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
check_compliance
Audit the live policy — or a candidate rule set if you pass one — against every constraint at once: latency ceilings, success-rate floors, quality gates, data-retention limits, the no-training-on-data requirement, AND the spend caps (TOTAL_BUDGET and PROVIDER_BUDGET blockers when projected spend exceeds a cap). Blockers mean the routing is not permissible as configured; warnings mean permissible but fragile. An empty blockers list is the bar a proposal should clear. Because spend is included, a clean result does mean the plan fits the operator's declared budget — but only the budget that is actually recorded, so if they stated a target in conversation, propose it via propose_budget_change first so it becomes auditable. simulate_policy returns this same verdict for a candidate; use this tool for the live policy.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
rules |
array | no | Candidate routing rules. One entry per traffic class you want to change; classes you omit keep their current rule. |
Raw JSON schema
{
"type": "object",
"properties": {
"rules": {
"type": "array",
"description": "Candidate routing rules. One entry per traffic class you want to change; classes you omit keep their current rule.",
"items": {
"type": "object",
"properties": {
"classId": {
"type": "string",
"description": "Traffic class this rule routes."
},
"primaryModelId": {
"type": "string",
"description": "Model tried first, e.g. 'opencode-go/minimax-m3'."
},
"fallbackModelIds": {
"type": "array",
"items": {
"type": "string"
},
"description": "Models tried in order if the primary fails. Pass [] for no fallback."
}
},
"required": [
"classId",
"primaryModelId",
"fallbackModelIds"
]
}
}
}
}
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