs, so the framework's structure pays off twice — once in design clarity, once in observability. The systems are listed in the **Related Projects** and **Related Experience** panels above.


## Site index

- [llms.txt](https://www.alexfeel.info/llms.txt)
- [Complete index](https://www.alexfeel.info/llms-index.txt)