Build a Custom Blog Writing Agent With No Code (Langflow)

  • Intermediate
  • 5 steps
  • By The Rundown University

Learn how to build a no-code blog-writing subagent in Langflow that writes posts in your website’s style. You will produce a local flow that takes a reference blog post and a new topic, then returns a first draft. Once it works, you can export it as an MCP server so tools like Claude can call it instead of making you rewrite the same prompt repeatedly.

Step by step 5 steps

  1. Step 1 of 5

    Open Langflow and start from the Blog Writer template

    Download Langflow and open it on your computer. It runs locally, so you can build a custom subagent without setting up a server or writing code just to get started.

    In the project area, click New Flow, go to the content generation section, and choose the Blog Writer template.

    image-2190
    Templates are the fastest way to learn Langflow.

  2. Step 2 of 5

    Add your style reference and a topic input

    Start by changing the reference URL. Use one of your best blog posts so the flow has something real to imitate.

    The built-in crawler can follow more than one page. If you want a broader writing sample, point it at your blog index and increase the crawl depth to 2.

    Then add a text input called topic. The reference content shapes the style, and the topic input tells the model what to write next.

    image-2191
    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.

  3. Step 3 of 5

    Add your model provider and pick the model

    Open the language model settings and click Manage model providers. Add your OpenAI or Anthropic API key, then pick the model you want to run.

    image-2192

    The source test used Anthropic and OpenAI. You could also run a model locally with Ollama and use it in Langflow.

  4. Step 4 of 5

    Test the flow in Playground

    Once the reference URL and topic input are wired up, click Playground and test the flow with a topic.

    how to use AI for marketing

    Langflow will pull the reference content, feed the style and topic into the prompt, and return a first draft.

    Use this test to tighten the flow. If the draft is too generic, add clearer instructions into the prompt template.

    No em dashes. Keep it concise. Sound like our site.

    Add voice guardrails early. Short lines like these usually do more than a big abstract style paragraph.

    If you want better output later, add more sources or drop files into a knowledge base. You can also batch multiple article runs once the basic flow is working.

  5. Step 5 of 5

    Export the flow as an MCP Server for Claude

    If you want Claude to use this as a subagent, open Share and choose MCP Server.

    image-2193

    From there, connect it to Claude. Once it loads, Claude can call the flow as a tool whenever you need a blog draft in that style.

    Use Langflow for the repetitive subagent, then let Claude save its context for the higher-level work.

That's the whole workflow

Mark it complete to keep your progress. The background follows.

Keep learning with Rundown Pro

Guides stay free. This is what Rundown Pro adds:

  • Every course and recording
  • The Rundown Certified Operator program
  • Member perks

$29/mo, cancel anytime

Background and context

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 simple blog-writing subagent that takes a topic, looks at one of your existing posts for style, and returns a new draft in that voice.

image-2189
  • 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

  • After the flow works, 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.