In the recent article, Building Isolated AI Code Environments with Cerebras and Docker Compose, our friends at Cerebras showcased how one can build a coding agent to use worlds fastest Cerebras’ AI inference API, Docker Compose, ADK-Python, and MCP servers. In this post, we’ll dive deeper into the underlying technologies and show how the pieces come together to build an AI agent environment that’s portable, secure, and fully containerized. You’ll learn how to create multi-agent systems, run some agents with local models in Docker Model Runner, and integrate custom tools as MCP servers into your AI agent’s workflow. We’ll also…
Author: drweb
Prompt AI released recently and I decided to try a few things with the tool that might help me in database work. I’ve had to do this task, but I had a customer recently ask me about this as well. They were wondering where they were short FKs.This post showed what I tried with Prompt AI.This is part of a series of experiments with AI systems. This is part of a series of posts on SQL Prompt. You can see all my posts on SQL Prompt under that tag. Help Me Query the DatabaseIn a recent post, I looked at the…
A sparse matrix is a data structure where most of the elements are zero. Think of it this way: if I have a matrix representing user-item interactions on a platform like Netflix, most users haven’t watched most movies, creating a matrix filled with zeros. Instead of wasting memory storing all those zeros, sparse matrices store only the non-zero values along with their positions.Here’s my thumb rule when working on sparse matrices: if more than 2/3 of your matrix elements are zeros, you’re dealing with a sparse matrix that can benefit from specialized storage. In practice, I’ve seen sparse matrices with…
OpenAI just released GPT-5-Codex, and it’s designed to handle the messy reality of enterprise software development. This isn’t just another coding assistant; it’s built for the complex, long-running tasks that define real software engineering work.What Makes GPT-5-Codex DifferentThe most significant change is how GPT-5-Codex adjusts its thinking time according to task complexity. For quick questions or simple fixes, it responds fast. However, for large refactorings or complex debugging sessions, it can work independently for hours, up to seven hours in testing, iterating on solutions until they are successful.This dynamic approach shows up in the numbers. For simple tasks, GPT-5-Codex uses…
Press enter or click to view image in full sizeRecently, I’ve covered different architecture options to control a dialog component. All these options had the component in place in the DOM and used some external trigger to show or hide the component’s template.But what about creating a component and rendering it on demand? Of course, we have lazy-loading and the @defer block, but what if we want to decide which component to display at runtime, or even better, can replace that component on-demand with Typescript code?Enter ViewContainerRefA view container is a place in Angular’s component tree where HTML content can…
If you’ve ever run a Linux system in production or even just kept a personal server, you’ll know that running out of disk space is one of the most frustrating issues. Suddenly, your applications stop working, databases won’t write new data, and log files keep filling up like a runaway train. The good news is that Linux makes it surprisingly easy to monitor disk usage and catch problems before they happen. All you need is a small shell script, a bit of logic, and maybe an email alert (or a message to your Slack channel, if you’re fancy). In this…
In the DevOps world, with its faster release cycles and continuous delivery, quality assurance (QA) cannot be sidelined until the end of the process. Companies that actively use automation achieve up to 60% faster release cycles compared to those relying solely on manual testing. However, automation alone is insufficient. Without the right QA mindset, moving faster can easily backfire if quality is not built into every stage. QA teams must evolve to become quality enablers throughout the software delivery cycle. Rather than joining at the tail end of the lifecycle, they must work alongside product owners to understand functional requirements,…
Oracle today announced the availability of Java 25, which provides capabilities that make it simpler to build both artificial intelligence (AI) applications.At the same time, Oracle also pledged to provide long-term support (LTS) for Java 25 for the next eight years.Chad Arimura, vice president of developer relations for Oracle, said this edition of Java makes it clear that Java will continue to be a de facto enterprise standard for building both existing and next-generation applications.For example, Java 25 provides early access to a vector application programming interface (API) to optimize computations as they are compiled at runtime. That capability will…
Job Type: Contractor; 6-12 monthsJob Location: Remote; ability to work on Eastern Standard TimeAbout us:ACTO is an Intelligent Field Excellence (IFE) platform built for life sciences that improves field and HCP interactions with unified agentic AI. ACTO helps Sales, Marketing, and Medical teams improve customer engagement and brand performance by turning field professionals into “Masters of the Message” that engage HCPs and their support teams with authority and impact. ACTO partners with biopharma companies to ensure field professionals are always competent, confident, and credible, delivering the right message to HCPs, while providing senior leaders and frontline managers with the insight…
Recently, I was in a technical interview where the topic of running PowerShell at scale came up. Although I’ve worked with PowerShell for quite some time, I realized I’d grown comfortable with “my” environment. Script runtimes and long-running processes were not a significant concern. I’d encountered PowerShell jobs and parallel execution before, but never felt the need to dive deep. That changed after the interview. It sparked some curiosity and led me to explore how PowerShell handles parallelism. Turns out, it’s a great topic for a blog.There are several ways to execute tasks concurrently in PowerShell, and the approach depends on…