Cloudberry Engineering

Also: The title has been editorialized for marketing purposes.

I just published my homebrew coding agent orchestrator I’ve been using in the last - checks calendar - three months.

One of the engineers behind Manus shared a bunch of interesting tips about building agents.

This is an interesting framing about agents writing meaningless tests: Unless you are very clear and careful, AI coding assistants at the moment will look at your implementation and write tests that confirm your code does what it already does.

As the product grows and engineers are adopting AI tooling, the security team has more and more code to protect from vulnerabilities.

Since there are so many to choose from, I built my own sandbox for local coding agents.

I am still on a quest to stay out of the loop with coding agents, to reach warp speed yoloness.

I am forcing myself to stay out of the loop, and I am looking at ways to sandbox coding agents running without supervision.

We are moving towards a place where ticketing systems will become an important component to protect, akin to CI/CD.

How does Claude Code sandbox work when used with --dangerously-skip-permissions?

Fully aware that this might be obsolete in half a year, this is my current mental model to reason about AI Agents risks.

Security is hard so let’s skip it.

Finding vulnerabilities in modern web apps using Claude Code and OpenAI Codex.

How did they breach nx to publish a malicious package?

Context I wrote this some time ago as an internal memo for marketing and product to help craft value propositions to sell security tools to security teams.

I’ve spent a good year working on a security strategy to manage multi-cloud environments, in this article I want to share what I wish we did in advance to be better prepared.

Using Apps Script for scripting GSuite / Google Workplace will generate Google Cloud Platform (GCP) projects in the background.

Service Accounts in Google Cloud Platform (GCP) are the main vector to hack an account: it’s easy to use them wrong and end up with a compromised key and a lot of headaches.

Securing containers is a complex task.

Identity and Access Management (IAM) is an important piece of the cloud puzzle and it’s usually a source of headaches from a security point of view.