Arize Annotation Skill

SPACE — --space flags accept a space name (e.g., my-workspace) or a base64 space ID (e.g., U3BhY2U6...). Resolve a known name with ax spaces get NAME; ax spaces list is for human browsing.

This skill covers annotation configs (the label schema) and annotation queues (human review workflows), as well as programmatically annotating project spans via the Python SDK.

Direction: Human labeling in Arize attaches values defined by configs to spans, dataset examples, experiment-related records, and queue items in the product UI. This skill covers: ax annotation-configs, ax annotation-queues, and bulk span updates with ArizeClient.spans.update_annotations.

Prerequisites

Proceed directly with the task — run the ax command you need. Do NOT check versions, env vars, or profiles upfront.

If an ax command fails, troubleshoot based on the error:

• command not found or version error → see references/ax-setup.md
• 401 Unauthorized / missing API key → run ax profiles show to inspect the current profile. If the profile is missing or the API key is wrong, follow references/ax-profiles.md to create/update it. If the user doesn't have their key, direct them to https://app.arize.com/admin > API Keys
• Space unknown → see Space
• Security: Never read .env files or search the filesystem for credentials. Exception: the non-secret ARIZE_SPACE_ID line (see Space). Use ax profiles for Arize credentials and ax ai-integrations for LLM provider keys. Never ask the user to paste secrets into chat. For missing credentials, see references/ax-profiles.md.

What is an Annotation Config?

An annotation config defines the schema for a single type of human feedback label. Before anyone can annotate a span, dataset record, experiment output, or queue item, a config must exist for that label in the space.

Where labels get applied (surfaces)

Always ensure the relevant annotation config exists in the space before expecting labels to persist.

Basic CRUD: Annotation Configs

List

ax annotation-configs list --space SPACE
ax annotation-configs list --space SPACE -o json
ax annotation-configs list --space SPACE --limit 20
ax annotation-configs list --space SPACE --name "Correctness"   # substring filter

Create — Categorical

Categorical configs present a fixed set of labels for reviewers to choose from.

ax annotation-configs create categorical \
  --name "Correctness" \
  --space SPACE \
  --value correct \
  --value incorrect \
  --optimization-direction MAXIMIZE

Common binary label pairs:

• correct / incorrect
• helpful / unhelpful
• safe / unsafe
• relevant / irrelevant
• pass / fail

Create — Continuous

Continuous configs let reviewers enter a numeric score within a defined range.

ax annotation-configs create continuous \
  --name "Quality Score" \
  --space SPACE \
  --min-score 0 \
  --max-score 10 \
  --optimization-direction MAXIMIZE

Create — Freeform

Freeform configs collect open-ended text feedback. No additional flags needed beyond name and space.

ax annotation-configs create freeform \
  --name "Reviewer Notes" \
  --space SPACE

Get

ax annotation-configs get NAME_OR_ID
ax annotation-configs get NAME_OR_ID -o json
ax annotation-configs get NAME_OR_ID --space SPACE   # required when using name instead of ID

Update

Each config type has its own update command. Only changed fields are updated.

Freeform:

ax annotation-configs update freeform NAME_OR_ID --space SPACE --new-name "Updated Name"

Continuous:

ax annotation-configs update continuous NAME_OR_ID --space SPACE --min-score 1 --max-score 5 --optimization-direction MINIMIZE

Categorical:

ax annotation-configs update categorical NAME_OR_ID --space SPACE --value correct --value incorrect --optimization-direction MAXIMIZE

--space is required when using a name instead of ID. Each --value supplies the complete categorical label list: it replaces existing labels rather than appending to them. Repeat --value for every label that should remain, or omitted labels are removed.

Delete

ax annotation-configs delete NAME_OR_ID
ax annotation-configs delete NAME_OR_ID --space SPACE   # required when using name instead of ID
ax annotation-configs delete NAME_OR_ID --force   # skip confirmation

Note: Deletion is irreversible. Any annotation queue associations to this config are also removed in the product (queues may remain; fix associations in the Arize UI if needed).

Annotation Queues: ax annotation-queues

Annotation queues route records (spans, dataset examples, experiment runs) to human reviewers. Each queue is linked to one or more annotation configs that define what labels reviewers can apply.

List / Get

ax annotation-queues list --space SPACE
ax annotation-queues list --space SPACE -o json
ax annotation-queues list --space SPACE --name "Review"   # substring filter

ax annotation-queues get NAME_OR_ID --space SPACE
ax annotation-queues get NAME_OR_ID --space SPACE -o json

Create

At least one --annotation-config-id is required.

ax annotation-queues create \
  --name "Correctness Review" \
  --space SPACE \
  --annotation-config-id CONFIG_ID \
  --annotator-email reviewer@example.com \
  --instructions "Label each response as correct or incorrect." \
  --assignment-method ALL   # or: RANDOM

Repeat --annotation-config-id and --annotator-email to attach multiple configs or reviewers.

