switchboard-100.pages.dev
Human + agent control center for LLM provider budgets, priced model catalogs and routing policy. Agent-ready via WebMCP.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 11 · Act 3 · Transact 1 · Score: Not yet scored
Tool inspector
find_waste
Lint the live policy against the measurements and report everything wrong with it. Each finding carries a kind: "spend" means money is being wasted right now (a routed model that never succeeds, a class routed to something dearer than a compliant alternative, a model over $1 per 1000 delivered outputs that still fails its gates); "risk" means a fragility rather than a cost (a class with one or zero eligible models); "hygiene" means a data gap (catalogue entries priced but never measured). Only "spend" findings carry estimatedMonthlySavingsUsd — do not present risk or hygiene findings as costs. Every finding cites the numbers behind it. Start here when the operator asks an open question like "where is my money going", but say plainly that these are projections from declared volumes, not billed spend.
Input schema
No input properties (empty object).
Raw JSON schema
{
"type": "object",
"properties": {}
}
Similar websites
reloadium.com
Paste a topic, URL, or PDF/TXT/MD — get a multi-episode AI podcast with audio, transcripts, timelines and quizzes. 60+ languages.
api.lmm.best
Connect AI models, tools and applications with LMM Forge. Explore model access, developer guides and open-source collaboration.
deskintab.dgkhan08.workers.dev
An operating system in your browser, where you and your AI agent share apps, files, and projects through WebMCP.
webmcp.agentsdesk.dev
Meridian Ops