Blog

One of the most interesting things about the current wave of AI-powered software development is that it has dramatically lowered the barrier to creating a working prototype. That's a good thing. Founders can validate ideas faster, test assumptions earlier, and communicate product concepts in ways that would have required significant engineering investment just a few years ago. But there's an important distinction between a prototype that demonstrates an idea and a system that can support a real business. Recently, we had the opportunity to explore that distinction firsthand while working…

At profiq, Project Weaver started as an internal experiment: could AI help professional engineering teams build serious, scalable backend systems faster without sacrificing architecture, security, maintainability, or engineering discipline? What followed became an evolving public engineering journal exploring planning, specifications, documentation, workflows, automation, and the changing role of engineers in the age of AI. It’s been about 5 months since our last recap of the Weaver journey, so we thought it was time to check in again to document the first idea through the latest automation and workflow experiments.  1.…

Towards auto-annotation pipeline for object detection models By Timotej Ponek To train any computer vision model (CV) model for a specific task, you first need to have (relevant) data. The second thing is to annotate and curate this data. You need high-quality annotation, meaning precise bounding boxes and for individual samples to be varying, so your model is trained to generalize well to unseen data (data not present in training). Gathering the data can take hours, and annotating takes days. Standard workflow At profiq we have experience with end-to-end CV…

We’re entering a new era of software. For years companies had two choices: buy expensive SaaS tools or build large custom systems that took months or years to deliver. Today, AI-assisted development and modern frameworks are changing that equation. Need a custom CRM tailored to your sales process? Need internal tools that automate workflows across teams? Need systems that integrate multiple services without the bloat of dozens of SaaS licenses? All of this is now possible, faster than ever. At profiq, we’ve been exploring how to build software responsibly and…

The Challenge Sometimes the most interesting engineering solutions come from simple frustration. This is a small but meaningful challenge to solve. I had purchased a fairly large list of icons that had no meaningful filenames. Their filenames were just ascending numbers. If I wanted an icon for a specific purpose, say a "flower" icon or a "zoom in" icon I needed to search visually one by one. This is time consuming and it would be much better if the icons had meaningful names, so I could just do a filesearch.…

When we talk about “AI-assisted development,” it’s easy to picture someone prompting a coding agent on their laptop and watching it produce a pull request. That workflow can already be useful. You get speed, you get momentum, and you can keep a human in the loop at every step. But in Project Weaver, that’s not the end goal. That’s the starting point. The goal of our Phase 2 work has been to take the good practices we’ve been writing about, and make them repeatable: Working from documentation and specs Using…

In the last couple of posts, we talked about planning and documentation as foundations of reliable AI-assisted development. Planning gives you direction. Documentation gives both humans and agents a shared understanding of what “done” actually means. But once those are in place, something else becomes critical. Feedback. Not as a refinement step. Not as polish. As the thing that makes an agent an agent. Without feedback, an AI model just produces output. It generates code and stops. With feedback, it can act, observe what happened, and adjust. That ability to…

In our last blog article, we talked about Workflow Planning as the most important step in reminded, reliable AI-assisted software delivery. Planning creates alignment, reduces rework, and gives both humans and agents a shared map of what “done” actually means. But once planning is solid, the next priority is: Documentation. Not as a nice-to-have. Not as a compliance checkbox. As a practical way to make coding agents more accurate, more consistent, and far less likely to drift into outdated assumptions. This post explains why documentation matters so much for AI…

In the early days of AI coding tools, the vibe was simple: point the model at a problem and let it generate code. That worked… sometimes. Mostly on small things. Mostly when you were lucky. But as Viktor Nawrath (who leads Project Weaver at profiq) emphasized: the tooling is moving so fast that “last month’s information is already too old.” The models aren’t always making huge leaps every release, but everything around them is compounding fast: agent harnesses, tool integrations, workflows, and how we actually “drive” agents responsibly. That’s where…

When we first imagined Project Weaver, it was a big, audacious idea: Could we build an AI-powered engineer that truly supports the creation of serious, production-ready backends? Not a toy tool. Not a research prototype. Something that could sit alongside human engineers and help them ship real work with real impact. Over the past several months, we’ve been building in public — documenting our thinking, sharing what we’ve learned, and inviting the community into a conversation about the future of AI-augmented software development. Below is a recap of that journey…