Roster for Anthropic

Use Claude models to interpret who should act.

Configure Anthropic as Roster's resolver model provider for approval routing, workflow ownership, human review, escalation, and delegation-aware participant resolution.

Your deployment controls the Anthropic credential, selected Claude model, endpoint, data-handling arrangement, and production validation.

Configure AnthropicReview supported models

Last verified 07/13/2026

Claude interprets organizational intent. Roster supplies the governed context.

Roster maintains the operational source of truth for:

Who should handle the Atlas security review while the primary owner is unavailable?

Claude helps interpret the request. Roster then validates the model's participant selection and resolves it into active users, groups, roles, agents, or delegated contacts.

  • Projects
  • Participants
  • Users and groups
  • Directory membership
  • Labels and metadata
  • Roles and responsibilities
  • Active delegations
  • Authorization boundaries

Anthropic does not become the organizational database. Roster remains the participant-resolution and governance layer.

How the integration works

Roster calls Anthropic's Messages API with structured schema, then validates the model's participant selection against its own authorization and directory context.

Agent, workflow, or application
   ↓
Roster Resolve
   ↓
Authorized participant context
   ↓
Anthropic Messages API
   ↓
Structured participant selection
   ↓
Active users, groups, roles, or delegates

Why use Anthropic with Roster?

Strong interpretation of complex requests
Claude models can be appropriate when resolution questions contain ambiguity, multiple responsibilities, or nuanced business context.
Structured response support
Anthropic supports structured outputs for compatible Claude models, allowing responses to conform to a schema suitable for downstream processing.
Direct Messages API integration
Roster connects directly to Anthropic's Messages API without requiring an additional gateway.
Enterprise data options
Anthropic documents data-retention and residency controls for eligible API arrangements. Availability and model-specific requirements must be reviewed for the selected account and model.

Configure Anthropic

Roster uses the Anthropic Messages API when ROSTER_MODEL_PROVIDER=anthropic.

ANTHROPIC_API_KEY=<anthropic-api-key>
ANTHROPIC_BASE_URL=https://api.anthropic.com
ROSTER_MODEL_PROVIDER=anthropic
ROSTER_MODEL_NAME=claude-opus-4-8

ANTHROPIC_BASE_URL is optional when using the standard Anthropic endpoint. Set it only when using an approved proxy, regional endpoint, or supported provider intermediary.

Store the API key in the deployment secret manager or protected runtime environment.

Quality-first — recommended for complex resolution questions:

ROSTER_MODEL_NAME=claude-opus-4-8

Full Resolve option — evaluate for latency, cost, availability, and data-retention fit:

ROSTER_MODEL_NAME=claude-fable-5

At the time of verification, Anthropic documents a specific 30-day retention requirement for Claude Fable 5 and states that the model is not available under a Zero Data Retention arrangement. Confirm the current requirement before selecting it.

Reasoning-effort behavior — direct Anthropic requests currently ignore ROSTER_MODEL_EFFORT even though Roster accepts the variable globally. Validate model behavior through model selection, Roster's prompt and schema, output-token limits, representative Resolve evaluations, participant-model quality, metadata design, and safe fallback rules.

Example resolution

A customer-operations agent asks:

Who should receive the Acme escalation for Canada, given that the normal enterprise account owner is away?
  1. Roster identifies the accessible Acme project.
  2. Roster collects relevant escalation participants.
  3. Roster includes region, customer segment, membership, and delegation context.
  4. Roster sends the structured interpretation task to Claude.
  5. Roster validates the selected participant.
  6. Roster expands it into active users, groups, or delegated contacts.
  7. Roster records the Resolve request and model invocation.

The calling system can then create a ticket, send a message, or assign the case.

Structured output and observability

Roster depends on predictable structured output, not merely fluent prose. The selected Claude model must reliably return parseable data, follow the expected schema, reference valid participant identifiers, avoid inventing unavailable participants, represent no-match cases correctly, and remain stable across similar queries.

Anthropic structured outputs can constrain compatible Claude responses to a defined format. Roster still validates the result against its own participant and authorization context.

Roster records provider and model, status, live or test mode, start and completion time, latency, input/output/total tokens, estimated cost, Resolve request and trace IDs, provider request ID, input and output payloads (subject to PII settings), and errors. Use Model Runs to compare the Anthropic configuration with other approved providers using the same evaluation cases.

Data handling and residency

Review the exact model
Anthropic data-retention eligibility may vary by model and feature. Do not assume that every Claude model has the same retention characteristics.
Zero Data Retention
Anthropic offers Zero Data Retention arrangements for eligible API features and models. Contractual eligibility and model coverage must be confirmed directly.
Model-specific exceptions
Some models can carry mandatory retention requirements that make them unsuitable for a ZDR deployment.
Data residency
Anthropic documents controls for inference and workspace geography in eligible configurations. Verify availability for the intended region, model, and commercial agreement.
Roster controls
Roster separately controls whether model-run inputs, outputs, tool payloads, actor details, and errors are retained or displayed. Provider-side and Roster-side controls must both satisfy the deployment's requirements.
Production validation
Verify Messages API connectivity, model-ID access, structured-output behavior, the full Resolve evaluation suite (including ambiguous, delegated, and no-match cases), latency and token usage, account rate limits, model-specific retention, regional processing, and provider-error handling.

Frequently asked questions

This page describes Anthropic as the server-side resolver model provider. Connecting the Claude user experience to Roster through MCP is a separate integration.

Use Claude for interpretation without moving governance into the model

Let Anthropic interpret complex workflow language while Roster controls projects, participants, authorization, directory context, delegation, and auditability.

Configure AnthropicReview model-provider documentationExplore all integrations