// Blog

Field notes for engineers building agentic software.

Essays on multi-agent delivery, security failures, and the architectural trade-offs that matter when systems leave the demo stage.

Showing 31-45 of 94 posts. Search and filters apply to this page.

17 Apr 2026 News

Claude Stays Ad-Free, And Why That's a Bigger Deal Than It Sounds

Anthropic announced Claude will remain ad-free. In an AI market racing toward advertising, that's a deliberate strategic choice with real consequences.

Read article →
16 Apr 2026 News

Cursor, Claude Code, and Codex Are Becoming One Stack Nobody Planned

The AI coding tool market isn't consolidating — it's layering. Cursor orchestrates, Claude Code executes, Codex reviews. Here's why that matters.

Read article →
16 Apr 2026 News

OpenAI's Agents SDK Gets Sandboxes and a Harness — Finally

OpenAI updates its Agents SDK with sandboxing and an in-distribution harness for frontier models. Here's why that matters and what's still missing.

Read article →
16 Apr 2026 News

Codex for (Almost) Everything - OpenAI Turns Its Coding Agent Into a Full Workspace

OpenAI's latest Codex update adds computer use, an in-app browser, 90+ plugins, memory, and automations. It's no longer just a coding assistant - it's trying to own your entire development workflow.

Read article →
16 Apr 2026 News

Claude Opus 4.7 - The Autonomy Jump

Anthropic's Opus 4.7 isn't just a benchmark bump. It's the first model that genuinely feels like you can hand off hard work and trust it to come back with something solid.

Read article →
14 Apr 2026 News

Anthropic Is Building a Full-Stack AI Company

The Opus 4.7 rumours are less important than the surrounding product moves. Anthropic is clearly expanding from model vendor to full workflow platform.

Read article →
14 Apr 2026 News

The Agentic AI Market Needs Critics, Not More Launches

Agentic.ai is a useful signal that the AI tools market is getting crowded enough to need curation, scoring, and actual judgment instead of another flood of generic directories.

Read article →
14 Apr 2026 News

The Open Agent Idea Is Now Too Big for Microsoft to Ignore

Microsoft experimenting with an OpenClaw-like agent inside 365 Copilot is the clearest sign yet that local, long-running AI agents are moving out of hobbyist territory and into the enterprise stack.

Read article →
12 Apr 2026 Guides

Getting Started with Claude — Mac Desktop App and Subscription

Getting Started: Getting Started with Claude — Mac Desktop App and Subscription

Read article →
12 Apr 2026 Guides

Getting Around the App — Interface and Keyboard Shortcuts

Getting Started: Getting Around the App — Interface and Keyboard Shortcuts

Read article →
12 Apr 2026 Guides

Your First Agent Session: Getting Real Work Done

Getting Started: Your First Agent Session: Getting Real Work Done

Read article →
12 Apr 2026 Guides

Basic Commands and How to Talk to Claude

Getting Started: Basic Commands and How to Talk to Claude

Read article →
12 Apr 2026 Guides

Understanding Contexts — What the Model Remembers

Getting Started: Understanding Contexts — What the Model Remembers

Read article →
12 Apr 2026 Guides

Code Review — Asking Claude to Critique Your Work

Core Workflows: Code Review — Asking Claude to Critique Your Work

Read article →
12 Apr 2026 Guides

Debugging with Claude — From Error to Fix

Core Workflows: Debugging with Claude — From Error to Fix

Read article →