
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.
Read full article
Why multi-repo setups are vital for Claude Code, and their trade-offs.
Read full article
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.
Read full article
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.
Read full article
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.
Read full article
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.
Read full article
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.
Read full article
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.
Read full article
AI code agents work best with typed languages. Better inference, safer refactors, and clearer APIs make typing feel like leverage rather than bureaucracy.
Read full article
Porting your product into ChatGPT won't work, building a genuinely useful conversational app is a product design challenge, not a technical one.
Read full article
Team size matters as much as team composition. This post argues why small, focused development teams consistently outperform large, bloated teams in practice.
Read full article
We have been building AI-based projects for 18 months now, so we wanted to share a few of the learnings and cool things we have built in this blog post.
Read full article