– laravel.com – Edit
Ryan Chandler makes a strong case for keeping PR descriptions human-written, even when agents handle most of the implementation. The piece focuses on ownership, review context, and why a concise explanation from the person driving the change is more useful than a long AI-generated summary.
Read more [laravel.com]
by Freek Van der Herten – 5 minute read – Edit
Over the past few weeks I've posted a couple of times about There There, the helpdesk we're building at Spatie. After two decades of running our own customer support, we decided to stop compromising on tools and build the one we actually want to use. A lot of the fun is on the AI side. We're not…
Join 9,500+ smart developers
Get my monthly newsletter with what I learn from running Spatie, building Oh Dear, and maintaining 300+ open source packages. Practical takes on Laravel, PHP, and AI that you can actually use.
No spam. Unsubscribe anytime. You can also follow me on X.
"Always fresh, useful tips and articles. Carefully selected community content. My favorite newsletter, which I look forward to every time."
by Freek Van der Herten – 5 minute read – Edit
A couple of posts back I walked through the agent and tools we built on top of the Laravel AI SDK for There There, the helpdesk we're putting together at Spatie. I ended that post on a small cliffhanger. We hand the agent off to a streaming service that turns the SDK's response stream into events…
A practical post on hardening Laravel projects against destructive AI agent behavior. It walks through the PocketOS incident and shows concrete safeguards like deny rules, credential isolation, and production guardrails.
Read more [hafiz.dev]
by Freek Van der Herten – 4 minute read – Edit
Recently I wrote about how we use Jev in There There to detect spam, bounces, and automatic replies. Jev reads an incoming email and answers questions we define up front. We keep the probabilities and decide in our own code what counts as a match. The cheap checks on mail headers still run first.
That post ended with a promise that we'd find more uses for Jev. Here are two we have since added to There There: smart conditions for workflows, and automatic assignment to a team or person.
– wendelladriel.com - submitted by Wendell Adriel – Edit
What Agent Experience engineering means in practice: discoverable code paths, scoped agent instructions, useful feedback, and human ownership of risky decisions.
Read more [wendelladriel.com]
by freekmurze – 8 minute read – Edit
Yesterday Taylor announced that Jev support landed in the 1.x branch of the Laravel AI SDK. We started using it that same day for spam detection in There There. Let's take a look at what Jev is and how you can use it.
– tighten.com - submitted by Kayla Helmick – Edit
Transformers.js lets you run AI models directly in the browser without a backend, API keys, or an internet connection after the model is cached. The article explores how it works, which models are available, and the trade-offs of client-side AI compared to traditional AI providers.
Read more [tighten.com]
– koomai.net - submitted by Sid – Edit
Split a task into reasoning and execution to get deterministic behaviour out of a non-deterministic model.
Read more [koomai.net]
– tighten.com - submitted by Kayla Helmick – Edit
In this article, we’ll build an AI-powered Slack bot with the Laravel AI SDK. Unlike tools such as Claude Tag, it can switch AI providers, answer questions, execute tasks, and retrieve information from a knowledge base you control.
Read more [tighten.com]
– twilson.net – Edit
Tom Wilson reflects on what AI is changing for design engineers, and where human judgment still matters. He argues that agents can take over more of the scaffolding work, while product taste, restraint, and polished visual craft remain the real edge.
Read more [twilson.net]
– flareapp.io – Edit
We explain why Flare's old AI-generated solutions no longer fit the way developers debug with modern coding agents. The replacement is a better workflow built around the MCP server, CLI, Copy for AI prompts, and agent-friendly docs.
Read more [flareapp.io]
Sebastian explains why Amp became his default coding harness, and why user experience now matters more to him than model churn. He also shares the AGENTS.md tweaks that reduced overzealous verification during day-to-day coding.
Read more [sebastiandedeyne.com]
– www.beberlei.de – Edit
A practical walkthrough for running Claude Code inside Docker's new sbx sandbox, with a custom PHP setup and extra tools for open source work. Benjamin also explains why sandboxing AI coding agents is the sensible default.
Read more [www.beberlei.de]
– ankursethi.com – Edit
Ankur Sethi argues that manually retyping LLM-generated code is a practical way to avoid cognitive debt. It slows you down, but helps you understand the code, catch bad suggestions, and keep a strong mental model of your codebase.
Read more [ankursethi.com]
– albertoarena.it - submitted by Alberto Arena – Edit
An essay on how AI-assisted development turns engineers into full-time reviewers. We spend our days evaluating AI-generated diffs instead of writing code, and that shift carries a new cognitive fatigue and may widen the senior/junior gap.
Read more [albertoarena.it]
– ma.ttias.be – Edit
Mattias walks through moving an AI coding setup off a laptop and onto a private VPS. He covers Tailscale, tmux, a browser-based editor, and the small tweaks that make a remote setup practical from any device.
Read more [ma.ttias.be]
– albertoarena.it - submitted by Alberto Arena – Edit
There's a third way to automate Claude Code, and unlike /goal and /loop, it doesn't need your laptop open at all. Anthropic just shipped routines: cloud-hosted automations triggered by a schedule, an API call, or a GitHub event.
Read more [albertoarena.it]
A sharp writeup on how a malicious site could trick Claude into exfiltrating memory-derived personal data through its web browsing flow. It walks through the attack chain, the prompt injection setup, and Anthropic's eventual mitigation.
Read more [www.ayush.digital]
Jarred Sumner explains why the Bun team is moving from Zig to Rust, after years of fighting memory safety issues in a codebase that mixes GC and manual memory management. He also shares how Claude helped make a mechanical, test-suite-driven rewrite realistic without pausing feature work for a year.
Read more [bun.com]
