Blog

Coding with AI, without losing control.

Methods, field notes and points of view from the Lyriks team.

Open source

From Unspaghettit to Lyriks Community Edition: Moving Your Projects

A thank-you to the first Unspaghettit users, what the Community Edition adds, and how to move your projects across in four steps with your own LLM.

November 5, 2026 · 2 min read
Legacy

You Just Inherited a System. Here Is What to Do Before You Touch It.

A takeover goes wrong when the first weeks go to patching. Four habits to know one module precisely and ship a first change you can stand behind.

November 4, 2026 · 5 min read
Sovereignty

Approving an AI Dev Tool: A Security Review That Checks Instead of Trusting

Network flows, install scripts, the LLM question and the answers a vendor can't give yet. How our security pack is built to be verified on your own pilot.

November 4, 2026 · 5 min read
Verifying AI code

What a Release Gate for AI-Written Code Actually Needs

Review says whether code is well written. A release gate must say whether it does what was decided. Four ideas from our white paper.

November 4, 2026 · 5 min read
Comparison

AI Code Review and Spec Verification: Running Both on Every Pull Request

Your AI reviewer comments on the diff; spec verification checks the code against the rules you validated. How to run both on one pull request.

November 2, 2026 · 5 min read
Sovereignty

Running an AI Tool Without Your Code Leaving the Building

A hospital IT team wants AI help on its appointment module. The CISO has three questions. Here is how an on-premise, air-gapped setup answers each one.

October 29, 2026 · 4 min read
Verifying AI code

Additions, omissions, regressions: the three gaps in AI-generated code

AI-written code can pass review and still drift from the spec in three ways. A checkout change shows how to name additions, omissions and regressions.

October 27, 2026 · 7 min read
Agents

Claude Code, Cursor, Copilot: give your agents the right spec with MCP

A coding agent builds from the context it gets. Over MCP, it can work from a validated spec with rules and sources, then be checked rule by rule.

October 21, 2026 · 4 min read
Comparison

AI code review or verification against the spec?

AI code review reads code once it's written. Verification checks it against what was decided. A one-cent VAT rounding change shows why you need both.

October 15, 2026 · 6 min read
Method

Spec-Driven Development: The Promise and the Blind Spots

Writing the spec before the agent codes is the right instinct. But a Markdown spec can't be verified and knows nothing of the existing system.

October 13, 2026 · 6 min read
Evolutions

The impact report: know what breaks before you write a line

Features, rules, screens and data touched, conflicts, tests, the decision to make: how an impact report moves the decision before the code.

October 7, 2026 · 4 min read
Migration

Migrate Off Delphi Without Losing a Single Business Rule

Delphi migrations rarely fail on syntax. They fail on a rule nobody wrote down. How to recover every rule, get sign-off and verify the new code.

September 24, 2026 · 7 min read
Evolutions

Simulate a Change Before You Code It

Two harmless-looking changes, one hidden billing conflict. How simulating the impact on a reverse-specified model surfaces it before anyone opens an editor.

September 22, 2026 · 5 min read
Legacy

Taking Over an Undocumented Project: A Five-Step Field Guide

You've inherited payroll software nobody can explain and nobody dares touch. Five steps to understand it, tie it to a spec and start changing it again.

September 16, 2026 · 7 min read
Verifying AI code

Deterministic or probabilistic: who should verify AI-written code?

Asking one model to check another's code stacks probability on probability. A loan eligibility rule shows why verification needs a deterministic engine.

September 10, 2026 · 4 min read
Method

False productivity: when AI speeds you up without moving you forward

More pull requests, more commits, longer reviews. A two-week sprint shows where AI speed goes, and how to measure real progress instead.

September 8, 2026 · 7 min read
Memory

Models Change. Memory Stays.

Coding assistants turn over every few months. What you know about your software, and why it works that way, has to stay with you, whatever the model.

September 2, 2026 · 4 min read
Open source

Why We Open-Sourced Our Engine

Lyriks is open source under the AGPL and installs with one command. A short case for why a tool that verifies your code should be open to verification itself.

August 27, 2026 · 4 min read
Method

Why 70 Pages of Markdown Won't Give You Back Control

An LLM can document your codebase in readable pages you can't verify. A structured spec, linked to the code and checked, answers what they can't.

August 20, 2026 · 3 min read
Legacy

Reverse Documentation vs. Reverse Specification: The Difference That Matters

Reverse documentation gives you pages of text. Reverse specification gives you a model of the whole system, linked to the code and checked.

August 18, 2026 · 5 min read
Legacy

Reverse Specification: Recovering What Your Code Is Supposed to Do

Reverse specification pulls business rules, journeys and invariants out of existing code, each linked to its source. A walkthrough on a streaming platform.

August 12, 2026 · 5 min read
Verifying AI code

AI Writes Twice as Much Code. Who Reviews It?

AI has nearly doubled merged pull requests and review can't keep up. Five common beliefs about reviewing AI code, and what actually holds up.

August 6, 2026 · 5 min read

Keep your software in tune

Start with one module. Lyriks recovers its spec, then verifies every change. All it needs is your repository.