arize-admin
Manages Arize users, organizations, spaces, projects, roles, role bindings, resource restrictions, and API keys via the ax CLI. Use for enterprise admin workflows: inviting and offboarding users, onboarding new teams, creating custom roles for SAML/SSO mappings, assigning roles to users, restricting project-level access, and managing service keys for multi-tenant architectures. Covers ax users, ax organizations, ax spaces, ax projects, ax roles, ax role-bindings, and ax api-keys.
Overview
Arize Admin Skill
Programmatic management of Arize users, organizations, spaces, roles, permissions, and API keys — the building blocks for enterprise access control.
Privilege requirement: Most operations require org-admin or account-admin privileges. If commands return
403 Forbidden, the authenticated profile lacks sufficient permissions.
Destructive-action rule: Commands that delete, revoke, remove, or irreversibly modify resources (
delete,revoke,remove-user,unrestrict) require explicit user confirmation before execution. When a user asks you to perform one of these operations:
- Summarize exactly what will happen (e.g., "This will delete user [email protected] and cascade-revoke their API keys and remove all their org/space memberships and role bindings.")
- Ask the user to confirm (use
AskUserQuestion).- Only after the user confirms, run the command with
--forceto skip the CLI's interactive prompt.Never run a
--forcedestructive command without confirming with the user first.
When to Use
- Invite users to the account, assign them to orgs and spaces
- Offboard a user and revoke all their access in one command
- Onboard a new team: create a space, create a custom role, assign users, generate a service key
- Create custom roles for SAML/SSO attribute mappings (need stable role IDs)
- Restrict a project so only explicitly bound users can access it
- Create scoped service keys for CI/CD pipelines or multi-tenant architectures
- Rotate or revoke API keys
- Create or delete projects within a space
Upfront Questions
For multi-step workflows, collect all required information before running any ax commands. Use AskUserQuestion to avoid back-and-forth mid-workflow. Fetch live data first (e.g. org list) so you can present real options rather than asking the user to recall IDs.
Onboarding a new team
- Run
ax organizations list -o jsonto get available org names. - Use
AskUserQuestion(single call, up to 4 questions) to gather:- Which org? — present the org names from the list as options
- Space name — what to call the new team's space
- Team members — names and emails to invite (user can type via "Other"; ask if none yet)
- Service key? — whether to generate a service key for CI/CD pipelines
Offboarding a user
Ask before running any commands:
- Which user? — email address (then look up with
ax users list --email)
Restricting a project
Ask before running any commands:
- Which space and project? — to look up the project global ID
- Which users get explicit access? — emails of users to bind to the restricted project
Inviting users (standalone)
Ask before running any commands:
- Name and email — for each user to invite
- Role —
ADMIN,MEMBER, orANNOTATOR(present as options; account-level user creation has noREAD_ONLYrole) - Invite mode —
EMAIL_LINK(default),TEMPORARY_PASSWORD, orNONE
Revoking or rotating an API key
Ask before running any commands:
- Which key? — run
ax api-keys list -o jsonand present options by name and status; or ask forKEY_ID - Revoke or rotate? —
revokeinvalidates immediately;refreshissues a new key with the same scope (zero-downtime rotation)
If the user says "delete" an API key, use ax api-keys revoke to invalidate it.
Concepts
- Organization — a named grouping within an account (e.g. one per business unit). Spaces live inside organizations. Users are added to the account first, then to orgs, then to spaces.
- Space — a workspace that isolates traces, datasets, and projects. A user must be an org member before they can be added to a space within that org.
- Role — a named set of permissions. Predefined roles are system-managed. Custom roles are created by admins. The roles for org/space membership (
ADMIN,MEMBER,READ_ONLY,ANNOTATOR) are separate from custom RBAC roles used withax role-bindings. - Role binding — fine-grained assignment of a custom role to a user on a specific resource (a space or a project).
- Resource restriction — marks a project so that only users with an explicit role binding on that project can access it. Roles bound at any higher hierarchy level (space, org, account) are excluded.
- API key — either a user key (authenticates as the creator, full user permissions) or a service key (scoped to a specific space, for automated pipelines).
Prerequisites
Proceed directly — run the ax command you need. Do NOT check versions or profiles upfront.
If an ax command fails:
command not foundor version error → see references/ax-setup.md401 Unauthorized/ missing API key → runax profiles show; follow references/ax-profiles.md403 Forbidden→ the active profile lacks admin privileges; see references/ax-profiles.md (never ask the user to paste an admin key into chat)- Security: Never read
.envfiles or search the filesystem for credentials. Exception: the non-secretARIZE_SPACE_IDline (see Space). Useax profilesfor Arize credentials. Never ask the user to paste secrets into chat. Never echo, log, or display raw API key values. For missing credentials, see references/ax-profiles.md.
