We spent the last several months building a hands-on series covering AWS CI/CD pipelines and deployment automation, published on AWS Builder Center. It contains seven posts, each with working AWS CloudFormation templates, CLI commands you...
Most AI product development stories involve a proof of concept that takes months to graduate into something real. CETA Global didn't have that runway. They had a Google Accelerator demo in December 2025, a vision for an AI product that...
Adapted from Issue #6 of LatAm AI Engineering Updates, our newsletter on funding, acquisitions, and AI talent news from Latin America, published by AgilityFeat CEO Arin Sime. If you want this kind of analysis in your inbox before it...
In just minutes, AI can produce software that looks 90% done. The question for engineering teams is what lives inside the other 10%. This is where the database, the tests, the security model, and everything else a business depends on tend...
Justin Williams is an AgilityFeat Senior WebRTC Engineer. Want to work with great nearshore engineers like Justin? Get in touch. I work primarily in the terminal, running agentic coding tools as my daily driver for everything from...
Early in one of AgilityFeat's staff augmentation projects, a sharp SRE flagged in standup that he wasn't sure his sprint was worth reviewing. The work had been entirely infrastructure. Nothing visible, nothing a user would notice. He'd...
AI-generated code stabilization is becoming one of the most critical steps in modern software development as AI-built prototypes grow more common. After AgilityFeat conducted a technical audit of the FarmGAP AI-built POC, the findings...
Open source LLMs have grown up. Models like Llama 4, Mistral, and DeepSeek now go toe-to-toe with commercial options like GPT, Gemini, and Claude on real-world tasks like code generation, summarization, document analysis, and customer...
I've been thinking about software development methodology for a long time. When I founded AgilityFeat in 2010, I was traveling the US coaching and training teams in Agile practices, principally Scrum and Kanban. Many people were still...
Not every software challenge calls for the same solution. Some projects need a long-term embedded team. Some need a full-service development team for larger-scope, end-to-end delivery at enterprise scale. And some simply need a small,...
At AgilityFeat, we look for engineers who solve real production problems, whether they’re part of a staff augmentation team or our internal nearshore team. This post shows how one engineer confronted the confusing behavior of npm...
AgilityFeat worked with an AI-native enterprise software startup, Compounds.dev, to implement and validate a Minimum Viable Product (MVP) for their software delivery platform. The platform combines spec-driven development, codebase...
The FarmGAP application was a promising AI-built proof of concept that had not yet been put into use. Before the platform could move toward launch, SG Farm Services needed a technical audit to assess the codebase, surface security and...
AI can generate code quickly, but speed alone does not produce reliable software. Generating thousands of lines of code in seconds is counterproductive if it compromises structural integrity, security, and overall quality. Fast technical...
Engineering leaders are being asked to navigate something genuinely new. Not just a technology upgrade, and not just another platform shift. Instead, we face a fundamental change in how software gets built, who builds it, and what it...
For more than 15 years, AgilityFeat has helped companies build software across Latin America. As AI reshapes how products are built, we created something new: Builder Pods. These are small, senior, AI-native nearshore squads designed for...
AgilityFeat CTO Alberto González recently appeared on the Software Defined Talk podcast to discuss the realities of building secure, scalable AI implementations for enterprise use. While the conversation also covers WebRTC foundations,...
Most companies struggle when scaling engineering teams because hiring is often treated as a sourcing activity rather than an alignment process. Speed becomes the primary objective, while ownership expectations, tenure patterns, and...
Building LLM-driven applications is not like building traditional software. The rules are different, the failure modes are different, and the gap between a working AI prototype and a production-ready AI system is wider than most teams...
At annual conferences across any vertical, AI has become the default lens for discussing modernization. Fintech Americas Miami 2026 was no exception. At the event, every conversation about banking modernization, core systems, customer...
When the conversation turns to AI, the lens almost always points westward. To San Francisco, Palo Alto, or to the handful of hyperscalers dominating the headlines. It's an understandable bias. But it's also an increasingly expensive one....
Spec-driven AI tools automate complex workflows by first generating detailed specifications. These are clear, step-by-step plans that humans review before executing them precisely, minimizing errors across industries like software...
In fintech and other regulated industries, technology decisions carry higher stakes than in most software domains. Systems must process financial transactions accurately, remain available under heavy load, and comply with strict...
When AI agents interact with live systems and sensitive data, safety can’t rely on a single model or moderation filter. True protection comes from layered guardrails: a structured stack spanning model-level safety, structured tool...