Find your next step.

Ctrl / ⌘ K to open · Esc to close · Demonstration commands use fictional data.

PLATFORM / AGENT RUNTIME

Give every AI worker
an identity.

An agent should be more than a prompt with tools. Define its mission, owner, permissions, memory, budget, and evaluation criteria. The runtime concept turns these controls into the operating conditions for each task.

Explore the live demoPlatform architecture
INTELLIGENCEOS / PLATFORM01 — OVERVIEW

02 / THE OPERATING CONTRACT

What agent runtime
brings into view.

01

Identity and mission

Assign a stable ID, a responsible team, a role, and a measurable outcome. A narrow mission is easier to evaluate than an open-ended instruction.

02

Tools and permissions

List approved systems and actions explicitly. Read, draft, and execute are different privileges and should be reviewed separately.

03

Memory and context

Scope memory to the worker’s role. Keep source references and freshness alongside retrieved context, rather than treating remembered data as current truth.

04

Versions and evaluation

Track changes to policies, tools, model configurations, and agent instructions. Compare evaluations before promoting a new version.

03 / CONNECTED BY DESIGN

The path
through the system.

Inspect the sequence.
Each stage has a defined responsibility.

Select a node to inspect its role in the workflow.

Before work begins.

Define the source of truth, permitted actions, accountable owner, and acceptance criteria. Scope matters more than an open-ended instruction.

Before work moves on.

Check the outcome, capture unresolved exceptions, and preserve the relevant policy and evidence. A task is complete only within its defined boundary.

04 / A CONCRETE EXAMPLE

Meet FINANCEOPS-17.

This fictional worker belongs to Northstar’s finance operations team. It uses a private reasoning model concept, can read ERP and warehouse records, and can draft a report. FIN-04 requires human approval for an external action. Its mission is reconciliation; payment approval is outside its role.

ILLUSTRATIVE SCENARIO

A practical agent specification includes task limits, data permissions, timeout behavior, failure recovery, and a named escalation owner.

Defined scopeEvidence preservedReview when required
Try the control plane

05 / QUESTIONS & BOUNDARIES

Details
that matter.

Architecture descriptions show intended system behavior. Validate implementation, integration, data handling, and operational controls before relying on a production workflow.

Can an agent change its own permissions?

The design principle is that permission changes require a separate authorized control process. An agent’s request does not grant itself access.

What happens when a budget is exhausted?

The proposed runtime pauses or stops the task and records the limit reached. It should not silently continue using more time or resources.

How does this fit with the rest of IntelligenceOS?

Identity, context, policy, evaluation, verification, execution, and audit form one operating model. Explore the related components below to see their responsibilities.

06 / CONTINUE THE EXPLORATION

See the whole
operating picture.