Notable verbatim quotes

"I'm doing business applications. So I don't do tools, I don't do products, I do business applications." — Scope (Section 2)

"system use cases were created by Ivar Jakob's own back in 1987" [Ivar Jacobson] — Origin of use cases (Section 4)

"I escaped the plan task phase. I just use this use case of 10th global and generate code." — Core differentiator of the AI Unified Process (Section 5)

"one user story is usually a flow in the use case" — Use cases vs user stories (Section 8)

"use cases are very well defined and even AI knows how to write use cases because it's around for a very long time" — Why use cases work well with AI (Section 8)

"in those projects we don't prompt. So we have skills for everything and we iterate in these fields." — Skills replace ad-hoc prompting (Section 8)

"if you have the product management or the inventory or if that doesn't work, that's probably not even a problem because people that are working with that inventory management system, they can just go grab a coffee. If the order management system doesn't work, that's. More of a problem because then the company probably will lose money." — Risk-based review intensity (Section 6)

"modernization is not left to chess [lift-and-shift] modernization is rethinking how people are working with the software" — What modernization means (Section 7)

"I'm working for an insurance company and they have around 500 microservices... if you have 500 microservices, a lot of components somewhere and you have to mix and match that, that becomes very difficult" — Why microservices are the worst case for AI workflows (Section 10)

"there's an architecture style that not so well known... It's called self-contained system... we create verticals. So we split our application to verticals which has UI, space logic and database in one report" — Self-contained systems definition (Section 10)

"never let AI create a project. First of all, you just raise [waste?] tokens that you do that." — Guardrail #1 (Section 12)

"there's a study from the university in Zurich. And they say the bigger system prompt more hallucinations. You get. So it's maybe even better to have none of those guys than people." — Why keep CLAUDE.md minimal (Section 12)

"if you do a good job and iterate on that, you really get probably. A near deterministic solution. So what I did before I can delete everything, do it again and get more or less the same outcome." — On regeneration determinism (Section 12)

"we don't do pull requests, by the way, at the moment. We do count-paced development and we do kind of an ongoing reading process." — Replacing PRs with pair + ongoing peer review (Section 12)

"we cannot wait two weeks. So that's way too long... we reduce that from like five to seven to one or two." — Sprints out, tiny teams in (Section 11)

"I'm a child developer that's byte code that's executed. AI could generate byte code. There's no reason to generate. The software. Or maybe we end up with programming language customer AI friendly and less human readable" — Speculation on future: source code as intermediate, not artifact (Q&A 2)

"the kind of the work moves or shapes left. So everything that's left will be private engineering [requirements engineering]" — Where the work goes (Section 12)

"the most important thing is you should know your architectural domain" — Closing line (Section 12)

"we have drift management... AI implement from saying that we create tests that are useless and stuff like that. And that's what we call reflection." — Drift management and reflection pipelines (Q&A 3)

"the problem is end-to-end tests are very slow. I'm doing integration tests because I'm using a service site render my framework... everything tested for UI backend or database. That runs around milliseconds per test." — Why Vaadin/SSR enables fast integration testing (Q&A 4)