AI Marketplaces Leaderboard

Agent Router

ChatGPT plugin

Plan reliable AI workflows

View in ChatGPT directory
Featured
No

not on the featured shelf

Movement

From our daily snapshots over the last 30 days.

Rank by placement

#6101of 7,033641places up24h—7d
#6,037#6,230#6,423#6,616Sep 18Sep 24Sep 30Oct 6Oct 12Oct 17

Rank in Productivity

#1399of 1,614147places up24h—7d
#1,385#1,430#1,475#1,520Sep 18Sep 24Sep 30Oct 6Oct 12Oct 17

In its category

How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.

Productivity1,399th of 1,614 by placement
#PluginPosition7d
1397Dispro#6092—
1398IVOA#6094—
1399Agent RouterThis page#6101—
1400Tango#6103—
1401JobFinder#6107—

All 1,614 Productivity plugins

Turn incomplete AI and automation ideas into practical, implementation-ready plans. Agent Router asks focused questions, determines whether AI or an autonomous agent is actually needed, recommends the simplest reliable architecture, defines human approvals, safeguards, source authority, failure handling, and test cases, and explains the result in plain language. It is designed for non-technical and technical users planning assistants, workflows, retrieval systems, or agents. Agent Router is an advisory planning tool: it does not send emails, modify external systems, execute business processes, or make legal, financial, or other high-impact decisions.

Example prompts

  • “Help me clarify an AI or automation idea and recommend the simplest reliable approach.”
  • “Critique my agent idea and tell me whether I actually need an agent.”
  • “Turn my validated idea into an implementation and evaluation plan.”

Skills

  • agent-router

    Use when the user wants to evaluate, route, design, critique, specify, or stress-test an AI automation or agent idea. It distinguishes AI usefulness from agentic autonomy, chooses the simplest robust pattern, treats untrusted content as data, separates entity resolution from business policy, resolves source authority explicitly, models write semantics and multi-system partial failure, and produces implementation-ready specifications and eval plans.

Categories
Made by
Alexander Würtz · Website
Sign-in
On Install
Capabilities
AI idea evaluation, Architecture recommendations, Implementation planning, Evaluation planning
Availability
Available
Version
1.0.0
Keywords
ai planning, automation, agent architecture, evaluation
Created
October 7, 2026
More info
Sponsorship
Promote this plugin