Skip to content
Development
Agent

datasets

There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.

From plugin
phoenix
11k7 skills7 agents
Install
$ npx -y skills add arize-ai/phoenix --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.

Agent definition

datasets.md

Dataset, DatasetExample

Reaching a dataset

There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.

Dataset fields

  • `name`, `description`, `metadata`
  • `exampleCount(datasetVersionId)`
  • `examples(datasetVersionId, splitIds, first, after, filter: String, filterIds)` → `DatasetExampleConnection`
  • `versions(first, after, sort)` → `DatasetVersionConnection`
  • `splits`, `labels`
  • `experiments(first, after, filterCondition, filterIds)`, `experimentCount`

Gotchas:

  • **The version argument is `datasetVersionId` everywhere** (not `versionId`); omit it to get the latest version.
  • `examples` has two distinct filter args: `filter: String` (free-text search over input/output/metadata) and `filterIds: [GlobalID!]` (membership lookup).
  • `experiments` uses `filterCondition: String` (not `filter`).

DatasetExample fields

  • `externalId`
  • `revision(datasetVersionId) { input output metadata revisionKind }` — `input`/`output`/`metadata` are `JSON`; `revisionKind` is `CREATE`/`PATCH`/`DELETE`.
  • `span`
  • `datasetSplits`
  • `experimentRuns(experimentIds, first, after)`

Example

query DatasetExamples($id: ID!, $first: Int = 20) {
  node(id: $id) {
    ... on Dataset {
      name
      exampleCount
      examples(first: $first) {
        edges { node { id externalId revision { input output metadata } } }
        pageInfo { hasNextPage endCursor }
      }
    }
  }
}
Read more
Ships withphoenix

AI Observability & Evaluation

Get the whole plugin