What if someone had already solved that problem?
re:boot builds up domain knowledge by industry and workflow with every AX project. Find cases close to your industry and your work, and what we learned along the way.
Cases
Cases by industry and workflow
Clients are named only by industry and size. The demo uses a fictional company and no real customer data.
Twelve business areas in one system: 225 features in 16 weeks
Global automotive parts maker · Program management and profitability analysis system
Over 500 requirements delivered, with AI driving each one from requirement to release and record — 700+ screens and about 3,000 APIs.
From a daily flood of news to AI reports on the topics you follow
Major card company · Trend news sensing portal
A research flow — choose topics, analyse news, get reports, receive alerts — built into an AI portal connected to the company's SSO, email and messenger.
Booking rules dug out of legacy code and moved behind APIs
Golf booking platform · Platform rebuild
AI found and documented booking and group-join rules scattered across old screens and SQL, and the platform was rebuilt around APIs that AI agents and other services can call.
Twelve manual entries become one request and one approval
re:boot Agent · Fictional company demo · No real customer data
Procedures live in skills, execution stays in existing systems. Contract → activation → billing with one natural-language request and one human approval.
Why cases
Every case makes the next AX project faster
A finished project leaves more than a system. It leaves domain knowledge — the rules and procedures of the work — and the next project in the same industry and workflow starts from there.
- Work on the ground
- Captured as domain knowledge
- Redesigned for AI to do the work
- Built and run
- Starting point for the next project
AX Field Notes
AX Field Notes
A ten-part series that follows a global automotive parts project from the start. Rewritten for the web from our social posts.
- #1We use AI. So why hasn't the way we work changed?Handing out AI accounts and adding a chatbot isn't AX if the order of work stays the same. Three questions that separate AX from AI adoption.
- #2Why requirement changes are really so expensiveChanges aren't expensive because of code, but because of the analysis, documents, tests and reporting that follow them. How we handed that work to AI agents.
- #3From one requirement to release: what the AI agent doesWe didn't hand AI a line of code; we handed it a whole requirement, start to finish. Who does what at each of five steps.
- #4Integrating business systems with AI agentsAn AI agent can't work in a system that only has screens. How we wrapped a requirements management system's API in a CLI and connected it.
- #5What we didn't hand to AITo hand AI more, we first had to decide what it would never do. Five rules that build boundaries AI can't cross into the system itself.
- #6Sixteen weeks in numbersComing up
- #7Rules, not tools, made us fastComing up
- #8AX is ultimately about peopleComing up
- #9Next: beyond the system, into the business workflowComing up
- #10Where should our company start?Coming up
Partners
IT services or consulting firm bringing AX to your clients?
We want to deliver AX projects with partners who know their clients' operations well. Tell us how we could work together, from on-site assessment to pilot.
Would this work for us? Find out with a free two-week assessment
Pick one workflow and we'll assess how it changes when AI does the work, then hand you a report and a pilot proposal. No obligation to go further.