Roster for OpenAI

Use OpenAI models to resolve who should act.

Configure an OpenAI model as Roster's resolver to interpret workflow questions, identify the relevant participants, and produce structured, auditable answers.

Your deployment controls the OpenAI account, API credential, model, reasoning effort, and production approval process.

Configure OpenAIReview supported models

Last verified 07/13/2026

OpenAI interprets the question. Roster governs the answer.

Roster maintains the organizational context:

Who should approve the Atlas vendor renewal for Europe?

The OpenAI model helps Roster interpret natural-language requests. Roster remains responsible for assembling the authorized context, validating the model response, resolving the selected participants, and recording the request.

  • Projects
  • Participants
  • Users and groups
  • Directory membership
  • Roles and labels
  • Participant metadata
  • Active delegations
  • Access boundaries

The model does not replace Roster's participant model or authorization layer.

How the integration works

Roster prepares the authorized participant context, calls the OpenAI Responses API with a structured schema, and validates the returned selection before resolving active users, groups, roles, or delegates.

Agent, workflow, or application
   ↓
Roster Resolve
   ↓
Authorized project and participant context
   ↓
OpenAI Responses API
   ↓
Structured participant selection
   ↓
Active users, groups, roles, or delegates

Why use OpenAI with Roster?

Quality for complex routing questions
OpenAI reasoning models can help interpret requests containing multiple constraints such as project, region, approval type, responsibility, and threshold.
Structured response behavior
Roster requires predictable, machine-readable model output. OpenAI's Responses API supports structured outputs constrained by a supplied schema.
Configurable reasoning effort
For supported models, reasoning effort provides a practical control over latency, cost, and the amount of model work applied to a resolution request.
Direct provider relationship
A direct OpenAI configuration avoids introducing a separate model-routing gateway between Roster and the selected model.

Configure OpenAI

OpenAI is Roster's default model-provider family.

OPENAI_API_KEY=<openai-api-key>
OPENAI_BASE_URL=https://api.openai.com/v1
ROSTER_MODEL_PROVIDER=openai
ROSTER_MODEL_NAME=gpt-5.6-sol
ROSTER_MODEL_EFFORT=low

OPENAI_BASE_URL is optional when using OpenAI's standard public endpoint. Set it only when your deployment uses an approved proxy, regional endpoint, or compatible model gateway.

Store the API key in your deployment secret manager or protected runtime environment. Do not commit it to source control.

Quality-first — recommended for complex, high-impact routing:

ROSTER_MODEL_NAME=gpt-5.6-sol

Balanced cost and quality — everyday production resolution:

ROSTER_MODEL_NAME=gpt-5.6-terra

Cost-sensitive and high-volume workloads — validate against representative data before high-impact routing:

ROSTER_MODEL_NAME=gpt-5.6-luna

Do not choose a model based only on general benchmark performance. Test it using the projects, participant structures, query patterns, ambiguity, and guardrails expected in your own deployment.

Reasoning effort — Roster accepts: none, minimal, low, medium, high, xhigh, max. Actual support is model-dependent. Use lower effort for straightforward, high-volume, latency-sensitive queries. Consider higher effort when multiple responsibilities may match, the query contains several constraints, or routing has financial, legal, security, or operational impact.

Example resolution

A procurement workflow asks:

Who should approve the Atlas software renewal for Europe when the contract exceeds the regional threshold?
  1. Roster identifies the authorized Atlas project context.
  2. Roster supplies relevant participants, labels, metadata, memberships, and delegations.
  3. Roster sends the structured resolution task to the configured OpenAI model.
  4. Roster validates the returned participant selection.
  5. Roster expands the selected participant into active users, groups, or delegates.
  6. Roster records the Resolve request and model run.

The workflow then uses its existing approval system to contact the selected participant. Roster resolves who should act — it does not send or enforce the approval itself.

Structured output and observability

Participant resolution is not ordinary conversational text generation. Roster needs responses that can be parsed reliably, validated against expected fields, connected to existing participant IDs, checked for unsupported selections, and audited after the request.

OpenAI Structured Outputs constrains responses to a defined JSON schema, reducing the risk of missing fields or invalid values. A successful API connection is not sufficient — the model must produce stable structured responses across Roster's expected Resolve workload.

Roster records provider, model name, run status, live or test mode, latency, input/output/total tokens, estimated cost, reasoning effort, Resolve request ID, provider request ID, trace identifiers, errors, and (subject to PII settings) input and output payloads. Administrators can use Model Runs to compare model choices and investigate latency, errors, cost, and resolution behavior.

Data handling and security

Customer-managed credential
The OpenAI API key remains deployment configuration controlled by the customer.
Intentional model context
Roster sends the model the context required to interpret the resolution request. Avoid adding unrelated personal, confidential, or proprietary data to participant metadata or query text.
Roster PII controls
Administrators can control whether model inputs, outputs, tool payloads, actor details, and errors are retained or visible inside Roster.
Provider review
Before production deployment, review the OpenAI account configuration and applicable terms for data retention, API response storage, processing location, logging, model availability, rate limits, and compliance requirements.
Production validation
Verify API connectivity, structured-output behavior, representative Resolve evaluations (including ambiguous and no-match cases), group membership and delegation scenarios, latency, token usage, rate limits, and a safe fallback for provider errors. Canary before broad rollout.
Retention boundaries
Roster's own retention controls do not override the model provider's processing and retention policies.

Frequently asked questions

No. Roster also supports Anthropic, Mistral, and approved OpenAI-compatible gateway configurations.

Bring OpenAI reasoning to governed participant resolution

Use an OpenAI model to interpret the workflow question while Roster governs projects, participants, directory context, authorization, delegation, and observability.

Configure OpenAIReview model-provider documentationExplore all integrations