OAuth login option (v0.18.0+): Users can authenticate via browser-based OAuth PKCE instead of API keys by running
ax auth login(thenax auth logoutto revoke). Inform users of this option if they ask about authentication alternatives — do not runax auth loginyourself, as it opens a browser interactively.
Users
A user must exist in the account before they can be added to an org or space. Account-level roles: ADMIN, MEMBER, ANNOTATOR
ax users list # all users
ax users list --email "jane" # substring filter
ax users list --status active # active only
ax users list -l 100 -o json # paginate, get global IDs
ax users get USER_ID
ax users create \
--full-name "Jane Doe" \
--email [email protected] \
--role MEMBER \
--invite-mode EMAIL_LINK # or: NONE | TEMPORARY_PASSWORD
ax users update USER_ID --full-name "Jane Smith"
ax users update USER_ID --is-developer # grant developer flag
ax users delete --id USER_ID --force # ⚠ confirm first — cascades: org/space memberships, API key revocation, role bindings
ax users delete --email [email protected] --force # or resolve by email instead of ID
ax users resend-invitation USER_ID
ax users reset-password USER_IDOrganizations
Organization roles: ADMIN, MEMBER, READ_ONLY, ANNOTATOR
ax organizations list
ax organizations list --name "platform"
ax organizations list -l 100 -o json
ax organizations get "Platform Team"
ax organizations create --name "Platform Team" --description "Core ML platform"
ax organizations update "Platform Team" --name "ML Platform" --description "Updated"
# Add user (must exist in account first)
ax organizations add-user "Platform Team" --user-id USER_ID --role MEMBER
# Remove user (also removes from all child spaces) — ⚠ confirm first
ax organizations remove-user "Platform Team" --user-id USER_ID --force
# Delete organization: ⚠ irreversible; deletes org and all resources inside (spaces, projects, experiments, datasets)
ax organizations delete "Platform Team" --forceSpaces
Space roles: ADMIN, MEMBER, READ_ONLY, ANNOTATOR
ax spaces list
ax spaces list --organization-id ORG_ID
ax spaces get "my-workspace"
# --organization-id required; get ORG_ID from ax organizations list -o json
ax spaces create --name "team-alpha" --organization-id ORG_ID
ax spaces update "team-alpha" --name "team-alpha-v2"
ax spaces delete "team-alpha" --force # ⚠ confirm first — irreversible; deletes all resources
# User must be an org member before being added to a space
ax spaces add-user "team-alpha" --user-id USER_ID --role MEMBER
ax spaces remove-user "team-alpha" --user-id USER_ID --force # ⚠ confirm firstRoles
Custom RBAC roles used with ax role-bindings. Separate from the simpler ADMIN/MEMBER/READ_ONLY/ANNOTATOR roles in org/space membership.
ax roles list # all roles
ax roles list --is-custom -o json # custom only — get stable IDs for SAML mappings
ax roles list --is-predefined
ax roles get "Data Scientist" # inspect permissions
# --permissions is comma-separated; fully replaces on update
ax roles create \
--name "Data Scientist" \
--permissions "PROJECT_READ,DATASET_CREATE,EXPERIMENT_CREATE" \
--description "Read traces, create datasets and experiments"
ax roles update "Data Scientist" --permissions "PROJECT_READ,DATASET_CREATE,EXPERIMENT_CREATE,EVALUATOR_CREATE"
ax roles delete "Data Scientist" --force # ⚠ confirm first — predefined roles cannot be deletedFinding available permissions: Run ax roles get <predefined-role> -o json on a system role (e.g. Member, Admin) to see valid permission names.
Role Bindings
Fine-grained assignment of a custom role to a user on a specific resource (space or project).
# Assign at space level
ax role-bindings create \
--user-id USER_GLOBAL_ID \
--role-id ROLE_GLOBAL_ID \
--resource-type SPACE \
--resource-id SPACE_GLOBAL_ID
# Assign at project level
ax role-bindings create \
--user-id USER_GLOBAL_ID \
--role-id ROLE_GLOBAL_ID \
--resource-type PROJECT \
--resource-id PROJECT_GLOBAL_ID
ax role-bindings get BINDING_ID
ax role-bindings update BINDING_ID --role-id NEW_ROLE_ID
ax role-bindings delete BINDING_ID --force # ⚠ confirm first
# List bindings for a resource type (--resource-type is required)
ax role-bindings list --resource-type SPACE
ax role-bindings list --resource-type PROJECT --user-id USER_GLOBAL_ID -o jsonIdempotent — if a binding already exists for the user on that resource, exits without error.
