Architecture platform · not documentation

The operating manual for a layered AI venture ecosystem.

Not a collection of AI projects — one architecture. A system of systems where reusable intelligence compounds from a shared foundation up through platforms, products, and applications to the ventures that serve customers. Every view here is generated from the Portfolio Graph; the markdown remains the single source of truth.

7Reusable capabilities
4Architecture layers
7Repositories
7Architecture decisions
21Governing principles
The problem

Built as separate apps, effort never compounds

A founder running several AI ventures accumulates hard-won intelligence every week — what converts in an industry, how a market behaves, which patterns repeat. Built the obvious way, each venture becomes its own application with its own copy of that intelligence, the same logic, and the same integrations.

So improvements don't travel and nothing compounds: the portfolio grows one unit of work per unit of value and quickly hits a ceiling a single founder cannot pass. The real question isn't "how do we build these apps?" but "how do we build them so every venture makes the next one cheaper?"

The model

One generated model — the Portfolio Graph

The answer is architectural — and this portal maps it. Built from the markdown at each build, the Portfolio Graph is the runtime model this whole site reads: every repository, capability, layer, and decision is a node, every dependency a typed edge. Nothing here is hand-maintained in the UI; it is derived from the source of truth.

161nodes — the entities
847typed edges — the relationships
Architecture

A layered platform

The ecosystem is organised as a stack — each layer consumes the one below and serves the one above; the shared foundation is used laterally by all. Open a layer to see what it contains.

Information flow

How intelligence moves

Knowledge is progressively refined as it moves up the stack — from raw sources into structured intelligence, versioned products, and finally customer-facing outcomes.

Feedback from outcomes is designed to return into the platform as new intelligence — a loop that is planned, not yet built.

Capabilities

The capability ecosystem

Reusable business & technical capabilities, documented independently of the repositories that implement them.

Capability

Architecture & Docs Governance

Document the system of systems and govern its architecture: repository digests, capability architecture,

operational Azwaan 3 connections
Capability

Commercial Opportunity & Outreach

Turn a website assessment into a Commercial Opportunity Profile (COP) — a structured decision on whether a

operational Azwaan 7 connections
Capability

Intelligence Productization

Package the platform's intelligence into versioned, immutable, machine-consumable packs that downstream

operational Azwaan 10 connections
Capability

Knowledge Intelligence

Turn a multi-venture founder's scattered knowledge into a queryable, AI-accessible, scoped asset library:

early-development Azwaan 8 connections
Capability

Reproducible Evaluation

Provide an immutable, fully-provenanced experiment & benchmark harness so engines (assessment, migration,

early-development Azwaan 5 connections
Capability

Reusable AI Skills

Package domain expertise into modular, invocable Agent Skills so competence is built once and reused

operational Azwaan 13 connections
Capability

Website Assessment Platform

Inexis Digital sells websites to service businesses — plumbers, electricians, builders, dentists. To win the

mixed Azwaan 14 connections

Open the Capability Registry →

Ventures

How systems compose

Systems group repositories into the platforms and ventures that deliver capability.

SystemShared Skills

Shared Skills Layer

The Shared Skills layer is the foundational capability layer of the ecosystem: a single curated

Composed of
Governance

How the architecture evolves

Significant decisions are recorded as Architecture Decision Records, and the ecosystem is governed by 21 documented principles.

Architecture Governance →  ·  All decisions →

Operational · deterministic

Portfolio Health

The portal's first operational capability: a deterministic read of the ecosystem's current state, computed straight from the graph — no AI, no estimates.

Open Portfolio Health →

RoadmapFuture

Toward Portfolio Intelligence

The graph and the health engine are designed to power more than a website. These capabilities are planned — not yet built. Future Portfolio Intelligence will interpret the deterministic health outputs, not replace them.

Future

Documentation freshness

Detect stale pages from review dates & cadence

Future

Architecture drift

Flag where docs and repositories diverge

Future

Capability & repo health

Roll graph signals into health scores

Future

Dashboards & APIs

The graph as a data contract for other tools

Portfolio Intelligence readiness →