annotations
Annotations are named labels/scores attached to spans, traces, or experiment runs by humans, code, or LLM judges.
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
> /plugin marketplace add arize-ai/phoenix > /plugin install arize-phoenix@arize-phoenix
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
query LatestPrompt($id: ID!) {
node(id: $id) {
... on Prompt {
name
version {
modelName
modelProvider
template {
... on PromptChatTemplate { messages { role } }
... on PromptStringTemplate { template }
}
}
}
}
}Repo: arize-ai/phoenix
Annotations are named labels/scores attached to spans, traces, or experiment runs by humans, code, or LLM judges.
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
An experiment is one run of a prompt or pipeline over every example in a dataset.
- `Project.spans(timeRange, first, after, sort: SpanSort, rootSpansOnly: Boolean, filterCondition: String)` → connection of `Span`. There is **no `traces`…
A session groups the traces of one multi-turn conversation.