🤖 AI-Assisted Product Development, in Practice

February 06, 2026

AI-Assisted Product Development, in Practice

The Starting Point

This started with a familiar frustration—returning from a trip and facing yet another spreadsheet to submit expenses to an accountant. During that conversation, I casually remarked that I could probably just build an app for it. To a certain extent, that turned out to be true.

More importantly, it became an opportunity. What started as a simple utility evolved into a focused applied R&D effort exploring how AI can be used responsibly across the product development lifecycle—from requirements discovery and architectural decision-making through implementation, testing, and deployment.

The resulting Expense Reports App is production-grade and functional. But the real value of this work is what it demonstrates about AI-assisted product development practices.

The Key Innovation: Using AI Upstream

The breakthrough wasn't using AI to write code—it was using AI upstream of code.

I leveraged AI throughout the product lifecycle to:

• Draft and refine requirements in structured Markdown
• Capture architectural trade-offs through Architectural Decision Records (ADRs)
• Translate intent directly into implementation with minimal translation loss
• Evolve specifications alongside code in the same repository

This approach reduces the distance between intent and execution. Requirements, ADRs, and implementation live together and evolve together. The result: faster iteration with higher confidence—exactly what modern product organizations need.

Grounding in Real Constraints

Early in the process, I grounded requirements in IRS expense reporting and substantiation guidelines. This wasn't just about compliance—it was about disciplined prioritization.

Understanding regulatory requirements clarified: - What elements are universally required - The natural initial market (individuals and small businesses) - Clear MVP boundaries that prevent scope creep

This regulatory grounding became a forcing function for product discipline. Rather than building everything that could be useful, I built only what the market demonstrably requires.

AI as a Learning Accelerator

Throughout this work, AI served as a learning accelerator, not a decision substitute.

When exploring unfamiliar territory—regulatory requirements, edge platform capabilities, testing strategies—AI helped me: - Rapidly survey options and trade-offs - Draft initial approaches for validation - Identify gaps in my understanding - Iterate toward better solutions

The key: AI accelerated my learning and execution, but product judgment remained central. Every architectural decision, every prioritization choice, every trade-off was still mine to make.

Why This Matters

While the functional domain is expense reporting, the broader value is in the methodology:

• AI applied across the full product lifecycle, not just implementation
• R&D conducted through real, production-grade systems with actual constraints
• MVP discipline informed by regulatory reality rather than feature wish lists
• Tight feedback loops between product intent and technical execution

This isn't theoretical—it's a working system that demonstrates these practices in action.

Key Takeaways

This applied R&D effort demonstrates several transferable patterns:

1. Upstream AI Use: Apply AI to requirements and architecture, not just code
2. Co-located Artifacts: Keep requirements, decisions, and implementation together
3. Regulatory Grounding: Use external constraints as forcing functions for discipline
4. AI as Accelerator: Leverage AI for learning and velocity, not judgment replacement
5. Hypothesis-Driven: Build real systems to validate approaches, not just prototypes

The result is a production-grade system that serves as an ongoing testbed for AI-assisted development practices. More importantly, these patterns are transferable to any product development context.

Related: For details on what was built, see the Expense Reports App project page.

Try it yourself: https://expensereports.app

Categories: blog

Tags: technology, product-management, systems