Method · How I build

I design the system. Then I direct AI to build it.

Code isn't improvised. I define the contracts first —vision, domain, architecture, rules— and only then I build, orchestrating AI under strict rules. Architecture is the absolute priority; code is a consequence.

"No line of code is written until the contract is complete."
Rule #1 · Master Contract

The process // 01

From concept to product, in phases.

Each phase ends before the next begins. Content is never produced before the systems capable of supporting it.

  1. PHASE 0

    Vision and contract

    I document what is being built and why. The highest-level contract. Zero code.

  2. PHASE 1

    Domain and architecture

    Entities, invariants, modules and contracts. Structure before behavior.

  3. PHASE 2

    Rules and data contracts

    What is data and what is code. Versioned schemas and fail-fast validation.

  4. PHASE 3

    Vertical slice

    The minimal cut that proves the architecture works, end to end.

  5. PHASE 4

    Construction

    AI implements against the contracts. I review architecture, trade-offs and decisions.

  6. PHASE 5

    Validation and production

    Build, tests, validators and post-work. Only then, to production.

The contracts // 02

Thirteen documents before the first line.

Every project starts with a hierarchy of living documents: when two decisions conflict, the higher-level document wins. This is BabelDestiny's, my game engine in development.

00

Vision

What is built and why. The highest-level contract.

01

Domain model

Entities, relationships, states and invariants.

02

Design

Core loop, mechanics and progression.

03

Technical architecture

Stack, modules, loaders and contracts.

04

Data-driven rules

Data vs. code, schemas and validation.

05

Vertical slice

Scope and acceptance criteria of the first cut.

06

AI rules

How the AI should work on the project.

07

Folder structure

What lives —and what does not— in each folder.

08

Coding standards

Language conventions.

09

Content pipeline

How each piece of content is created and validated.

10

Roadmap

Phases 0→6 and advancement criteria.

ADR

Decisions

Architecture decision record, each with its rationale.

Orchestrating AI // 03

AI builds. I decide.

I treat AI as a very high-level executor, not an oracle. Every behavior must be explainable; no decision is magic.

Design and decisions

Me + reasoning models

  • Vision, domain and architecture
  • Trade-offs and decisions (recorded as ADR)
  • What is data and what is code
  • Scope and acceptance criteria
Implementation

The AI, under rules

  • Builds against the existing contracts
  • Tier 1 flows; Tier 2 (architecture, schemas) stops and asks
  • Mandatory post-work: build, validation, tests
  • Documents marked "approval required" are never touched alone
Propose → confirm → implement → document → test ADR for every decision Fail fast Validate everything Zero hardcoded content

Principles // 04

The rules that aren't up for debate.

Case · In development

BabelDestiny

A data-driven engine for an isometric Action Roguelite. Before writing a single line of code, I documented the entire architecture: the full hierarchy of contracts and the rules for AI to build without drifting. The goal isn't a game: it's an engine that grows by adding data, never by touching code.

13contracts written first
0hardcoded content
100%data-driven

Let's build systems that last.

For products that need real architecture, not throwaway prototypes.