The AI Development Workflow That Changed How We Build Software

I recall a time at Radware in 2017 when we spent six months developing a management console for their AppWall product. It involved a whole team, thousands of commits, and ultimately led to a successful launch, despite two other teams having previously failed.

Today, at PolarGrid, we shipped our first production management console in just over a week. No design team needed. AI created a superior design. A single competent engineer, proficient with LLMs, handled the entire delivery. We iterated on feedback and shipped.

But what about quality?

“Our CI has teeth,” proclaimed a Slack message in our #engineering channel. 573 unit tests across the management console, SDK, and edge agent. All written in a few hours by an engineer effectively using a model with access to our codebase.

Besides unit tests, how do we know our real-time edge infrastructure works for a customer? A fully functional voice agent would have been unthinkable even a year ago, taking months of development by the entire engineering team. Now, we built a fully functional voice agent test bench in a few days, essentially dogfooding our own infrastructure.

This is how we ship at PolarGrid.

Our Workflow

Here’s the pipeline that replaced months of front-end work:

Notes → PRDs → LLM Artifact Prototypes → Production Web Application → User Feedback → Notes

Step 1: Notes to PRDs

Raw notes consist of customer conversations, sketches, transcriptions, or voice memos. While I use AI notetakers, I still pay close attention to meetings and take notes by hand because their summaries often miss nuance and key points.

During this step, we convert human thinking into structured product requirements. I use AI to transform these fragments into PRDs by providing the model with context about our architecture, our constraints, and our customers. The output is a structured document with clear acceptance criteria.

Step 2: PRDs to LLM Artifact Prototypes

A well-written PRD becomes a working prototype in minutes. These are functional web components you can interact with, test, and break, enabling stakeholders to see UX designs immediately and give feedback. Want them to be in the style of your website? Take a screenshot of a sample and provide images as context.

Step 3: Artifacts to Production React

This is where inexperienced developers get stuck for weeks, sometimes forced to rebuild entire applications from scratch. The artifact is a proof-of-concept, while production code requires state management, error handling, edge cases, API integration, and proper testing.

The transition requires someone who understands both what the artifact demonstrates and has the skill set to understand production requirements. At this point, we iterate and refactor something that works on a happy path into something that scales.

Step 4: User Feedback to Notes

We are building everything for the end user and ease of use. Our team members and design partners provide feedback on our product, and the team then uses LLM to convert those notes into the next PRD. Thus, we keep the feedback cycle going and improve the product with each iteration.

The Evidence: Testing at Scale

There’s a persistent myth that AI-generated code is untestable or generates technical debt. Concerns that AI will produce worse software are often exaggerated and fail to consider that LLMs give us raw horsepower to build far better test coverage and iterate more rapidly than in the pre-LLM world.

At PolarGrid, AI-assisted development enabled us to produce 573 unit tests in hours rather than weeks. These tests aren’t trivial coverage padding. They include integration tests that spin up edge node mock servers, end-to-end tests that run the full STT→LLM→TTS pipeline against our staging environment, and property-based tests that verify routing logic across thousands of generated input combinations.

The result is a codebase that ships faster and breaks less. Not because AI writes perfect code — it doesn’t — but because AI makes comprehensive testing economically viable in a way it simply wasn’t before.

What It Means for Teams

The workflow above doesn’t eliminate engineers. It changes what engineers do. The bottleneck shifts from writing code to making good architectural decisions, reviewing AI output critically, and maintaining the judgment to know when the prototype and the production requirement have diverged.

The engineers who thrive in this environment are the ones who can hold the full system in their head, spot the edge cases the AI missed, and know which shortcuts are acceptable and which will cause pain six months later. That skill doesn’t go away. It becomes more valuable, not less.