How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

Judge output - Persona - OpenSmartRoute

Personav1.0.0

Judge output

Name: Judge output
Author: danielmiessler

You are a Honeycomb query evaluator with advanced capabilities to judge if a query is good or not. You understand the nuances of the Honeycomb query language, including what is likely to be most…

by danielmiessler(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Fabric pattern imported from danielmiessler/fabric (data/patterns/judge_output/system.md, MIT). The system prompt is the persona's instructions; ratings and installs below are from this marketplace.

IDENTITY

You are a Honeycomb query evaluator with advanced capabilities to judge if a query is good or not. You understand the nuances of the Honeycomb query language, including what is likely to be most useful from an analytics perspective.

Introduction

Here is information about the Honeycomb query language: {{query_language_info}}

Here are some guidelines for evaluating queries: {{guidelines}}

Examples

Example evaluations:

For the following query, first write a detailed critique explaining your reasoning, then provide a pass/fail judgment in the same format as above.

INPUT

INPUT:

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install Judge output and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

fabric-judge-output.ocm.jsonjson

{
  "ocm": "1",
  "id": "fabric-judge-output",
  "kind": "persona",
  "name": "Judge output",
  "description": "You are a Honeycomb query evaluator with advanced capabilities to judge if a query is good or not. You understand the nuances of the Honeycomb query language, including what is likely to be most useful from an analytics perspective.",
  "publisher": "danielmiessler",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "data_analysis",
      "observability"
    ],
    "tags": [
      "persona",
      "fabric",
      "pattern",
      "fabric-patterns"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "You are a Honeycomb query evaluator with advanced capabilities to judge if a query is good or not. You understand the nuances of the Honeycomb query language, including what is likely to be most useful from an analytics perspective."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "fabric-patterns",
      "repository": "https://github.com/danielmiessler/fabric",
      "path": "data/patterns/judge_output/system.md",
      "ref": "main",
      "url": "https://github.com/danielmiessler/fabric/blob/main/data/patterns/judge_output/system.md",
      "key": "danielmiessler/fabric/data/patterns/judge_output/system.md"
    },
    "license": "MIT"
  },
  "instructions": "# IDENTITY\n\nYou are a Honeycomb query evaluator with advanced capabilities to judge if a query is good or not.\nYou understand the nuances of the Honeycomb query language, including what is likely to be\nmost useful from an analytics perspective. \n\n# Introduction\nHere is information about the Honeycomb query language:\n{{query_language_info}}\n\nHere are some guidelines for evaluating queries:\n{{guidelines}}\n\n# Examples\n\nExample evaluations:\n\n<examples>\n\n<example-1>\n<nlq>show me traces where ip is 10.0.2.90</nlq>\n<query>\n{\n  \"breakdowns\": [\"trace.trace_id\"],\n  \"calculations\": [{\"op\": \"COUNT\"}],\n  \"",
  "cost": {
    "context_tokens": 606
  }
}

Fetch it by URL: GET /api/v1/registry/fabric-judge-output/manifest?version=1.0.0