TechResearch articles

Is The Most Valuable AI Function Asking Better Questions?

Anke Corbin

5 min read2 months agoJune 19, 2026

How the “Grill Me” method became a key part of Project Weaver’s approach to AI-assisted software development. In previous articles, we’ve shared some of the thinking behind Project Weaver—the internal engineering framework we’ve developed at profiq to help our teams and AI work together more effectively. Rather than treating AI as a magic code generator, […]

Annotation Is the Bottleneck — Here’s How We Fixed It

Anke Corbin

10 min read4 months agoApril 9, 2026

Build a scalable auto-annotation pipeline for object detection using SAM3, DINOv2, and MLPs. Reduce manual labeling, improve dataset quality, and speed up computer vision workflows.

Vision language models for image classification without training

Timotej Ponek

10 min read5 months agoMarch 12, 2026

Learn how to label icons locally with vision-language models (VLMs), test prompts, evaluate results, and create distinct searchable icon names without custom training.

Project Weaver: Automations That Don’t Turn Into Chaos

Anke Corbin

10 min read5 months agoFebruary 24, 2026

There are two ways we’ve explored automating Weaver so far. The first is the obvious one: use GitHub Actions and the second Temporal for Time Travel.

Feedback Loops: What Makes AI Coding Agents Actually Useful

Anke Corbin

8 min read6 months agoFebruary 11, 2026

In the last couple of posts, we talked about planning and documentation as foundations of reliable AI-assisted development.

“Documentation – the Next Priority in AI-Assisted Development”

Anke Corbin

8 min read6 months agoJanuary 27, 2026

A priority is 'Documentation', as a practical way to make coding agents more accurate, more consistent, and far less likely to drift into outdated assumptions.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 coding workflows, what tends to go wrong with “just search the web” approaches, and why Weaver treats documentation as a first-class citizen inside the repository.

From “Just Let It Code” to “Build a Plan”: The Weaver Workflow

Anke Corbin

10 min read7 months agoJanuary 15, 2026

Why a key AI development capability is workflow planning: the ability for an agent to take a problem, ask the right questions, propose implementation steps, and only then move into execution.

Project Weaver: The Journey So Far and What’s Next

Anke Corbin

6 min read7 months agoDecember 23, 2025

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.

Spec-Driven Development: How AI Is Changing the Way We Think About Software Design

Anke Corbin

8 min read8 months agoDecember 16, 2025

Project Weaver is answering the question: What does it take for an AI system to operate as a genuine engineering partner- not a code autocomplete, but a collaborator that can meaningfully participate in the creation of real backend applications?

Building in Public: Why We're Sharing the Evolution of Project Weaver

Anke Corbin

5 min read8 months agoNovember 26, 2025

At profiq, we've always believed that the best engineering work grows from curiosity, collaboration, and honest reflection. That is why we've decided to build in public.