<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Routing on Tokenise</title><link>https://tokenise.rosvetic.com/tags/routing/</link><description>Recent content in Routing on Tokenise</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Thu, 29 Oct 2026 17:50:00 +0000</lastBuildDate><atom:link href="https://tokenise.rosvetic.com/tags/routing/index.xml" rel="self" type="application/rss+xml"/><item><title>Jev won't write your code. Here's where it fits in an agent pipeline anyway</title><link>https://tokenise.rosvetic.com/posts/jev-decision-model-agent-pipeline-fit/</link><pubDate>Thu, 29 Oct 2026 17:50:00 +0000</pubDate><guid>https://tokenise.rosvetic.com/posts/jev-decision-model-agent-pipeline-fit/</guid><description>&lt;p&gt;Jev doesn&amp;rsquo;t write code, doesn&amp;rsquo;t chat and doesn&amp;rsquo;t summarise anything. TypeSafe AI&amp;rsquo;s own docs say so, and add that it isn&amp;rsquo;t a model to swap in behind Claude Code, Cursor or Copilot. That sounds like a reason to skip it. It&amp;rsquo;s closer to the opposite: the useful part of Jev is the part of your pipeline that currently burns a full LLM call to answer a question with three possible answers.&lt;/p&gt;</description></item></channel></rss>