https://blog.rodolpheg.xyz/tags/llm/Recent content in LLM on RORO's blogHugoencontact@rodolpheg.xyz (0xRo)contact@rodolpheg.xyz (0xRo)Tue, 01 Sep 2026 00:00:00 +0000https://blog.rodolpheg.xyz/posts/the-model-proposes-the-engine-decides/Tue, 01 Sep 2026 00:00:00 +0000contact@rodolpheg.xyz (0xRo)https://blog.rodolpheg.xyz/posts/the-model-proposes-the-engine-decides/<p><img src="img/cat-meme-wave-emoji.gif" alt="Hi o/" loading="lazy"> </p> <p>Hi o/,</p> <p>Today I want to share where I am with <strong>sek</strong>. I already wrote about the project in <a href="https://blog.rodolpheg.xyz/posts/why-i-wanted-my-own-code-audit-tool/">another post</a> if you missed it. That one covers how the idea started and how I ended up building the tool. This post is about what happened when I started adding an agent to it.</p> <p><em>A technical look at SEK&rsquo;s deterministic-first agentic scan</em></p> <p>There is a point in every security tool project where somebody says: &ldquo;we should add an agent.&rdquo;</p>