Author
Founder macleodlabs.ai, heimdall, Generative Agents, Advisor/ CTO graph8.com, ex AWS CTO/ IBM Technology Leader | xAWS Principal Architect | xBanking Chief Architect | Cloud, Crypto, & AI | DevOps & Containers inventor
How autonomous coding agents are rewiring the software development lifecycle — and the primary-source evidence on where they help, where they hurt, and what you must keep human.
Read →
How autonomous coding agents reshape planning, review, testing, and ops — and why the hard part of shipping them is governing what they produce, not generating it.
Read →
Anthropic's Project Fetch Phase Two shows Claude Opus 4.7 crushing the software side of robotics autonomously, while precise physical control remains stubbornly unsolved.
Read →
A primary-source deep dive into the agent execution loop — plan/act/observe/repeat, stop conditions, context management, verification, sub-agents, and the failure modes (doom loops, reward hacking, context rot) you must engineer against to ship agentic AI.
Read →
Agentic AI just learned to delegate at scale—and the architecture is simpler than you'd think.
Read →
Anthropic's new economic study argues coding agents amplify domain expertise rather than replace it — here's what's real, what's contested, and what it changes about production agent design.
Read →
Frontier models may not own all the best points on the cost-accuracy Pareto curve—and they may not be on the curve at all.
Read →
AI vendor lock-in just became more dangerous than cloud lock-in ever was—and the solution isn't what you'd expect.
Read →
Production agent monitoring has a brutal cost-accuracy trade-off. Frontier models (Claude, GPT) give you high-quality judgments but burn money at scale. Rule-based evals are cheap but brittle. Human review doesn't scale past hundreds of traces per day.
Read →
Agentic AI is moving from monolithic loops to orchestrated multi-agent systems, and the shift is visible in production tooling.
Read →
How a defensive find-fix-test loop got reframed as a national-security weapon — and why dual-use capability is the substrate of every coding agent, not a flaw to be guardrailed away.
Read →
What does it actually mean to manage when half your team's output is generated by something that can't be held accountable?
Read →