Product tour

From one request to a governed application.

ObjectStack is the open, typed target format and runtime for AI-written enterprise software: an agent writes compact metadata, a person reviews the diff, and the runtime derives the repeatable application surfaces. ObjectOS is the commercial production platform for building, deploying, and operating those apps.

ObjectOS product surface connecting business data, applications, and AI agents
AI Writes metadata Objects, permissions, workflows, tools
Human Reviews diff Business authority, data access, approvals
Runtime Enforces policy UI, APIs, audit, MCP, actions
<150k tokens
A complete CRM including UI — one context window
<100k tokens
Objects, workflows, permissions, and business logic
~50k tokens
The UI metadata for the complete CRM

Review surface

The diff is the product boundary.

Instead of asking a reviewer to audit a generated application codebase, ObjectStack gives the agent an open, typed definition layer to change: objects, fields, views, permissions, workflows, actions, APIs, and tools.

import { ObjectSchema, Field } from '@objectstack/spec/data';

export const Case = ObjectSchema.create({
  name: 'support_case',
  label: 'Case',
  fields: {
    subject: Field.text({ label: 'Subject', required: true, searchable: true }),
    customer: Field.lookup('crm_account', { label: 'Customer' }),
    priority: Field.select({
      label: 'Priority',
      options: [
        { label: 'Low', value: 'low', default: true },
        { label: 'Normal', value: 'normal' },
        { label: 'Urgent', value: 'urgent', color: '#EF4444' },
      ],
    }),
    status: Field.select({
      label: 'Status',
      trackHistory: true,
      options: [
        { label: 'New', value: 'new', default: true },
        { label: 'Triage', value: 'triage' },
        { label: 'Waiting', value: 'waiting' },
        { label: 'Resolved', value: 'resolved' },
      ],
    }),
  },
});

How it works

The governed build loop

The product loop is designed around the two readers that matter: the AI that writes the system and the human who must understand and approve it.

Human intent

1. Describe the business change

Start with a real operating request: a case queue, approval chain, procurement flow, customer portal, or workflow that already has owners and rules.

AI writes

2. Agent writes metadata

The coding agent edits Strict TypeScript ObjectStack definitions that must conform to the published Zod schemas instead of generating controllers, screens, migrations, APIs, and permission glue by hand.

Human review

3. Reviewer signs off

After the validation gate passes, the reviewer checks a compact diff: field names, relationships, permissions, transitions, workflow rules, and tool exposure.

Runtime layer

4. Runtime supplies surfaces

The ObjectStack runtime derives tables, views, forms, ObjectQL, APIs, audit trails, MCP tools, and admin surfaces. ObjectOS operates the resulting app in production.

Governed AI

5. Agents operate inside policy

AI can query and act through governed tools that inherit identity, record rules, field rules, approvals, and audit logging.

Existing systems

Add an object layer without replacing systems of record

Most enterprise software value is already trapped in databases, ERP, CRM, ticketing, files, and custom systems. ObjectStack gives agents an explicit object model over that estate; ObjectOS gives teams a production platform for operating apps built on it.

Connect databases and APIs

Map existing records into business objects, relationships, calculated fields, and actions without forcing a rip-and-replace migration.

Keep authority explicit

Each object says who can read, write, approve, export, automate, or expose it as a tool. That authority remains visible in review.

Ship new surfaces on top

The same definition can back internal apps, dashboards, portals, workflows, APIs, reports, and AI agent tools.

Decision surface

What changes, who reviews it, what runs

LayerAI writesObjectStack runtime derives
Data modelObjects, fields, relationships, validationsTables, migrations, ObjectQL, generated APIs
ExperienceViews, forms, dashboards, actionsRendered UI, navigation, status states, access checks
GovernanceRoles, row rules, field rules, approvalsRuntime enforcement, audit log, user-scoped tools
AI surfaceAgent tools, skills, prompts, action contractsMCP exposure, policy checks, execution records

Review checklist

A reviewer should be able to answer

  • What business objects changed?
  • Which people, roles, and agents gained authority?
  • Which actions need approval before execution?
  • Which data can leave the runtime, if any?
  • What will appear in audit logs after the change?

FAQ

Questions this page should answer

Is ObjectOS a low-code builder?

No. Low-code usually optimizes human screen building. ObjectOS is the commercial production platform for ObjectStack apps. ObjectStack is the open, typed target format and runtime that keeps metadata reviewable and enforces governance on every call.

How do ObjectStack and ObjectOS differ?

ObjectStack defines and runs the application as open, versioned metadata. ObjectOS is the commercial production platform that adds the in-app AI experience, team operation, deployment choices, and enterprise support around ObjectStack apps.

Next pages

Keep building the evaluation packet.