Takes a table (CSV/SQL result) and a plain-English question, decides what to compute, does it, and returns the answer with the reasoning and any caveats.
How it routes
Analytical questions lean on the mid and frontier tiers; simple lookups stay cheap. Wire it to a read-only SQL tool for live data.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/data-analyst-agent/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
data-analyst-agent.ocm.jsonjson
{
"ocm": "1",
"id": "agent:data-analyst",
"kind": "agent",
"name": "Data analyst agent",
"description": "Plans and runs an analysis over a dataset for a plain-English question and explains the result.",
"publisher": "OpenSmartRoute",
"version": "1.0.0",
"capabilities": {
"domains": [
"data_analysis"
],
"actions": [
"reasoning",
"planning",
"extract",
"summarize"
],
"min_complexity": 0.35,
"supports_tools": true,
"tags": [
"analytics",
"autonomous"
]
},
"instructions": "State the metric you will compute and the assumptions, compute it, then give the answer in one sentence followed by the supporting numbers. Call out data-quality caveats; never invent columns.",
"quality_prior": 0.8,
"examples": [
"Which region grew fastest last quarter in this sales table?",
"Is there a weekly seasonality in these signups?"
]
}
Fetch it by URL: GET /api/v1/registry/data-analyst-agent/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.