
Decision models could make AI practical in applications where cost and complexity have kept it out. Here’s what they are and why we’re keeping an eye on them.
Leer el artículo: Decision models: practical AI where it used to be too costly
Why multi-repo setups are vital for Claude Code, and their trade-offs.
Leer el artículo: Why multi-repo workspaces are a must for Claude Code
We put the new Fable AI model to the test on a real production project: how we compressed two weeks of development into just five hours, and why true success still depends on solid architecture and human review.
Leer el artículo: Our first production test of Fable
We shipped llms.txt on marsbased.com and checked the data. Honest verdict: low cost, useful for docs, not a SEO play, and almost no bots read it yet.
Leer el artículo: Our honest take on llms.txt
A few months ago we quietly added a new section to the MarsBased Handbook laying out exactly how we use Claude Code day to day, from research to planning to implementation. We never wrote about it here, so we're fixing that now.
Leer el artículo: How we actually use AI to build software: what's in the Handbook's AI-Augmented Development page
At MarsBased, AI has become part of our daily workflow: from how developers write code to how non-technical teams create, translate, and manage content. Here’s a look at how we’re Claude Code and similar tools to improve efficiency across the entire company.
Leer el artículo: How MarsBased integrates AI across development and operations
What does a great software engineer look like today? A look inside our updated review templates and the new AI criteria we use to evaluate our team.
Leer el artículo: How we evaluate software engineers in the age of AI
AI agents often over-abstract coincidental duplication, creating fragile architectures that increase cognitive load and technical debt. Prioritizing clear domain boundaries over rigid DRY principles is essential for keeping codebases maintainable for both humans and AI.
Leer el artículo: How "Don’t repeat yourself" can mess up with your AI-generated code
How we integrate agents like Claude and Copilot into our workflow using a rigorous Research, Plan, and Implement framework to ensure speed without sacrificing architectural excellence.
Leer el artículo: Standardising innovation: Our internal guide to AI-augmented development
True quality is defined by a mindset of accountability and the Boy-Scout Rule of leaving code cleaner than you found it. Senior success requires radical ownership and rigorous self-review to deliver excellence in every single commit.
Leer el artículo: The boy-scout engineer: Frontending with detail series (part 3)
Software quality is declining even as tools improve. Buggy launches and unpolished AI apps signal a crisis in digital craft — quality is now a competitive edge.
Leer el artículo: The quality crisis in software
We have been building all kinds of technical platforms and projects for over ten years at MarsBased, and we apply this accumulated knowledge to the AI projects we're building now at GPTApps.
Leer el artículo: How we build GPTApps