OmniBuilder.

HOME OF METHOD-DRIVEN ENGINEERING

Your business.
Your specifications.
Your application.

Tell AI about your business. It interviews you, develops specifications, proposes design and architecture for your review, then builds and verifies your application.

Start with MDETry a demo

Open source · MIT licensed · In active development

MDE / BUILD WITH INTENT
A method behind
every build.
01
AI interviews youBusiness goals, roles & rules
02
AI develops the specificationsRefine them through conversation
03
AI designs & buildsYou review design and architecture
04
AI verifies the resultTests & traceable evidence
YOU SET THE GOAL.YOU STEER THE WORK.
AI does the work. You keep the direction.SPECIFICATIONS / CODE / EVIDENCE

01 / THE METHOD

From a conversation
to a working business application.

AI performs the engineering work using MDE's explicit methods and reusable knowledge. Review or change requirements, design, architecture and evidence at every stage.

01

AI asks the questions.

An AI interview discovers your goals, people, processes and rules, then writes versioned specifications you can review.

02

AI makes it tangible.

AI builds a prototype with sample data so you can explore how your application will work before the final build.

03

Review before the build.

AI develops design and architecture for your review, then implements the application using the agreed technology stack.

04

See the evidence.

AI checks implementation against requirements, tests business rules and produces evidence of what works and what remains unresolved.

ENGINEERING KNOWLEDGE / VERIFICATION

More than prompts.
A method AI can improve.

MDE puts engineering knowledge and verification into the project, not just instructions to generate code.

01

Engineering knowledge

AI consults reusable business patterns, features, design guidance and architecture knowledge when relevant.

02

Chat with your specifications

No special syntax to learn. Ask AI to change any entity, use case, rule or design through conversation.

03

Improve the method

The method is editable too. AI can help evolve its strategies, knowledge, meta model and verification rules.

04

Verification & evidence

Verification checks the application against the specifications and records evidence—not merely a claim that it works.

STEP-BY-STEP / MDE TUTORIAL

Watch AI engineer
an application.

Follow a real business application from business understanding through requirements, design, architecture, implementation, verification and evidence. The tutorial uses actual MDE Workbench screenshots and shows where engineering knowledge enters the process.

Open the MDE tutorial →
01 Business02 Requirements03 Design04 Architecture05 Build06 Evidence

TRY & WATCH / DEMOS

See the idea.
Try the rules.

Explore a small scheduling example, then open recorded MDE walkthroughs to see the engineering process.

● LIVE SANDBOXTRY IT — SAMPLE DATA ONLY
HANDS-ON DEMO

A service clinic, in miniature.

Choose a service, practitioner, and time. See how explicit business rules govern which appointments can be booked.

NOT A REAL CLINIC

Book a sample appointment

Loading the interactive example…

The rules behind the action

Required skillChecking
Within available hoursChecking
No overlapping appointmentChecking

Avery: assessments & follow-ups · 09:00–12:00
Jordan: follow-ups · 13:00–16:00

Read the specification

An appointment needs a service, a qualified practitioner, and a start time. Its full duration must fit within that practitioner's available hours. Two appointments for the same practitioner must not overlap.

Sample schedule

One demonstration day

DEMO ENVIRONMENT — Nothing here is real or saved. This example illustrates how MDE business rules can govern an application. Sample appointments disappear when the page reloads.

Recorded walkthroughs

These archived recordings show an earlier version of MDE. Commands and screens may differ from the current release. GitHub access is required.

01 / OVERVIEW

MDE demonstration

Open the existing demonstration recording from the MDE archive.

Open recording on GitHub
02 / REQUIREMENTS

Business analysis recording

Explore the archived business analysis recording alongside the original user story.

Open recording on GitHub

02 / THE WORKBENCH

See the work.
Steer the outcome.

The Workbench makes your project visible: its specifications, running prototype, current goal, and verification evidence.

Explore the Workbench guide
MDE WORKBENCHILLUSTRATIVE PROJECT

An example of the project information MDE helps you explore.

03 / YOUR GOAL, YOUR RIGOR

One method.
Different ways to move.

Choose a strategy for the work ahead. Explore an idea, build with guidance, or check every stage.

EXPLORE

Prototype

Make the idea tangible with diagrams, sample data, and pages on the MDE runtime.

Verification when you ask
BUILD

Guided

Keep the work moving and the gaps visible. Decide what matters before the next release.

Verification on request & before release
CONTROL

Controlled

Confirm choices, verify each stage, and move toward a release supported by evidence.

Verification at every stage
Read about goals and strategies

04 / THE MDE ECOSYSTEM

A foundation you can own.

The method, the tools, and your project's specifications remain visible and editable.

CORE PROJECT

Method & tools

Explore the MDE source, the engineering method, and the Workbench.

View repositoryBUSINESS MODELS

Industry patterns

Explore reusable business concepts and models across industries and common business functions.

Explore patternsDOCUMENTATION

Learn the approach

Understand the concepts, write your business story, and begin your first project.

Read the guides

GitHub resources may require repository access.

LIMITED-TIME OFFER / CHALLENGE MDE

Give us your requirements.
We'll deliver the application.

Tell us about a useful business application. AI interviews you to understand your business, then develops requirements, design and architecture for your review before building the final application. Selected challenges receive a fully tested, production-quality implementation supported by verification evidence.

See how the Challenge worksFollow the MDE tutorial →

Useful business applications only. No games, student projects, programming exercises, or toy applications. Submissions are selected based on business value, suitability, and reasonable scope.

01
AI interview & requirementsAI learns how your business works
YOU REVIEW
02
DesignAI proposes how the application will work
YOU REVIEW
03
ArchitectureAI explains the technical approach
YOU REVIEW
04
BuildProduction-quality implementation
MDE + AI
05
Verification & evidenceTests and documented results
DELIVER

See what AI believes about your business before that understanding becomes code.

05 / GET STARTED

Start with the business.
Build with a method.

MDE gives AI coding agents such as Codex and Claude Code engineering knowledge, strategies, patterns and verification rules. Describe your business in natural language; AI helps interview you and manage the specifications.

Read the quick start

Node.js 24+ required. MDE is in active development and is not yet published to npm.

CREATE YOUR FIRST PROJECT
# After installing MDE from source
mde init my-app
cd my-app
mde workbench
Then open your project in your AI tool
and type /proceed.