● classifier online

Route every prompt to the right agent

AgentSwitch classifies incoming prompts against skills you configure — URL namespaces, keywords, intents — and tells your frontier agent exactly where to route, with the schema it needs.

Add your first skill Read the API docs
01

Define skills

Each skill maps namespaces, keywords and intents to an agent — plus the input schema that agent expects.

02

Send prompts

Your agent calls POST /api/classify with the message and optional context JSON. Origin is verified server-side from request headers; backend callers may declare a schema namespace.

03

Get the route

Deterministic rules answer fast; ambiguous prompts fall back to an LLM. You get agent, intent, schema, confidence.

Configure

Your skills

Create or update a skill here and the classifier uses it on the very next request. No redeploy.

Add a skill

Loading skills…
Try it

Classification playground

Exactly what your agent will call in production — same endpoint, same response.

Request

Response 

{
  "message": "Hit Classify to see the routing decision"
}
Agent hub

Build & test agents

Register agents backed by your own or public MCP servers — AgentSwitch runs the agentic loop (model picks tools, hub executes them via MCP, results feed back) and classify routes to them by name. The chef-agent is free: recipes from whatever ingredients you have.

Agents

Add an Agent
Loading agents…

Test runner

Output appears here — try the free chef-agent with some ingredients.

Measure

Prompt evaluator

Industry-standard eval: faithfulness, hallucination (SelfCheckGPT sampling), precision and recall. Evaluate your agent's answer against its context — or let the model answer and self-check — and see how it ranks against every prior eval.

Evaluate a prompt

Full evaluation matrix →
Integrate

Call it from your agent

Point your frontier agent at these endpoints. Set an API secret in production and send it as a Bearer header.

POST /api/classify

curl -X POST https://agents.publichome.page/api/classify \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "refund invoice INV-123",
    "schema": "app.foo.com/billing",
    "context": { "user_id": "u_42" }
  }'

Response

{
  "referrer": "app.foo.com",
  "namespace": "app.foo.com/billing/*",
  "skill": "billing-agent",
  "agent": "billing",
  "agent_intent": "refund",
  "schema": { … },          // what the agent expects
  "confidence": 0.87,
  "method": "rules",      // rules | llm | fallback | none
  "context": { … }          // your context, passed through
}

From an agent (JS)

const route = await fetch("https://agents.publichome.page/api/classify", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${TOKEN}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ prompt, schema, context }),
}).then(r => r.json());

// then dispatch:
await agents[route.agent].run(route.agent_intent, route.schema);