Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
See `content/06-decision-tree.xml`. The tree starts from the question "Are there ≥2 realistic vendors AND contract value ≥ $1k/yr?" and routes observable input signals to a concrete action, each leaf
Imported from faionfaion/faion-network (skills/faion/knowledge/product/vendor-evaluation-scorecard/AGENTS.md). Install upstream with npx skills add faionfaion/faion-network --skill vendor-evaluation-scorecard. Copyright stays with the author.
Vendor Evaluation Scorecard for AI Tooling
Summary
One-sentence: Scorecard rubric for choosing AI vendors (LLM, vector DB, eval, observability) across quality, cost, lock-in, security, and SLA — produces a comparable score + decision artefact.
One-paragraph: Scorecard rubric for choosing AI vendors (LLM, vector DB, eval, observability) across quality, cost, lock-in, security, and SLA — produces a comparable score + decision artefact. The methodology is testable end-to-end: each artefact it produces conforms to the JSON Schema in content/02-output-contract.xml, every claim in the body resolves to a rule in content/01-core-rules.xml, and the decision-tree in content/06-decision-tree.xml routes observable inputs to the right rule.
Ефективно для:
Обираєш LLM-провайдера між OpenAI / Anthropic / Bedrock з compliance + lock-in factor.
Vector DB shortlist: Qdrant vs Weaviate vs Pinecone + self-host vs SaaS.
Eval / observability tools (Braintrust, LangSmith, Helicone) — порівняння за єдиною rubric.
Procurement gate: pricing tier vs scale; SLA + DPA + SOC2 obov'yazkovi для enterprise.
Applies If (ALL must hold)
≥2 vendors під розгляд для тієї ж функції.
Контракт > $5k/рік або production-залежність.
Доступний technical contact зі сторони вендора для уточнень.
Skip If (ANY kills it)
Один вендор з якого вже залежиш і немає реальної alternative.
Routing tree on observable signals → rule in 01-core-rules.xml
600
Task Routing
Sub-task
Model
Rationale
classify-input
sonnet
Light judgment; identifies branch in decision tree.
draft-output
sonnet
Drafting the output artefact per schema.
validate-output
haiku
Mechanical schema validation via script.
Templates
File
Purpose
templates/scorecard.md.j2
Human-readable scorecard with five-axis table
templates/scorecard.md
Human-readable scorecard with five-axis table Generated from templates/scorecard.md.j2 by tpl-jinja --migrate; do not hand-edit.
templates/scorecard.json
Machine-readable scorecard matching schema
Scripts
File
Purpose
When to call
scripts/validate-vendor-evaluation-scorecard.py
Validate output artefact against schema in 02-output-contract.xml
CI on each artefact change; pre-commit
Related
[[ai-research-tools]]
[[ai-research-tool-categories]]
[[ai-native-product-development]]
Decision tree
See content/06-decision-tree.xml. The tree starts from the question "Are there ≥2 realistic vendors AND contract value ≥ $1k/yr?" and routes observable input signals to a concrete action, each leaf referencing a rule from 01-core-rules.xml. Apply it whenever the input shape changes or before scaling a pilot run.
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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "faionfaion-faion-network-vendor-evaluation-scorecard",
"kind": "skill",
"name": "vendor-evaluation-scorecard",
"description": "See `content/06-decision-tree.xml`. The tree starts from the question \"Are there ≥2 realistic vendors AND contract value ≥ $1k/yr?\" and routes observable input signals to a concrete action, each leaf referencing a rule from `01-core-rules.xml`. Apply it whenever the input shape changes or before scaling a pilot run.",
"publisher": "faionfaion",
"version": "1.0.0",
"capabilities": {
"domains": [
"legal"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"See `content/06-decision-tree.xml`. The tree starts from the question \"Are there ≥2 realistic vendors AND contract value ≥ $1k/yr?\" and routes observable input signals to a concrete action, each leaf referencing a rule from `01-core-rules.xml`. Apply it whenever the input shape changes or before scaling a pilot run."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/faionfaion/faion-network",
"path": "skills/faion/knowledge/product/vendor-evaluation-scorecard/AGENTS.md",
"ref": "8e31684537e64d45c75264b1e0a2384f9b024a34",
"url": "https://github.com/faionfaion/faion-network/blob/8e31684537e64d45c75264b1e0a2384f9b024a34/skills/faion/knowledge/product/vendor-evaluation-scorecard/AGENTS.md",
"key": "faionfaion/faion-network/skills/faion/knowledge/product/vendor-evaluation-scorecard/AGENTS.md"
}
},
"instructions": "# Vendor Evaluation Scorecard for AI Tooling\n\n## Summary\n\n**One-sentence:** Scorecard rubric for choosing AI vendors (LLM, vector DB, eval, observability) across quality, cost, lock-in, security, and SLA — produces a comparable score + decision artefact.\n\n**One-paragraph:** Scorecard rubric for choosing AI vendors (LLM, vector DB, eval, observability) across quality, cost, lock-in, security, and SLA — produces a comparable score + decision artefact. The methodology is testable end-to-end: each artefact it produces conforms to the JSON Schema in `content/02-output-contract.xml`, every claim in ",
"cost": {
"context_tokens": 1009
}
}
Fetch it by URL: GET /api/v1/registry/faionfaion-faion-network-vendor-evaluation-scorecard/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
