Aymen Furter | Senior Software Engineer

Coding agents are constantly evolving.

In a recent LinkedIn post, I mentioned that GPT-6 Astra is one of those models that represents such a leap that it allows all of us to jointly explore its capabilities.

I am often asked how I manage multiple sessions in parallel.

Sometimes an app does not fit your workflow exactly.

Almost every customer conversation I have lately lands on the same point: the productivity gains from coding agents are real.

The way we build software keeps changing, and not in a way that ever settles.

LLMs are getting better at writing and executing code with every release.

In my previous article I introduced Polyclaw — an autonomous AI copilot inspired by OpenClaw and rebuilt to be Azure-native.

What if your AI assistant didn’t forget everything the moment you closed the tab?

⚠️ Disclaimer: The features discussed in this article, specifically the o3-deep-research model and certain Foundry capabilities, are currently in Preview.

Recently, a new programming pattern for AI coding agents has emerged.

Recently, Anthropic released their new flagship model, Opus 4.5.

We’ve all been there.

What problem are we solving Many agent failures are not caused by weak prompts or undertrained models, but by poor environments.

As AI apps become more complex, a pattern emerges: we move from a single monolithic agent to a collection of smaller, specialized agents.

We’ve all been there.

In the initial wave of AI adoption, the focus was on making unstructured data discoverable.

Many years ago, I was part of a project migrating legacy APIs from an old XML-based protocol to modern, REST-based OpenAPI specs.

My views here are my own and do not reflect any employer or organization I may be affiliated with.

In my previous post we built a custom tool to make ETL output order consistent.

GitHub.com recently announced the public preview of its Copilot coding agent, which can take ownership of entire issues, plan the steps, and work through them autonomously.

GitHub Copilot Chat has taken a big leap forward by letting you connect your own custom AI model - for instance powered by Azure AI Foundry - to the chat interface.

Organizations manage a broad spectrum of official documents, from internal memos and client proposals to compliance submissions and operational guidelines.

I often see customers eager to leverage generative AI to better understand and reason over their existing data.

Before diving into the article, there’s also a podcast version available!

In the wake of the generative AI revolution, we’ve witnessed a surge in AI-powered applications promising to transform how we interact with computers.

Over the past few weeks, it has been my privilege to collaborate with my distinguished colleagues, Damiano Curia, Carlos Garcia Lalicata, Francesco Rinaldi, Rolf Egli and Yasmin Sarbaoui, on investigating ways to incorporate Generative AI capabilities into

In the digital era, extensive libraries of images have become ubiquitous across multiple industries, such as e-commerce, education, marketing, and online media.

With the ongoing updates in Large Language Models (LLMs) and their orchestration libraries, it is important to recognize and prepare for potential changes that may arise when upgrading to newer releases.

In past articles, I talked about making a chatbot called “Upskiller” that uses the vast information from YouTube videos about Azure.

I often study a lot of material to understand the details of Azure services.

Before we start, remember these tips are meant for fun projects that can handle some downtime.

Azure API Management can give you security-in-depth by already identifying invalid requests containing no or invalid JWT tokens on your requests before they even reach your backend.

Over the past few months, we all witnessed a surge in popularity of Large Language Models.

Disclaimer: I’m just experimenting with this as a personal hobby / for fun.

Recently, there has been a lot of hype around large language models and their application in chatbots.

WSL2 is the optimal solution for bringing the Linux command line experience to Windows.

I recently built a Unity game with the help of ChatGPT, an amazing tool for developers.

ChatGPT is a GPT-based chatbot developed by OpenAI that allows users to engage in natural language conversations with a virtual assistant.

Terraform helps users get the most out of their cloud when provisioning infrastructure in an automated and repeatable way.

Profiling applications can be a difficult and time-consuming process, but it is essential for understanding how an application is performing and where potential bottlenecks may exist.

I recently ran into an issue when setting app settings via the az functionapp config appsettings command.

As developers, we are always looking for ways to be more productive.

When working with GitHub Actions it can be useful to use Selenium.

It is probably no surprise for you if I tell you that I am writing this on an iPad.

One would usually use an interactive login to access the Google Sheets on behalf of a user.

I recently moved to a Macbook M1 as my daily driver (running Linux on top).

This year I helped to build drugplug as part of Hack Zurich.

Recently I’ve started to publish sticker designs on redbubble.

In this article, we are going to take a look at the impact of the recent log4j Zero-Day on Apache Karaf based apps.