Skip to main content

HOW IT WORKS

Architecture and deployment

The runtime, Intelligence Packs, drivers, and how a deployment fits inside a customer environment.

Huitzo helps regulated companies use AI without losing control of data, workflow, or audit records.

AI applications, called Intelligence Packs, run on that control layer. Huitzo is model-agnostic and deploys in weeks instead of the 12-18 months a custom build typically requires. This page explains the mechanism: what executes, where AI fits, and what evidence each run leaves behind.

Section 1: THE MECHANISM

What happens when a Pack runs

Your own artifacts, made legible to an AI layer that lives where they live.

FIG. 01. THE SAME SYSTEM, IN YOUR NOUNS.

YOUR NETWORK BOUNDARY YOUR DOCUMENTS YOUR POLICIES YOUR TEAM INTELLIGENCE PACKS DETERMINISTIC LAYER YOUR INFRASTRUCTURE ONE GATE ANY MODEL YOUR CHOICE OF PROVIDER, HOSTED OR SELF-HOSTED PROMPTS LEAVE YOUR DATA STAYS YOUR NETWORK BOUNDARY YOUR DOCUMENTS YOUR POLICIES YOUR TEAM INTELLIGENCE PACKS DETERMINISTIC LAYER YOUR INFRASTRUCTURE ONE GATE ANY MODEL YOUR CHOICE OF PROVIDER, HOSTED OR SELF-HOSTED PROMPTS LEAVE YOUR DATA STAYS
Your documents, your policies, and your team feed the deterministic layer on your infrastructure. Any model, through one gate.

Deterministic Python executes

An Intelligence Pack is business logic written as code your team can read, test, and audit. The code owns the decisions and runs the same way every time.

AI is invoked only where it adds value, bounded

Where a step genuinely needs a model (classify, extract, summarize) the Pack calls one through a declared driver, either a self-hosted model inside your boundary or a hosted provider, and the record states which. AI augments the process; it does not own it.

Every run emits an audit record

The execution itself produces the record: what ran, what the AI step saw, what was approved, and what data never left the network. Not a log you hope is complete; evidence produced by the run.

Every Intelligence Pack ships with a machine-readable Policy Card declaring allowed actions, data-handling scope, escalation requirements, and logging obligations, and the platform logs every action for audit. Packs never phone home; that is enforced by architecture, not policy.

Section 2: THE DIFFERENTIATOR

Observers prove what crossed the wire. Huitzo proves what your application did.

Most AI assurance tools watch from outside. They can tell you what crossed the wire. Huitzo is the runtime your AI applications actually run on, so the evidence of what happened is produced by the execution itself.

Inspect a sample audit record SAMPLE. VERIFIED AT BUILD TIME.

Section 3: THE RUNTIME

The runtime

Like the Linux kernel hosts processes, the Huitzo runtime hosts Intelligence Packs. It is deployed inside the customer environment as a single Linux service.

YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS
One service on your infrastructure. Everything else runs inside it.

Section 4: INTELLIGENCE PACKS

Intelligence Packs

An Intelligence Pack is an AI application: the unit that gets deployed, versioned, and audited. Like a containerized application on a Linux host, but with one shared interface to models, storage, and drivers. Most deployments start from the standard Pack library rather than a blank repository. Where nothing in the library fits, a team builds a custom Pack against the same interface, and it runs on the same runtime inside the same boundary.

YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS
Packs slot into the runtime the way applications install on an operating system.

Section 5: DRIVERS

Drivers

Drivers extend Huitzo to external and internal systems, the way Linux device drivers extend the kernel. Standard drivers ship for OpenAI, Anthropic, and S3-compatible storage. Custom drivers connect the runtime to databases and proprietary systems.

YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS
Drivers connect the runtime to models and external systems, self-hosted or hosted, and the record states what crossed the boundary.

Section 6: DEPLOYMENT

Deployment in five steps

STEP 1

Provision the runtime host

Stand up a Linux host inside the customer environment. The runtime needs network access to the chosen model provider, or to a self-hosted model, and to the systems the Intelligence Pack will integrate with.

STEP 2

Install the Huitzo runtime

Run the Huitzo install script. The runtime is a self-contained service. No data is sent outside the host during installation.

STEP 3

Configure drivers

Drivers connect the runtime to model providers, object storage, and internal systems. Standard drivers ship out of the box; custom drivers extend the runtime to anything proprietary.

STEP 4

Deploy an Intelligence Pack

An Intelligence Pack is the application unit that runs on the runtime. Build locally with the Python SDK, then deploy to the runtime.

STEP 5

Connect the Hub

The Hub is the operations dashboard for monitoring and managing deployed Intelligence Packs. Authentication plugs into the customer identity provider.

Section 7: ENGAGEMENT

From conversation to production

Intelligence Packs go live in weeks instead of the 12-18 months an internal build takes, and every Pack runs inside the customer's environment.

Conversation

A working session with the founder. Your environment, your processes, and whether an Intelligence Pack fits. No deck.

Scoped pilot

One process becomes an Intelligence Pack running inside your environment, with audit records from day one to judge it by.

Production

The Pack goes live where your data lives, and every run keeps producing its own evidence.

Book a working session

Section 8: QUESTIONS

How it works: questions

What gets installed on customer infrastructure?

A single Linux service, the Huitzo runtime, plus the Intelligence Packs the customer chooses to deploy. There is no Huitzo-managed cloud component on the data path.

Where do AI models run?

Huitzo is model-agnostic. The customer chooses: a hosted provider (OpenAI, Anthropic) reached over the network, or a self-hosted model on customer infrastructure for fully air-gapped deployments.

How long does deployment typically take?

Most production deployments take weeks rather than the 12-18 months a custom build typically requires. Air-gapped environments take longer because of additional integration scope.

How do Intelligence Packs differ from containers?

An Intelligence Pack is a Huitzo-runtime application, like an ELF binary on Linux. It runs on top of the runtime, which provides the shared interface to models, storage, and drivers. A container is a packaging format; an Intelligence Pack is an application unit.

Section 9: CLOSING

AI operating system for regulated companies

Simple by design. Built to scale. Runs where your data lives.

Product access
Huitzo Hub is available by invitation for teams evaluating the product.
Book a working session
Read the specification SPEC v0.1. DRAFT. Inspect a sample audit record SAMPLE. VERIFIED AT BUILD TIME.