Compare 8 agentic AI software development services firms on production deployments, security and compliance, guardrails, integration depth, seniority, and engagement models.
How We Used LLMs to Understand and Modernize a Legacy Delphi Application
Many legacy modernization projects start with a simple question: what does this thing actually do?
In this project, we were modernizing a decades-old Delphi application with limited documentation, no meaningful test coverage, engineers long since moved on, and significant unknowns about the environment in which it operated.
Modernizing legacy systems is challenging, particularly when documentation is limited and system knowledge has been lost over time. When LLMs and AI are applied thoughtfully, they can help teams understand legacy systems faster and reduce modernization risk.
This article focuses on how we used LLMs to understand, document, and de-risk an unfamiliar legacy system before modernization began. Once the application was understood and the architecture was defined, the team leveraged AI-assisted development workflows to accelerate the Delphi-to-.NET rewrite itself. Evan Sanning shares that side of the project in his companion article, How We Used LLMs to Rewrite a Legacy Delphi Application in C#.
AI-Generated Unit Tests: A Practical Workflow with Vitest and React
AI-generated unit testing is changing how developers write tests. Learn a practical workflow for generating unit tests with tools like ChatGPT, Claude, and Copilot using React, TypeScript, and Vitest.
Enterprise AI-Assisted Development: How Teams Get Repeatable Results
Learn how enterprise teams use AI coding tools with guardrails, governance, and workflow structure to improve speed without sacrificing code quality or control.
Many organizations are experimenting with AI coding tools, but fewer are measuring or achieving consistent, repeatable results from enterprise AI-assisted development in practice. The difference is not the tools. It is how engineering teams operationalize them day to day.
These observations are drawn from internal engineering roundtables and hands-on client work, where teams are actively working through how AI fits into production development workflows today.
How AI-Accelerated Software Development Is Changing Engineering Teams
Over the past year, we’ve had a lot of conversations with developers and engineering leaders asking the same question: “Is AI going to replace software engineers?” It’s a fair concern. AI coding tools can now generate code, write tests, and handle implementation work that used to take hours. But that’s not what we’re seeing in real enterprise software development environments …