In this guide, you will build a no-code blog-writing subagent in Langflow that writes posts in your website’s style. It runs locally, is free besides LLM calls, and can be triggered by Claude, Codex, or another coding agent once exported. The setup is a simple local flow, so you can get started without writing code or setting up a server.
published apr 29, 2026
Build a Custom Blog Writing Agent with No Code (langflow)
intermediateThe Rundown
Who This Is Useful For
- Marketers and creators who write repeat blog posts and want the same structure every time
- Anyone using Claude or another coding agent across multiple projects who wants to stop wasting context on the same writing task
- People curious about AI agents who want a simple local tool to understand how subagents and MCP tools work
What You Will Build
You will build a reusable blog-writing subagent that takes a topic, looks at one of your existing posts for style, and returns a new draft in that voice.
- A URL input for the reference post
- A text input for the new topic
- A prompt template that combines the style reference and topic
- A language model node
- A chat output
What You Need
- Langflow installed locally
- An OpenAI or Anthropic API key
- One strong blog post you want the agent to use as a style reference
- A test topic for the first draft
Going Further
- Once the flow works, you can export it as an MCP server and connect it to Claude. Claude can then call the flow as a tool whenever you need a blog draft in that style, while saving its context for higher-level work.
Pick a reference post that already sounds how you want future posts to sound. If the source post is weak, the draft will be weak too.