Generative Specification · a discipline by Juan Carlos Ghiringhelli

Build software with AI that doesn't quietly fall apart six months later.

AI writes plausible code fast, and every new session is a stranger to the last. Generative Specification keeps intent explicit enough that any reader, human or AI, can rebuild the system without guessing.

AI writes plausible code fast, and then every new session is a stranger to the last. Generative Specification keeps intent explicit enough for a stateless reader, human or AI, to rebuild a system without guessing. A specification, a harness that verifies it against a running system, and a standard you can hold a codebase to. Everything here is designed to be used, not just read.

A discipline, tools, and training by Juan Carlos Ghiringhelli.

No install, no CLI: paste one prompt into your AI assistant and get a scored report with a remediation plan.  ·  For teams and buyers, see engagements →

Start Here

Two ways in

Whether you write the code or you own it, the fastest path is to see the discipline work on a real codebase.

For practitioners · free
You build software with AI

Try it on your own code in 20 minutes, no install. Score a repo, see the failure modes named, get a remediation plan, then use the gates and spec templates to hold the line across sessions.

For teams & buyers
You own or are acquiring a codebase

Get an independent read you can act on: a Readiness Assessment scored to a maturity level, remediation that installs the guardrails in place, or technical due diligence with a clear asset / conditional / liability verdict.

From the field
"Everyone feels like a systems engineer capable of building things now, but the truth is it gets us into trouble, especially at publish time."
— Operations lead, a LATAM brokerage · after the Forge workshop
"A non-technical analyst on the team built an audit agent for their CRM from what he learned, documented it, and presented it to leadership. They called it complete."
The Discipline

Generative Specification

A programming paradigm for the stateless reader. Seven properties that make a specification derivable by an AI that carries no accumulated context, so the decisions that hold a system together stop being forgotten between sessions.

Open Tools

The MCP Stack

Free tools for individual developers. Each one addresses a specific failure mode of AI-assisted development.

Quality Gates · Free
The Gate Template

Portable quality gates, one per property, wired to standard tools: mutation, real coverage, complexity, duplication, dead code. Hand it to your AI and it cables the gates into your project straight from the spec. The ratchet only goes up.

Quality gates →
Code Intelligence · Free
CodeSeeker

Graph-powered hybrid search for your codebase. Vector + BM25 + path, fused with RRF. Semantic search, dependency traversal, and contextual file reads — the AI reads your codebase the way you do, not just grep.

GitHub
Memory · In Development
Chronicle

Three-tier persistent memory for AI sessions. Buffer, Working, and Core layers with Ebbinghaus decay and an intelligence distillation layer. Cross-project knowledge that survives context boundaries.

GitHub
Training

The Forge

Two days. Your team. Your codebase. A different speed.

Train your team in the discipline that keeps AI-built code correct

Point AI at a codebase and you get plausible output fast, then pay for it in review and rework. The Forge teaches the discipline that makes the output correct enough to trust: spec-driven development, clean architecture, and directing AI against a spec instead of prompting into the dark. Two days, on your actual codebase, with your team.

Book a Conversation
Investment
$20,000
2 days · up to 15 engineers
on-site or remote
Writing

Ambient Engineer

Long-form writing on specification, AI-assisted development, and what it means to engineer in an age of stateless readers.

ambientengineer.dev The Harness Manifesto →
Contact

Get in Touch

Workshop inquiries, research questions, collaboration.