Resource Restrictions
Restricts a project or dashboard so only users with an explicit role binding on that resource can access it. Space/org-level roles are excluded.
ax resource-restrictions list # all restrictions, paginated
ax resource-restrictions list --resource-type DASHBOARD # filter to one resource type (PROJECT or DASHBOARD)
ax resource-restrictions list --limit 50 --cursor PAGINATION_CURSOR # fetch next page
ax resource-restrictions restrict --resource-id PROJECT_OR_DASHBOARD_GLOBAL_ID # idempotent
ax resource-restrictions unrestrict --resource-id PROJECT_OR_DASHBOARD_GLOBAL_ID --force # ⚠ confirm first
# Finding project IDs
ax projects list -l 100 -o json --space "my-workspace"API Keys
Scope:
ax api-keys listreturns only keys owned by the authenticated user. For org-wide auditing, use the Arize UI (Settings > API Keys).
ax api-keys list
ax api-keys list --key-type SERVICE --status ACTIVE -o json
# User key — authenticates as creator, inherits their full permissions
ax api-keys create --name "CI pipeline" --expires-at "2027-01-01T00:00:00"
# Service key — bot user scoped to org(s)/space(s) via --assignments JSON
# (recommended for CI/CD pipelines; get ORG_ID from `ax organizations list -o json`)
ax api-keys create-service-key \
--name "team-alpha-traces" \
--assignments '[{"org_id": "ORG_ID", "spaces": [{"space": "team-alpha"}]}]' \
--expires-at "2027-01-01T00:00:00"
ax api-keys revoke KEY_ID --force # ⚠ confirm first — invalidates the key immediately
# Zero-downtime rotation — revokes old key, issues new one with same scope
ax api-keys refresh KEY_ID
ax api-keys refresh KEY_ID --expires-at "2028-01-01T00:00:00"The raw key is displayed once. Save it immediately in your secrets manager. It cannot be retrieved again.
create-service-key flags:
| Flag | Required | Description |
|---|---|---|
--name | yes | Key name |
--assignments | yes | JSON array (or path to a JSON file) of org/space assignments for the bot user: [{"org_id": "<id>", "role": "<org-role>", "spaces": [{"space": "<name-or-id>", "role": "<space-role>"}]}]. role is optional at both levels — omitted roles default to space=MEMBER, org=READ_ONLY. Custom roles use {"type": "CUSTOM", "id": "<role-id>"}. |
--account-role | no | Account-level role for the bot user: ADMIN, MEMBER, or ANNOTATOR (default MEMBER) |
--expires-at | no | ISO 8601 expiry date |
--description | no | Optional description |
Scope create-service-key entirely through --assignments, not through separate --space/--space-role/--org-role flags.
Projects
Projects live inside spaces and contain traces, datasets, and experiments.
ax projects list --space SPACE
ax projects list --space SPACE --name "playground" # substring filter
ax projects list --space SPACE -l 100 -o json # get base64 IDs
ax projects get NAME_OR_ID --space SPACE
ax projects create --name "my-project" --space SPACE
ax projects update NAME_OR_ID --name "new-project-name" --space SPACE
ax projects delete NAME_OR_ID --space SPACE --force # ⚠ confirm first — deletes all traces and datasetsNote: Project IDs (base64 strings) are used by
ax spans export,ax traces export, andax resource-restrictions. If commands reject a project name, look up theidfield fromax projects list -o jsonand use that instead.
Enterprise Workflows & Troubleshooting
Step-by-step workflows (onboard a team, SAML/SSO mappings, project restriction, offboarding, multi-tenant keys) and a troubleshooting table are in references/REFERENCE.md.
Related Skills
- arize-instrumentation: Set up tracing in an LLM app once a space is ready.
- arize-trace: Export and inspect traces within a managed space.
- arize-dataset: Create and manage datasets within a space.
Files 4 files
Install it by hand
Deska runs this for you, for every agent you pick. To run it yourself in a terminal:
npx skills add arize-ai/arize-skills --skill arize-adminMore from arize-ai
- arize-instrumentationarize-aiAdds Arize AX tracing to an LLM application for the first time. Detects the stack, routes to the single matching integration doc, wires auto-instrumentation after user confirmation, and verifies traces land. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or openinference, or get started with Arize tracing.3,200 installs on skills.sh0
- arize-prompt-optimizationarize-aiOptimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.3,100 installs on skills.sh0
- arize-tracearize-aiDownloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by ID, spans by ID, sessions by ID, and root-cause investigation using the ax CLI. Use when the user wants to look at existing trace data, see what their LLM app is doing, export traces, download spans, investigate errors, or analyze behavior regressions.3,000 installs on skills.sh0
- arize-datasetarize-aiCreates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.2,900 installs on skills.sh0
- arize-evaluatorarize-aiHandles LLM-as-judge and code evaluator workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, code evaluator, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.2,900 installs on skills.sh0