Back to cases

225 features and 3 releases a day over 16 weeks

We are building a program management and profitability system for a global automotive parts maker entirely through vibe coding and iterative, requirement-by-requirement development.

AI-Native Development · Build

Client
Global automotive parts maker
Domain
Program management & profitability
Approach
End-to-end vibe coding · AX build
Timeline
Kicked off June 2026 · ongoing

The project in numbers

16 wks

Since kickoff

225

Features · 12 business areas

700+

Screens

~3,000

APIs

10,000+

Commits

2,800+

Merge requests

3 / day

Releases

500+

Requirements delivered

Measured as of October 8, 2026

The challenge

  • Twelve business areas — orders, cost, profitability, quality and schedule — and 225 features had to come together in one system.
  • Business teams, the PMO and developers moved together, so requirements kept arriving and changing.
  • The usual enterprise system build — freeze requirements, go live months later — could not handle the schedule and the change at the same time.

An AI-native delivery process

VIBE OPS methodology

VIBE OPS is a development methodology in which AI drives the work from requirement to release and records. When a requirement comes in, AI writes the documents, code, release and progress records in a fixed order; people request, approve and check the result on screen.

How one requirement flows

AIPeople
  1. Submit requirement
  2. Analyze · write PRD
  3. Approve scope
  4. Dev spec · test scenarios
  5. Break into work items
  6. Build · verify locally · open MR
  7. Review · merge
  8. Release at fixed times · release notes
  9. Record each stage
  10. Check on screen · sign off

Who does what

Requirement

AI doesAnalyzes it, drafts and files the PRD

People doSubmit requirements, approve scope

Design

AI doesWrites dev specs and test scenarios, splits work items

People doReview specs

Build

AI doesWrites and refactors code, writes tests, verifies locally, opens MRs

People doReview, decide merges

Release

AI doesWrites release notes for each release

People doNone — merged changes ship at fixed times

Records

AI doesLogs stage start/finish, dates and comments automatically

People doFinal check on screen, sign off

Three principles

Progress is never typed by hand

Records are created when a stage actually finishes, and progress is calculated from them.

Scope grows only by approval

Approving a requirement approves its scope; work items exist only inside it.

Procedures live in AI skills

From branching to checks, MRs, merges and release notes, 16 skills make everyone follow the same order.

An integration interface that connects AI to the work

VIBE OPS system · Ops CLI

The VIBE OPS system is the requirements and work-item system built for this methodology, and Ops CLI opens its API on the command line. People use the web screens; AI uses the CLI on the same data. With an AI agent integration interface, AI became a participant that reads requirements and records progress itself.

AI working through the CLI (example)
# 1. Read the requirement as development context$ ops req get REQ-101# 2. File the PRD and move the requirement to approved$ ops req artifact save REQ-101 prd prd.md$ ops req status REQ-101 APPROVED "PRD filed"# 3. Split it into work items$ ops dev add --process PRC-01 --title "Quote list screen" --type SCREEN$ ops dev add --process PRC-01 --title "Quote history API" --type API# 4. Record each stage — progress is calculated from here$ ops dev stage step DEV-201 BUILD DOING$ ops dev stage step DEV-201 BUILD APPROVE

How we opened it safely

Irreversible actions stay human

Deleting and revoking approvals are not in the CLI — people do them on the web.

Only within assigned work

AI can write only to the items assigned to its user.

Tokens never exposed

Auth tokens are passed so they never appear on the command line or process list.

Order enforced by the server

A stage can't start until the previous one is finished.

Open a CLI on a business system and AI can take part in that work. The re:boot Agent demo applies the same idea to sales, service and finance.

What was different from a traditional system build

Requirements

re:boot AX buildTaken one at a time and delivered right away

Traditional system buildFrozen before kickoff

Design docs

re:boot AX buildDrafted by AI (PRD · specs), approved by people

Traditional system buildWritten by people over weeks

Development

re:boot AX buildEnd-to-end vibe coding with AI agents and 16 skills

Traditional system buildHand-written code

Releases

re:boot AX buildScheduled releases at fixed times (three a day as of Oct 8)

Traditional system buildPhased go-lives months apart

Progress tracking

re:boot AX buildCalculated from stage records

Traditional system buildManual spreadsheet reports

Handling change

re:boot AX buildAbsorbed one requirement at a time

Traditional system buildChange request → renegotiation

Business involvement

re:boot AX buildDaily checks and feedback in the dev environment

Traditional system buildTesting just before go-live

The same idea across the business

Try an AI agent that handles several business systems from a single sentence.

See the re:boot Agent demo

Would this work for us? Find out with a free two-week on-site diagnosis

Pick one workflow and we'll diagnose it on site for two weeks, then hand you a report and a build proposal. No obligation to go further.

Explore consulting

Transform your organization
with AI — starting now

A simple consultation can reveal where to automate and how to boost productivity across your business.

Book an AX call

A 30-minute call is booked with a calendar invite · no obligation

terry@reboot.im