Open Digital Product Factory

Find your business

Built for how your business actually works

DPF isn’t a blank tool you configure for weeks. Pick what you do and the whole platform — your public storefront, the words your AI coworkers use, your scheduling, your finances, your compliance defaults — reshapes itself to match. Fifteen market categories and 56 ready business types ship in the box.

In plain terms

One install gives you a website your customers can use, a place to run the work, and AI coworkers that already speak your line of work. You approve the important moves, and everything stays on your own computers.

One backbone, many shapes

Every small business runs the same five moves

Attract someone, capture their intent, deliver the thing they pay for, account for the money, and keep the relationship. What differs is which move is make-or-break — and DPF tunes itself to that for each business below.

How a small business runs on DPF The customer engages your business, which runs on DPF; value is delivered and money recognised, an AI coworker assists, the whole flow is governed, and the relationship loops back. You approve every step · you approve every step — and it's all logged CUSTOMER a stranger with aneed YOUR BUSINESS · ON DPF Your business, reshaped tohow it actually runs VALUE + MONEY Value delivered Money recognised truthfully AI COWORKER speaks your language, not jargon is captured delivers value The relationship persists & compounds

Scroll the diagram sideways →

The same governed backbone underneath; a different load-bearing stage on top. That’s why a salon, a plumber, a credit union, and a food bank each get a platform that feels purpose-built.

Grouped by how you operate — not by industry jargon

You go to the customer

Field & dispatch

A technician, crew, or officer travels to the customer’s property or vehicle. The work lives on a dispatch board and finishes on-site — so routing, job context, and field invoicing are what make or break the day.

Customers come to you

Appointments & booking

People book time with a named person or place. The calendar is the product: real per-provider availability, the right records on hand, and a nudge to come back.

You sell goods

Catalogue & orders

Browse → cart → checkout → fulfil. The moment of commitment can’t drop a product image, a price, or a delivery detail, and repeat buyers should be recognised.

You serve members & community

Members, residents & regulated

Donors, members, residents, ratepayers, borrowers. A trust gate — eligibility, disclosures, the duty to serve everyone — comes before the value stream, and money is recognised as a receipt or a statutory fee, not a hard sell.

You rent, build & advise

Projects, rentals & engagements

Quotes, proposals, agreements, rental periods, milestones. Value is delivered over time under a scope or an agreement, with the customer’s estate kept clean and isolated.

For builders, resellers & architects

Under the hood

Everything above is for the people running a business. The rest is the technical detail for those who extend, resell, or evaluate the platform.

How it's built

One business type generates the whole setup

The business type you pick at setup is the single source of truth (StorefrontConfig.archetypeId in the data model). From it, DPF generates the website wording, scheduling defaults, finance assumptions, licence hints, the words each AI coworker uses, and the direction of the mobile app — which is how one platform covers 19 business types without a custom app for each. (For builders, the precise internal term is the “archetype”.)

SOURCE OF TRUTHBusiness typeStorefrontConfig.archetypeId
DERIVESGenerated setupactivationProfile · axes · vocabulary
Storefrontintake, CTAs, sections
AI coworkervocabulary, tools, routing
Workflowsscheduling, finance, compliance
Mobile manifestcapability direction (vision)

For architects & standards reviewers

DPF as a reference implementation

DPF is a working prototype for two proposed standards — not a claim of full present-day conformance. TAK governs what an agent may do; GAID governs who the agent is and what evidence follows its actions. Here is what is real today, what is partial, and what is still proposed — the gaps are mapped, not hidden.

TAK — Trusted AI Kernel

The runtime-governance harness: authority mediation, tool-execution gating, human-in-the-loop, memory limits, and audit/evidence — enforced as an agent operates.

GAID — Global AI Agent Identification & Governance

Who an agent is, the claims it carries, and how its actions are identified and traced — identity documents, badges, authorization classes, and action receipts.

Implemented now

  • Route-scoped AI coworkers — each route gets a purpose-built coworker with its own tools and vocabulary
  • Tool authority = grant ∩ user capability — every tool exposure filtered by user authority, mode, and external-access posture
  • Proposal-mode gated actions — consequential actions break the loop and return an approval payload instead of executing
  • Tool-execution audit logging — every call written to ToolExecution — agent, user, tool, params, result, route, duration, audit class
  • Archetype-driven UX & vocabulary — storefront, scheduling, finance and compliance defaults generated from one archetype
  • Internal agent registry — stable identifiers, model bindings, supervisors, delegates, grants, HITL defaults

Partially implemented

  • TAK runtime transparency — an Authority & Audit workspace with a supervisor-ready Agent Card snapshot
  • Agent Card / AIDoc projection — the registry approximates an AIDoc — not yet signed or resolvable
  • Stable internal agent identity — platform-local today, not yet canonical GAID identifiers
  • HITL tier metadata — carried per agent, not yet one uniform runtime policy engine
  • Delegation & authority modeling — supervisor & delegation recorded, not yet a receipt-backed chain
  • Chain-of-custody trace — agent, user, route and tool recorded; not yet end-to-end across boundaries

Planned / proposed

  • Signed / tamper-evident receipts — cryptographically verifiable receipts for consequential actions
  • GAID public/private namespaces — explicit private vs externally-accredited public identity scopes
  • Public verifier metadata — published A2A Agent Cards and external receipt-status endpoints
  • External certificates & status — issuer validation and public status services for exposed agents
  • Capability & governance badges — evidence-backed assurance levels
  • Repeatable conformance suites — automated TAK & GAID test packs preserved as evidence

Grounded in the platform’s own first-pass assessment: TAK / GAID conformance assessment · TAK · GAID · governance white paper. DPF is the proving ground where these ideas are exercised in real workflows.

Vision · not yet shipped

The mobile app — where this gets even better

Even when the work isn’t in the field, you are. We want a pocket app that pings you when a coworker needs a yes or no on a risky step, and lets your customers book, track, and pay from your own branded app.

One generic native iOS/Android app (published by Arcamanus LLC) that connects to your own install and lets the platform drive its look and features — so field techs, customers, and you each get the right screens without a separate app per business.

Where it stands today: the foundation is real and in the codebase — a React Native/Expo app shell (native shell + install manifest + offline form/screen renderer), a REST API, and secure sign-in. The end-user experience — persona-aware screens, connecting one app to any install, push notifications, and App Store / Play delivery — is the next phase and not yet available. We’re building toward field dispatch and owner approvals first.

Don’t see an exact match?

The 56 business types are starting points — the platform adapts further to your specifics during setup, and your AI coworkers keep tailoring as you go. Install and choose the closest fit.

Install Back to overview
↑ Top