Intent Classification and Routing in a Multi-Agent Desktop App
Melvin Vivas · X post · 2026-09-18 · Open on X
Topics: AI Agents, Tool Use & MCP, AI System Design & Architecture · Level: intermediate
Summary
Melvin Vivas describes a routing pattern in his Coworker app. A generalist agent called Jev, from TypeSafe AI, works out what the user wants, classifies the task and hands it to the bot best suited to handle it. This is a short example of a router or orchestrator in a multi-agent system.
Key points
- The user asks one generalist entry point instead of choosing a specialist bot.
- Jev works out the user's intent and classifies the task.
- The classified task goes to the specialist bot best able to handle it.
- This is the common router/orchestrator pattern in multi-agent systems.
Resources mentioned
- Jev (TypeSafe AI) · tool · typesafe.ai · free
TypeSafe's new post-training algorithm for calibrated, confidence-scored decisions, pitched as a replacement for RLHF.
Also in: JevDev: Open-Source UI Tool for Experimenting with Jev (Typesafe.ai) (Melvin Vivas on X · notes), jev-dev: A UI Tool to Keep Run History When Experimenting with Jev (Melvin Vivas on X · notes), JevDev: Open-Source UI for Experimenting with Jev by Typesafe.ai (Melvin Vivas on X · notes), Building a Jev Session-History Tool with Codex and Astra (Melvin Vivas on X · notes) and 7 more - TypeSafe AI (@typesafeai) on X · person · x.com · free
Company that built Jev and the RLCD training method, focused on reliable models for automation.
Also in: Decision Model Rankings by Spend and Token Share (Melvin Vivas on X · notes), JevDev v0.1.3: Free UI Environment for Experimenting with Jev Models (Melvin Vivas on X · notes), Using Jev (TypeSafe AI) as a Decision Model for Email Classification (Melvin Vivas on X · notes), Building a Jev Session-History Tool with Codex and Astra (Melvin Vivas on X · notes) and 9 more - Coworker (donvito/coworker) · repo · github.com · free
The creator's agent/bot tool. Version 0.7.0 adds a Primary Bot, free web search, an activity dashboard and support for open models through OpenRouter.
Also in: Coworker: a local-first desktop AI coworker that works with any model (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Coworker v0.7.2: Open-Source Desktop AI Assistant (Melvin Vivas on X · notes) and 59 more
Try this
- Build a generalist agent that classifies each user request and routes it to a specialist sub-agent.
More in AI Agents, Tool Use & MCP
- Running Gemma4-E2B tool calling locally on an iPhone
- Jev + WebMCP Solves 100% of Benchmark Tasks at About 112× Lower Cost
- Agent Monitor: Visualize Codex and Claude Code Subagents, Traces and Costs
- Coworker: Open-Source Desktop App for AI Agents, with Jev
- Agent Monitor: Visualize Coding-Agent Subagents, Traces and Costs
- Coworker: an open-source AI agent desktop app for non-technical users