I am interested in people who have tried generative AI coding projects.  In your experience, are there project attributes that make generative AI coding capabilities a "good fit"?  Are there project attributes that are likely indicators that generative AI will not result in something useful?  I would think complexity of requirements is a big factor.  If the complexity of the project or its requirements is low - I assume genAI coding can get you within the ballpark.  For instance, logic stores: if your project has critical business logic spread out all over the place and not centralized I think that generative AI would not be able to make sufficient sense of that.

Lovable for mockups, but no for real enterprise solutions since it doesn't work based on my experience.

Your question hits the core of where GenAI coding shines and where it struggles. In my experience, GenAI works well on projects with clear patterns, well-defined logic, and modular requirements. It accelerates boilerplate, refactoring, and integration work really well.

Where it becomes less useful is exactly what you mentioned: high-complexity requirements, fragmented business logic, or systems with a lot of implicit knowledge. In those cases, GenAI produces output, but not necessarily value.

The sweet spot seems to be projects where architecture and rules are already structured, and GenAI becomes a force multiplier rather than a guesser.

This is not about project specifics or complexity of requirements.

Essentially, a paradigm shift is required from producing deliverables based on human-friendly descriptions (legacy artifacts - diagrams, BRDs, etc.) to machine-optimized ones. Prompt the almighty, with a complex and intricately defined structure of inferences rules it all. And not only everything is prompt-to-prompt, that flow itself is handled by MCP - going from system to system directly, with humans in supervisory role, and agents full-on execution.

GenAI is inherently hampered by the fact that it is, for all needs and purposes, a glorified autocomplete. Yet, when you ask it the right questions - you get the right answers. And when you set up and manage the context correctly, hallucinations (another inherent feature of models designed with assistance in mind) become a minor impact to be buffered.

Last but not least - consider engineering commoditized. Codebase, infrastructure (IaC, obviously) - everything is disposable. The only thing that persists, is UVP of a product, and/or enabling capability. These evolve, but remain. Everything else is re-generated continuously - so you basically live in a massive repository for everything, from prompts to outcomes.

We have tried Vibe Coding 'A Lot' and from our experience, I can guide you that doing Spec-based coding using a tool/IDE like KIRO is a relief. You can do a lot of what you mentioned in your post efficiently and accurately if you write the correct 'Spec'. Try it out once, happy to chat more about it.

We are implementing a multi-layered strategy for leveraging Generative AI and automation technologies to drive business outcomes. Our current stack includes:

- Code-Gen AI for Developer Velocity: We are deploying AI coding assistants, including Cursor and Copilot, across our primary development stacks (Python, .NET, Node.js, React). The objective is to accelerate feature delivery by reducing coding time and automating the generation of documentation and test cases. This initiative is complemented by enhanced code review processes to ensure quality and maintainability.

- No-Code Platforms for Business Agility: Our Marketing and Community teams are empowered with the Lovable platform to independently develop and deploy landing pages and user registration flows, increasing operational agility.

- Enterprise-Wide Productivity Suite: As a Google Workspace organization, we have standardized on Gemini Pro for company-wide use, democratizing AI-powered content creation, analysis, and communication.

- Proprietary Hyperautomation Platform: At the core of our strategy is Skyone Studio, one of our flagship products (an integrated platform that includes iPaaS/Lakehouse/Agent Builder&Orchestration). This low-code environment enables complex data integration from SAP and 17 other enterprise systems and facilitates the creation and orchestration of autonomous and conversational AI agents, which are being deployed across all business functions to drive efficiency and innovation.