Automate repeated site content updates

A developer used an agent to turn one podcast-page update into a repeatable workflow for their Nuxt site.

Done with Custom agentยท Intermediateยท Jan 2026

What they did
Debbie O'Brien saved her podcast-page instructions as a Goose recipe that accepts the episode link as an input. When run, Goose used Playwright MCP to inspect the episode page, Cloudinary MCP to send over the image, and GitHub MCP to create a pull request. It also started the local app, confirmed the podcast page, and left the code for her to review.
How it went
The process let new podcast entries and their images flow into her Nuxt site, then into a merged pull request after she approved it. She said building the automation took longer than updating one entry manually, and she has not tried it with a big list of URLs.
Tips
A setup like this is best for a task you expect to repeat, but expect an upfront time cost. Keep a manual check in the loop, especially for uploaded assets such as image links.

Try it yourself with Claude Code

I have a website repo at [repo path or URL]. Help me build an agent workflow that updates [content type] from [source]. Make it reusable, and use an MCP server if that makes the job easier. Show me the changes as a diff first, then stop and wait for approval before you commit, open a pull request, upload files, send anything out, delete anything, or publish the result. After approval, run it once for [input] and verify that [page or section] reflects the update.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on dev.to โ†—

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.