DEIXEI · Engineering reference

The AI Delivery Factory

A practical reference for building software at machine speed while keeping architecture, accountability, control, and evidence attached to the work.

Design

Choose the least complex product shape that meets the need.

Deliver

Commit intent, specification, plan, code, review, release, and evidence.

Operate

Use actuals and evaluations to improve the next delivery cycle.

Key ideas

The factory in eight pictures

Eight ideas carry most of this reference. Each picture is the short version; the reference page behind it holds the full technical diagram, the sources and the decisions.

  1. Agency classes and the least-agency rule: choose the lowest class that meets the need; in a workflow code decides, in an agent the model does.

    01

    Choose the least agency

    Four agency classes run from a fixed workflow, where code decides the next step, to an agent, where the model decides. Start at the lowest class that meets the need and climb only on evidence.

    Read Choose the Shape of an AI Product
  2. Ten recipe families cover most of what a regulated firm will build with AI; start from the nearest family, not a blank page.

    02

    Start from the nearest recipe

    Ten recipe families, ordered by rising agency, cover most of what a regulated firm will build with AI. A new product starts from its nearest family, not from a blank page.

    Read The Ten AI Product Recipe Families
  3. The bill of material and recipe as a living spec — versioned, queryable, with history — consumed by coding agents.

    03

    Keep one living specification

    The bill of material and the recipe are one versioned, queryable specification with a history, and that specification is what the coding agent reads.

    Read Build a Living Product Bill of Material and Recipe
  4. The six-layer product portfolio: reusable primitives at the bottom, differentiated products at the top; funding follows the layer boundary.

    04

    Fund along the layer boundary

    Six layers, from the engineering chassis and AI primitives at the roots to workflow and domain products in the canopy. Platform funding pays for the roots; product business cases pay for the canopy.

    Read Build the Standard Application Foundation
  5. The committed artefact chain from intent to monitoring, where every arrow is a commit and the chain is the audit trail.

    05

    Make every step a commit

    Intent, specification, plan, diff and tests, review, release and evidence: each step is a committed artefact, so the chain itself becomes the audit trail.

    Read The Agent-Speed SDLC
  6. Control, management and data planes: controls do not apply uniformly, and the data plane is the loading bay.

    06

    Lock the loading bay too

    Every resource is reached through a control, a management and a data plane, and controls do not apply evenly across them. Governing the control plane alone leaves the data plane open.

    Read Design the Cloud Production Line and Hosting Boundaries
  7. The gateway is the enforcement point; the egress allowlist is what makes it the only path to the model.

    07

    Make the gateway the only path

    The model gateway enforces identity, policy, data handling and evidence. The egress allowlist is what makes it the only route to the model, and not just one of several.

    Read Design and Operate the Model Gateway
  8. Governance as a continuous loop: policy states intent, actuals record what ran, audit reads the gap, exceptions revise policy.

    08

    Run governance as a loop

    Policy states intent, actuals record what really ran, audit reads the gap between them, and exceptions feed back into the policy.

    Read Close the Policy, Audit and Actuals Loop

Start with a task

Where do you need to make progress?

The reference is organised around decisions and work, so you can enter where your problem starts.

Concept

The AI Delivery Factory: Operating Model

The factory's six connected parts, the control gap it closes, the handover curve that governs what agents may take over, and how to start one without rebuilding your tooling.

Decision Guide

Choose the Shape of an AI Product

A least-agency decision sequence for choosing a product design: agency classes and their trade-offs, the eight questions, evidence for every step up, the consequence matrix that caps action scope, the cut-set review for agents, the other selection dimensions, and the design record.

Implementation Guide

The Agent-Speed SDLC

A committed artefact chain, governed context, trusted tests and eight SDLC controls that let coding agents work quickly while intent, review, identity and evidence stay connected.

Pattern

Workflow Pattern

Use a workflow when code can determine the next step, even when some steps call a model: the eight workflow patterns with their forces and factory notes, why class 2 is the default, how code-orchestrated multi-agent flows stay workflows, how to codify a stable agent path down or delegate exceptions up, and a composite service-desk triage example read across frameworks and cloud pillars.

Pattern

Bounded-Agent Pattern

A class 3 agent lets a model choose the next step, but only inside a registered, validated and enforced envelope of Mandate, Means, Memory and Monitoring.

Worked Example

Worked Example: Research Assistant

A composite Asset Manager X request is split into a grounded assistant and a deterministic routing workflow instead of a multi-agent research crew, then written down twice: as the ten-field design record and as a filled bounded-agency envelope, with two contrasting envelopes and their alert thresholds.

Reading paths

Follow a path for your role

Reference library

Browse by area

Understand

The factory model and the parts that make it work.

Design

Choose a product shape, agency class, and recipe.

Build the platform

Landing zone, identity, data, gateway, connectors and the agent workstation.

Deliver changes

The agent-speed SDLC, release engineering and change governance.

Govern and prove

Controls, regulation, evidence, accountability, models and third parties.

Operate and assure

Run the factory and its agents, respond to incidents, assure and measure.

Adopt and fund

Plan the roadmap, readiness, sourcing, budget and charter.

Patterns

Reusable design choices with explicit trade-offs.

Worked examples

See the decisions applied to a concrete case.

Reference

Glossary, schemas and tools, primary sources and the source index.

A reference that is designed to evolve

This reference is growing in reviewable stages. Draft pages are visible in the local preview with their status and provenance; published builds include only pages that have completed review.

51 pages in this view · 0 marked Draft

See which books and chapters each page draws on →