agentic-coding

A collection of 133 posts

Agentic Engineering Isn't Vibe Coding — And Pretending Otherwise Wrecks Brownfield Codebases

There's a particular kind of engineering debt that doesn't show up in your code review metrics. It's the debt that accumulates when your agent generates code that looks right in isolation and is quietly wrong in context — the abstraction that breaks three layers away,

02 May 2026 6 min read

agentic-coding

The Four Layers of AI Agent Development That Actually Work

Most developers who picked up AI coding tools in the past eighteen months have had the same experience. It works beautifully — until it doesn't. You start a project, you prompt, you iterate, you ship. Then the codebase grows. More services, more state, more API surface. The agent starts

02 May 2026 6 min read

agentic-coding

GitHub Copilot's June Billing Overhaul Is Real: Here's What Changes and Who It Hurts

GitHub paused new sign-ups for Copilot Pro, Pro+, and Student plans this week. That's the tell. Companies don't freeze new customer acquisition for a product that's hitting its numbers — they do it when demand is outrunning their cost recovery targets faster than they can

01 May 2026 4 min read

agentic-coding

Anthropic Opens Claude Security Beta, Brings AI-Powered Vulnerability Scanning to Enterprise Codebases

Anthropic has a habit of shipping the offense and the defense in the same quarter. On Thursday, it moved Claude Security — the tool that finds and patches vulnerabilities in enterprise codebases — from closed research preview to public beta for all Claude Enterprise customers. The same week it publicly disclosed that

01 May 2026 4 min read

agentic-coding

Bluesky Outage Spawns the Predictable Vibe Coding Blame Cycle — the Tech Industry's New Boogeyman Is Up and Running

Bluesky had a bad Monday. The service went down, users lost access, and within hours the discourse on social media had found its familiar villain: vibe coding. The posts and memes were predictable — blame for the outage being attributed to AI-generated code, insufficient human review, and the general sin of

30 Apr 2026 3 min read

agentic-coding

Microsoft Agent Framework 1.0 Unifies AutoGen and Semantic Kernel and Ships the Stable APIs Enterprises Have Been Waiting For

Microsoft shipped Agent Framework 1.0 this week, and the version number is doing real work here. This is not a preview with asterisks. It is the completion of a unification project that merged two distinct agent frameworks — Semantic Kernel and AutoGen — into a single open-source SDK under the Microsoft.

30 Apr 2026 3 min read

agentic-coding

Apple Pushes Back on Vibe Coding Apps Over Guideline 2.5.2 — and the Category Has to Split Around It

Apple just confirmed what the vibe-coding ecosystem has been dreading for weeks: the App Store crackdown on apps that download and execute new code dynamically is real, it's systematic, and it has a specific rule behind it. Guideline 2.5.2 — the requirement that apps be self-contained and

30 Apr 2026 4 min read

agentic-coding

A2A Protocol Hits 150 Organizations and Three Clouds at One Year — the HTTP for AI Agents Is No Longer a Science Project

A protocol nobody outside enterprise IT had on their bingo card just turned one year old and nobody is laughing it off anymore. The A2A Protocol — the Linux Foundation-hosted standard for getting AI agents from different vendors to talk to each other without bespoke integration work — announced it has crossed

30 Apr 2026 3 min read

agentic-coding

Vibe Coding Goes Mobile — and Apple Just Rewrote the Rules While Letting Lovable Through the Door

Apple's enforcement of Guideline 2.5.2 against vibe-coding apps has been one of the more instructive regulatory stories in the developer tools space, and Lovable's mobile app launch this week is the clearest example yet of what compliance actually looks like — and what it costs.

29 Apr 2026 3 min read

agentic-coding

OpenAI Jumps Out of Microsoft's Bed, Into Amazon's Bedrock — and the Whole Cloud AI Map Redraws Around It

OpenAI and Amazon announced something this week that should interest every developer who has spent time navigating the awkward gap between "we want to use your AI model" and "here is our enterprise procurement policy." GPT-5.5 and Codex are now available in limited preview on

29 Apr 2026 3 min read

claude-code

Claude Code Is Quietly Becoming Anthropic's Default Interface for Building Software

Claude Code Is Quietly Becoming Anthropic's Default Interface for Building Software Anthropic published a new Claude Code product page last week, and it reads less like a landing page refresh than a positioning document. The company is no longer presenting Claude Code as a clever CLI for power

29 Apr 2026 4 min read

agentic-coding

Argus Gives Claude Code the Observability Layer Every Production Tool Needs: It Knows What the Agent Did, When, and What It Cost

Claude Code runs on your machine, touches your files, executes shell commands, and costs money per token. Most developers still have no idea what their agent session actually did between "start" and "done" except for what they can remember from the scrollback. That was acceptable when

28 Apr 2026 3 min read

← Newer Posts Page 6 of 12 Older Posts →