profile

Filip Hric

AI, BDD, and Why We're Bad at Predicting the Future

Published 11 months ago • 1 min read

Filip Hric

22th July 2025

AI, BDD, and Why We're Bad at Predicting the Future

Hello Reader,
Lately, it seems the conversation around AI has shifted. We're moving past the initial "what can this chat window do?" phase and into the more practical, and sometimes awkward, integration into our development lifecycle.

To me, one of the most interesting moments recently is that we're seeing major players like Amazon use BDD for AI-driven requirement planning. Plus the whole ecosystem of AI builder tools is emerging, each with its own take on how to plan and execute tasks.

Blogposts, discussions, events

Amazon's New Code Editor Uses BDD-like syntax for Planning

Amazon's new code editor uses Behavior-Driven Development (BDD) for planning requirements. This is a significant move, embedding a classic testing and collaboration practice directly into the AI development workflow.

​Read more →​

A Comparison of Planning in AI Builder Tools

I recorded a short video comparing how planning is implemented in different AI builder tools. If you're exploring this space, this video breaks down the different approaches you'll encounter.

​Watch video →​

Future of AI (and Phones)

We have a tendency to imagine the future as just a different version of the present. People once imagined the future of phones would look like the image above. It's a good reminder to be humble when predicting how AI will actually shape our future.

​Join the disucssion →​

99 Cypress.io tips is on summer sale!

Get full course for 50% cheaper!

99 bite-sized video lessons. Each under 5 minutes. Each immediately applicable. No fluff, just immediately applicable tips for automation engineers who are serious about their craft 🔧

✅ Eliminate flaky tests forever

✅ Master undocumented Cypress features

✅ Implement patterns used by pros

✅ Debug like a pro, not by trial and error

Filip Hric

Teaching testers about development, and developers about testing

filip@filiphric.sk, Senec, Slovakia 90301
​Unsubscribe · Preferences​

Filip Hric

I teach testers about development and developers about testing

Sign up for weekly tips on testing, development, and everything related. Unsubscribe anytime you feel like you had enough 😊

Read more from Filip Hric

Hey Reader,, A few years ago Cursor was a nicer place to type code. This week it announced Origin, its own Git competitor built for agent workloads, and got acquired by SpaceX for sixty billion dollars. Somewhere in between, it stopped being an editor and started becoming the whole stack — the place you write, review, merge, and increasingly test your software. I come from QA, so my first instinct isn’t excitement, it’s a question: when one tool owns every step of the loop, who’s the...

6 days ago • 3 min read

“Too dangerous to release” has become its own genre of AI announcement. Project Glasswing is the latest entry: not quite a product launch, but a claim about a threshold, dressed up with enough corporate coalition to signal this one is serious. Anthropic says their new security-focused model, Claude Mythos Preview, can find software vulnerabilities better than all but the most skilled human experts. George Hotz challenged the “too dangerous to release” narrative by pointing at the obvious:...

2 months ago • 2 min read

Anthropic had a rough week. And the part that stings isn’t just that something went wrong - it’s how they handled it. A map file, a DMCA frenzy, and a Python loophole On March 31st, Anthropic accidentally shipped Claude Code’s TypeScript source code via a map file left in their npm package. The leak was spotted almost immediately, and GitHub repositories mirroring the code started receiving DMCA takedowns shortly after. What followed was a fairly aggressive takedown campaign by Anthropic. One...

3 months ago • 2 min read