Why Codex has become my everyday AI tool
My current preference is less about collecting models and more about having one tool that fits my agent-driven working day.
AI Agents
Agentic AI systems, automation assistants, permissions, and workflows.
Talking to AI is turning tools into a working team
Voice makes briefing agents across several projects feel closer to working with a team than stopping to write another prompt.
The small uses of AI agents are still the ones that get me
AI agents are impressive in the big demos, but the everyday micro-uses are where they start to feel genuinely useful.
Why my personal AI agent runs on a Mac Mini
The appeal of a local agent is not just the conversation. It is being able to connect that conversation to files, browsers and everyday tools.
AI Agents Do Not Need Your Whole Password Manager
AI agents need controlled, auditable access to specific credentials, not your whole password manager and a prayer.
The Hard Part of AI Agents Is Not the Code
Code is becoming cheaper. Taste, boundaries, memory, permissions, and judgement are what make AI agents safe enough to trust.
The Lead Generation Tool I Actually Want Is Not an AI SDR
Useful AI lead generation should surface evidence, context, and human-reviewed opportunities, not blast cold messages at scale.
I Didn’t Build One AI Assistant. I Built a Team.
Why specialised AI agents beat one magical assistant, and how an agent team can reduce the cognitive glue of daily work.
OpenClaw Is Not Too Dangerous. It Is Too Powerful to Ignore.
OpenClaw shows why local, operator-owned AI agents are powerful, practical, and too important for founders to ignore.
From Clawdbot to OpenClaw: The AI Agent That Is Making the World Pay Attention
A practical look at OpenClaw, agentic AI, and why assistants that actually work for you feel like an inflection point.