https://melwis880.github.io/Recent content on M. Meriç OrduHugoen-USFri, 09 Oct 2026 00:00:00 +0300https://melwis880.github.io/post/n8n-organizer-case-study/Fri, 09 Oct 2026 00:00:00 +0300https://melwis880.github.io/post/n8n-organizer-case-study/<p><em>This is my own tool, not a client project. The workflows belong to the public <a href="https://github.com/Zie619/n8n-workflows">Zie619/n8n-workflows</a> collection, not to me. Full write-up and code: <a href="https://github.com/Melwis880/n8n-organizer">github.com/Melwis880/n8n-organizer</a>.</em></p> <h2 id="the-problem">The problem</h2> <p>When scoping an automation project, the useful question is &ldquo;what has already been built for this?&rdquo; A public library of n8n workflows answers it, but only if you can search it. The collection has 2,057 JSON files in 187 folders. Raw n8n JSON is long, full of node parameters and canvas positions, and some files are copies of others. Loaded as-is into a notebook tool like NotebookLM, it means hundreds of sources and a lot of noise.</p> <p>The goal: a few large, clean sources, each workflow described the same way, with a category you can trust and see the reason for.</p>https://melwis880.github.io/post/flx-case-study/Thu, 08 Oct 2026 00:00:00 +0300https://melwis880.github.io/post/flx-case-study/<p><em>This is my own tool, not a client project. Full write-up and code: <a href="https://github.com/Melwis880/freelancer-cli">github.com/Melwis880/freelancer-cli</a>.</em></p> <h2 id="the-problem">The problem</h2> <p>AI and automation jobs on Freelancer.com are buried in noise. A search for n8n or LangChain also returns logo design, translation and data-entry jobs. Finding the few worth bidding on meant running the same searches by hand and re-reading jobs I had already seen.</p> <p>The next step, an agent that drafts proposals, needed more than a browser tab: clean, structured, de-duplicated data it can trust.</p>