How I work with AI

AI with accountability

AI helps me move faster through repetitive delivery work. It does not replace business judgment, architecture review, or responsibility for the result.

The delivery process

Most clients have never seen a delivery process. Showing one builds trust immediately. AI is part of it — as a tool that speeds up delivery, not as a slogan. I review the architecture and the code by hand.

• Discovery — I listen to the people doing the work.
• Business analysis — I map the real process and the bottlenecks before any code.
• Architecture — a design your team can maintain, not a black box.
• AI-assisted development — agents draft; I review architecture and code manually.
• Testing — automated tests alongside the feature, not after.
• Deployment — CI/CD ships it; nothing built on the server.
• Support — observability and handover so it keeps running.

How long it takes

Ballpark elapsed time so you can plan. Every engagement starts with paid discovery. Fixed scope is agreed before any build, so price and timeline don’t drift. Milestone payments; escrow available on the first project.

• Automation audit / discovery — 1–2 weeks
• Workflow automation (one integration or process) — 2–8 weeks
• Internal business system (CRM, operations platform, migration) — 2–6 months

What you can count on

• Fixed scope first. I write down what’s in and what’s out before any code, so price and timeline don’t drift.
• Availability. Predictable check-ins — you’re never wondering where the project is.
• Testing. Automated tests alongside the feature, not “we’ll add tests later”.
• Handoff. Docs, deploy steps, and observability so your team can run it without me.

See it in practice

The process above is exactly how the case studies were built. Each one follows Problem → Analysis → Architecture → Implementation → Result → Lessons.