What does the Stellaris AOS documentation cover?

It covers how to deploy and operate the platform: agent definitions, the orchestration layer, permission scopes, Human-In-The-Loop approval gates, audit logging and the integration endpoints used to connect enterprise systems.

Do we need our own engineering team to run it?

No. We deploy and operate the infrastructure for you in isolated environments. Your team owns the business knowledge and the approval decisions; we own the orchestration, the routing and the security perimeter.

How do we start a deployment?

Start from a single process with a measurable bottleneck. We map how the work happens today, define the agents and their permissions, deploy the first cell with full traceability, and expand only once that process runs reliably.

Documentation

Stellaris AOS Documentation

Architecture, API reference, deployment models, and governance frameworks for enterprise agentic orchestration.

Core Architecture Concepts

Stellaris AOS is designed as a secure, deterministic routing layer between foundation models (LLMs) and enterprise infrastructure. It acts as the Agentic Operating System that governs how, when, and why an AI agent can execute an action.

Deterministic Routing

Ensures that agent intents are mapped to strictly typed API endpoints with predefined schemas, eliminating hallucinated function calls.

Governance Layer

Every mutation request passes through the HITL (Human-In-The-Loop) validation gateway before execution.

Human-In-The-Loop (HITL)

For high-risk operations, Stellaris AOS pauses execution and queues a validation request for a human operator.

[Agent: Procurement] -> Intent: Purchase Order [Stellaris AOS] -> Intercepted: High Risk (Budget > $0) [Stellaris AOS] -> State: PAUSED_WAITING_APPROVAL [Human Operator] -> Validates via Dashboard -> State: APPROVED [Stellaris AOS] -> Executes API Call -> SAP / ERP

Competitor Benchmarking

Capability	Stellaris AOS	Standard iPaaS (e.g., Zapier)	Custom Python Scripts
Multi-Agent State Sync	Native (Graph-based)	No	Manual Dev Required
HITL Constraints	Enterprise Grade	Basic (Email approvals)	Manual Dev Required
ISO 42001 Auditing	Built-in (Immutable Logs)	None	None

Frequently asked questions

What does the Stellaris AOS documentation cover?: It covers how to deploy and operate the platform: agent definitions, the orchestration layer, permission scopes, Human-In-The-Loop approval gates, audit logging and the integration endpoints used to connect enterprise systems.
Do we need our own engineering team to run it?: No. We deploy and operate the infrastructure for you in isolated environments. Your team owns the business knowledge and the approval decisions; we own the orchestration, the routing and the security perimeter.
How do we start a deployment?: Start from a single process with a measurable bottleneck. We map how the work happens today, define the agents and their permissions, deploy the first cell with full traceability, and expand only once that process runs reliably.