In Retrospect

GitHub data shows AI coding tools increase individual developer output by 25-35%. But code review capacity scales with headcount, not tooling. Here is how AI-assisted code review closes that gap before quality problems reach production.

Learn how technology leaders align modernization approaches with business opportunities. Strategic frameworks for ROI-focused legacy system updates.

We all know that AI's potential is enormous, yet the way to win with AI is to embrace customization and deep integration. It is for this reason that I believe (and I’ve been running tech services companies for 25 years) that the entire software services industry is about to change for the foreseeable future.

In the rapidly evolving landscape of AI, protocols like Google's Agent-to-Agent (A2A) and Anthropic's Model Context Protocol (MCP) are emerging as key enablers for building sophisticated AI systems. Understanding the differences between these protocols is crucial for making informed decisions about which one best suits your project's needs. This post will break down the core distinctions between A2A and MCP to help you choose the right tool for the job.

Agent workflows have quickly emerged as one of the most compelling frontiers in AI application development—but building them for real-world production use cases is still a nuanced and evolving challenge. At Stride, we recently partnered with a healthcare client to redesign a complex patient-facing workflow using LangGraph, LangChain’s graph-based orchestration framework.

Claude Code represents a fascinating approach to AI-assisted development, leveraging powerful language models through command-line tools and file manipulation. However, this architecture creates an interesting trade-off compared to editor-native AI assistants, particularly when it comes to tasks that modern IDEs handle through built-in tooling.

When choosing between AI coding assistants, understanding their underlying search capabilities can significantly impact your development experience. While both Claude Code and GitHub Copilot excel at code generation and assistance, they differ fundamentally in how they find and understand relevant code context—and this difference can lead to dramatically different results.

Artificial Intelligence is reshaping industries at an astonishing pace. From automating repetitive tasks to enabling smarter decision-making, AI promises massive efficiency gains and competitive advantages. But here’s the hard truth: most organizations aren’t ready to adopt AI responsibly or effectively.

Legacy systems are the quiet workhorses of enterprise IT. They’ve processed payroll, managed logistics, and powered customer interactions for decades. But in today’s fast-moving digital economy, that once-reliable code has become a liability.If your organization is still relying on outdated software, you’re not alone—and you’re not stuck. Here’s why modernizing legacy code isn’t just beneficial—it’s mission-critical.

When companies talk about AI transformation, they usually focus on the tools: agents, chatbots, automation platforms, but the real shift is in how we work, who does the work, and how teams are structured. It’s flattening hierarchies, evolving roles, and exposing which organizational models can actually keep up.

And yet, tens of thousands of VB6 and early VB.NET systems are still running core operations inside banks, government agencies, and Fortune 500s, and they’re all mission-critical. They handle payroll, track licenses, and process transactions.

6 Lessons from Agile’s Hard-Won Transformation, for Today’s CTO.

Let’s cut to the chase: Yes, you can absolutely generate code using generative AI models.

Changes coming in 2025 will challenge healthcare in ways that will force organizations to digitally evolve to avoid falling behind the competition.

For decades, pair programming has been a much discussed aspect of Extreme Programming (XP): two developers working side by side with the goal of writing better code than either could alone.

Changes coming in 2025 will challenge the automotive, logistics, and manufacturing industries in ways that’ll force organizations to digitally evolve to avoid falling behind the competition.

According to McKinsey, up to 70% of the software in use at Fortune 500 companies was developed over two decades ago.

CIOs and CTOs can harness AI to boost productivity in legacy software modernization but must maintain delivery stability through human oversight.

I recently attended Re-Work’s AI in Finance Boston event and as an experienced product manager and engineer, what struck me as I listened is how difficult it is to maintain financial software products. In an industry built on calculating risk and managing assets, an unfortunate reality has crept in, slowing innovation to a snail’s pace and increasing risks across the board: technical debt. 

Large Language Models (LLMs) can be very powerful right out of the box, but to truly unlock their potential, integrating with your proprietary data is key. In this article, we’ll explore the benefits of data integration with an LLM and how Stride can assist in maximizing the productivity and creativity of your team.

At Stride, our recent work makes us believe strongly that LLMs will transform the way everyone, everywhere, builds software.

While the resurgence of TDD in the age of Large Language Models offers a promising solution to the challenges posed by AI-generated code, there's another layer to this trust equation: the tests themselves.

In the ever-evolving landscape of software development, there are few constants. Yet, as the tech world becomes increasingly enamored with Large Language Models (LLMs) and their myriad applications, an old stalwart of software engineering is poised for a renaissance: Test Driven Development (TDD).

Learn about grid hosting capacity in the energy sector, and which factors can help us build a sustainable future!

The hype curve is a common pattern observed when a new technology emerges. Initially, there is tremendous excitement and anticipation, often driven by lofty promises and visionary predictions. 

Navigate AI integration with the goal of real business results.

Discover solutions to accelerate renewable deployment and overcome grid challenges.

If there’s one thing you read about artificial intelligence this week, this should be it. 

Culture is the heart of an organization. It’s who you are: the home and the heart of a company.

Being laid off can be a difficult and demoralizing experience. But fear not! There are still plenty of things you can do to stay positive, productive, and come out of this experience stronger than ever before.

In a galaxy far, far away software developers, project managers, and designers are learning agile lessons from the Madalorians.

Design comes with a variety of steps, creating a storyboard sketch being one of them. Learn about the process of creating a storyboard sketch through the lens of a Principal Designer at Stride.

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Id diam vel quam elementum pulvinar etiam non quam.

Ever wonder why RedHat and IBM both recommend the declarative approach, also known as “declarative infrastructure”? Read about the basics of the imperative approach and how it differs from the former!