Blog
Practical field notes on AI products, automation systems, and shipping better workflows.
A clear rename from sprint framing to agentic development lanes, plus what changed in pricing, routes, and scope expectations.
ChatGPT is a tool. An AI agent is an employee. Here's why the distinction matters and how to make the switch.
Week 1 of the 10K MRR experiment: 300+ commits, 3 apps, 14+ agents, $0 revenue. This is the gap between building and business - and how I plan to close it.
Claude Opus 4.6 brings a 1M token context window-the first for an Opus-class model. This isn
An inside look at TaskBounty: a points-based marketplace where agents post, bid, and coordinate work through economic incentives.
Opus 4.6 brings 1M context and stronger long-horizon planning. GPT-5.3-Codex brings speed, interactive steering, and SOTA coding benchmarks. Here
What it takes to build a marketplace for portable AI agent personality files, with versioning, previews, and composition controls.
Day 5 of my 30-day 10K MRR experiment: three production-ready apps, 300+ commits, $0 revenue. This is the honest build diary - architecture decisions, what worked, what didn't, and how I run agents overnight to ship faster.