REF / WRITING

Writing.

Essays, playbooks, and short notes on software, digital marketing, and start-up operating. One new piece each week.

Total posts109
CadenceWeekly
Domains4
FormatEssay · Note · Case
01
FILTER

By domain.

02
LATEST

All posts.

Showing 2130 of 109.

Antigravity 2.0 Hands-On: Is Google's Agent-First IDE Ready for Production?

Google's I/O announcement that most affects what my IDE looks like next quarter is Antigravity 2.0. The redesigned desktop application, a stable Antigravity CLI, a new SDK for programmatic agent deployment, specialized sub-agents, and a security posture (cross

Gemini 3.5 Flash: What the 3.1 - 3.5 Jump Changes for Builders

Google released Gemini 3.5 Flash yesterday at I/O. The headline that actually matters for builders: a Flash-tier model that beats the previous-generation Pro across coding and agentic benchmarks while running roughly four times faster than other frontier model

Gemini Omni: Multimodal Generation Crosses a Production Threshold

The release that has the least clear practical implication from I/O is also the most strategically interesting. Gemini Omni is a multimodal generation model that takes image, audio, video, and text as input and outputs video. The output is "grounded in real-wo

Google's AI Search Box Overhaul: A Marketer's Playbook

Google rebuilt its Search box at I/O. The new version accepts images, files, videos, and even open Chrome tabs as inputs, with AI Mode promoted from a separate destination to a primary surface inside core search. This is the single most consequential I/O annou

Why HTML Beats Markdown for Claude Code Plans and Specs

I have stopped writing markdown plans for Claude Code. Not because markdown stopped working, but because I stopped reading them. Once the model started running long enough to produce thousand-line plans, my honest behaviour was to skim, lose the loop, and shru

Google's Managed Agents API: A Production Agent in One Call

The most consequential developer announcement from I/O isn't a new model. It's a new primitive: the Managed Agents API. One API call spins up a fully provisioned agent — sandboxed Linux environment, tool use, code execution, persistent context — running on Gem

Cursor 3 Builder's Guide: 7 Things That Changed for Production Code (2026)

Cursor 3 is the first version of the product that isn't a VS Code skin. The editor has been rebuilt around agents instead of files, and after six weeks of using it as my daily driver the change is bigger than the marketing makes it sound. It is not "an IDE wit

Cursor Composer 2.5 Builder's Guide: 10× Cheaper Than Opus 4.7 (2026)

Composer 2.5 shipped yesterday. The headline number, accurate as far as I can tell, is that it sits within striking distance of Claude Opus 4.7 and GPT-5.5 on coding benchmarks while costing roughly a tenth as much per task. If that holds up in your workloads,

5 Levels of Using Claude in 2026: From First Chat to Always-On Architect

Most people using Claude are stuck one level below their actual potential. Not because they lack the skill to operate the next surface, but because they cannot picture what the next ceiling looks like, so they keep optimising the one they're already on. This e

The Operating Cadence I Run for SMB Clients (and Why Weekly Beats Daily)

When I started taking on fractional CTO and operational advisory engagements, I defaulted to the cadence I knew from agency life: daily standups, weekly status reports, and monthly strategy reviews. Three months into my first few engagements, I noticed somethi