Add Records

Add records to an existing queue (create also accepts --record-sources for initial records).

ax annotation-queues add-records NAME_OR_ID --space SPACE --record-sources sources.json

ax annotation-queues add-records NAME_OR_ID --space SPACE \
  --record-sources '[{"record_type": "EXAMPLE", "dataset_id": "ds-1", "example_ids": ["ex-1", "ex-2"]}]'

--record-sources is required and accepts a JSON file path or inline JSON array. Each source specifies record_type (SPAN or EXAMPLE) plus type-specific fields:

• Span: project_id, start_time (ISO 8601), end_time (ISO 8601), optional span_ids
• Example: dataset_id, example_ids

Update

List flags (--annotation-config-id, --annotator-email) fully replace existing values when provided — pass all desired values, not just the new ones.

ax annotation-queues update NAME_OR_ID --space SPACE --name "New Name"
ax annotation-queues update NAME_OR_ID --space SPACE --instructions "Updated instructions"
ax annotation-queues update NAME_OR_ID --space SPACE \
  --annotation-config-id CONFIG_ID_A \
  --annotation-config-id CONFIG_ID_B

Delete

ax annotation-queues delete NAME_OR_ID --space SPACE
ax annotation-queues delete NAME_OR_ID --space SPACE --force   # skip confirmation

List Records

ax annotation-queues list-records NAME_OR_ID --space SPACE
ax annotation-queues list-records NAME_OR_ID --space SPACE --limit 50 -o json

Submit an Annotation for a Record

Annotations are upserted by config name — call once per annotation config. Supply at least one of --score, --label, or --text.

ax annotation-queues annotate-record NAME_OR_ID RECORD_ID \
  --annotation-name "Correctness" \
  --label "correct" \
  --space SPACE

ax annotation-queues annotate-record NAME_OR_ID RECORD_ID \
  --annotation-name "Quality Score" \
  --score 8.5 \
  --text "Response was accurate but slightly verbose." \
  --space SPACE

Assign a Record

Assign users to review a specific record by repeating --email; this fully replaces existing assignments, so pass every assignee each time (passing no --email flags clears all assignments):

ax annotation-queues assign-record NAME_OR_ID RECORD_ID --email user@example.com --space SPACE

Delete Records

ax annotation-queues delete-records NAME_OR_ID --space SPACE --record-id REC_1 --record-id REC_2   # max 100; --force skips confirmation

Applying Annotations to Spans (Python SDK)

Use the Python SDK to bulk-apply annotations to project spans when you already have labels (e.g., from a review export or an external labeling tool).

import pandas as pd
from arize import ArizeClient

import os

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])

# Build a DataFrame with annotation columns
# Required: context.span_id + at least one annotation.<name>.label or annotation.<name>.score
annotations_df = pd.DataFrame([
    {
        "context.span_id": "span_001",
        "annotation.Correctness.label": "correct",
        "annotation.Correctness.updated_by": "reviewer@example.com",
    },
    {
        "context.span_id": "span_002",
        "annotation.Correctness.label": "incorrect",
        "annotation.Correctness.updated_by": "reviewer@example.com",
    },
])

response = client.spans.update_annotations(
    space_id=os.environ["ARIZE_SPACE_ID"],
    project_name="your-project",
    dataframe=annotations_df,
    validate=True,
)

DataFrame column schema:

Limitation: Annotations apply only to spans within 31 days prior to submission.

Troubleshooting

Batch Annotate via CLI

The ax CLI provides batch annotation commands for writing annotations at scale without the Python SDK. All commands accept a file (CSV, JSON, JSONL, or Parquet) with up to 1000 annotations per request and use upsert semantics (existing annotations with the same key are updated; new ones are created).

Gotchas:

• ax spans annotate: one span ID not found in the time window rejects the entire request.
• ax datasets annotate-examples and ax experiments annotate-runs: unmatched record IDs are silently ignored.
• ax experiments annotate-runs: omit --dataset for a standalone experiment and pass --space.

See the linked skills for file format details.

Related Skills

• arize-trace: Export spans to find span IDs and time ranges; batch annotate spans via ax spans annotate
• arize-dataset: Find dataset IDs and example IDs; batch annotate examples via ax datasets annotate-examples
• arize-evaluator: Automated LLM-as-judge alongside human annotation
• arize-experiment: Experiments tied to datasets and evaluation workflows; batch annotate runs via ax experiments annotate-runs
• arize-prompts: Manage prompt templates; annotate prompt outputs for quality tracking
• arize-link: Deep links to annotation configs and queues in the Arize UI

Save Credentials for Future Use

See references/ax-profiles.md § Save Credentials for Future Use.