Digital Wire: Digital business, digital transformation, APIs, AI and payments

  Intro I have built my own orchestration framework because most of what I’ve seen was too complex or tried to lock you into creating workflows a certain way. I wanted something very simple and yet maximally flexible. I’m not going into details here on the framework — that’s another blog post — but I will in some cases explain why I could do what I did thanks to the flexibility of the framework, which is a dynamic DAG, can do call-backs, and uses functions and MCP servers. I will also not explain in detail what I’m doing with my current workflow, other than to say I was looking for a way to bypass large language models and instead run it on my own system at home. I succeeded with that — but that’s another blog post. Instead, what I will try to explain in this post is the most important thing after prompt engineering: context engineering, and why it’s so crucial to manage that aspect (especially when you run this at home). Stage setting A couple of weeks ago, Anthropic posted this: ...

  The News Google’s rebirth as the AI behemoth it was always meant to be has finally come to fruition. With the release of Gemini 3, Google has made it clear that it can compete with—and even surpass—OpenAI and Anthropic. And now it seems everyone and their mother is shipping AI-enhanced IDEs which, in almost all cases, are forks of VS Code. Google’s offering is no exception: Antigravity—a rather interesting choice of name. The Need I’ve been working on a Node.js–based orchestration framework for AI agents—yes, yet another one, even though there are already countless options out there. I looked, but none really did what I wanted, so I went ahead and built my own, thanks in part to the helping hands of Claude Code (Anthropic). Bottom line: it works fine. There’s still a lot of manual tweaking required, but I was able to achieve things I couldn’t do with plain ChatGPT or Claude alone. However, it lacks a UI. I didn’t even consider building or using one, because I figured I just neede...

TL;DR AI Playground User Guide

My better half is an artist and maintains a Wix.com site. For the second time in two years, Wix decided to raise the hosting fees. That’s when I suggested to my spouse that I could rebuild the website and host it on Firebase (where I host most of my projects). I assumed this wouldn’t be a big deal (I was wrong) and started researching ways to use a lightweight CMS with Firebase support. Such a system exists — it’s called FireCMS — and it’s excellent. Before I dive deeper, here’s her original site (no longer a paid Wix site):  Miyuki's WIX site Her instructions were clear: replicate it as closely as possible. So I went to work. I created a product development document with use cases, scope, screenshots from the original site, the required features, and of course FireCMS integration. I used ChatGPT to draft the document, then set up a new Firebase instance, and finally launched the Vibe Coding agent (Claude Code). The process wasn’t too different from my other projects, but what sur...

Back in April, I wrote about the verticalization of coding agents by comparing OpenAI’s Codex and Claude Code . Since then, I haven’t really used Codex — Claude Code just keeps getting better and better. But now there’s a new contender in the mix: Google’s own Gemini CLI , which (as the name implies) is powered by Gemini 2.5 Pro . Gemini CLI is very similar in usage to the other two, with one potential advantage (or at least I hope so): it should be an expert in all things Google and Google Cloud. That’s important to me, since I host everything in Google Cloud. That said, the real trigger for trying out Gemini CLI came from a different direction:  Manus . Manus is a Perplexity-style, AI-powered workflow builder. I’m not entirely sure how to categorize it, but you can prompt it with complex tasks and it delivers structured documents. I’ve used it to create presentations and parts of a business plan, and I’ve found it surprisingly effective. Now, my website was built dur...

Yesterday, OpenAI released Codex, a response to Anthropic’s Claude Code. Here’s a summary from ChatGPT what they actually do:  Anthropic’s Claude Code On February 24, 2025, Anthropic quietly rolled out Claude Code, a command‐line interface built atop its Claude 3.7 Sonnet model. Designed to “live in your terminal,” it ingests your codebase context and lets you invoke natural‐language commands—everything from scaffolding new modules to refactoring existing functions—without leaving the command line. By embedding its own LLM at the core of the developer workflow, Anthropic ensures feature parity between the model’s evolving capabilities and the tool’s UX. OpenAI’s Codex CLI Just weeks later, on April 16 and 17, 2025, OpenAI published its open‐source Codex CLI, bringing the latest OpenAI reasoning engines straight to the shell. Out of the box, it supports multimodal inputs—text, screenshots, even hand‐drawn diagrams—and provides a granular approval workflow (suggest, auto‐edit, full‐a...

In the past few months, I've embarked on an experiment that has fundamentally changed how I approach software development. I've been "vibe coding" - essentially directing AI to build software for me without writing a single line of code myself. This journey has been eye-opening, and I'd like to share what I've learned and where I think this is all heading. My Vibe Coding Journey I started vibe coding with Claude and Anthropic's Sonnet 3.5 model, later upgrading to Sonnet 3.7, Claude Code, and other tools. My goal was straightforward but comprehensive: create a CRM system with all the features I needed: Contact management (CRUD operations, relationships, email integration, notes) Calendar management (scheduling meetings, avoiding conflicts) Group management for organizing contacts A campaign system with templates A standalone application using the CRM's APIs for external contacts to book meetings direct The technical evolution of this project was inter...