Jul 9, 2026
The Activity Log System
A plain-markdown log that gives AI coding agents a time-ordered project memory across sessions, machines, and tools.
Ben Jones • 14 years building products • learning to build with AI
Making sense of AI by building with it.
A practical record of learning what AI is actually useful for, where it falls short, and how it changes the work.
No hype cycle recap. Just useful experiments, working notes, and lessons from figuring this out in practice.
Working notes
Latest working notes
Jun 28, 2026
AI Product Workflow Patterns
A working note on using AI to gather context, structure product artifacts, sharpen judgment, and preserve what I learn between sessions.
Jun 7, 2026
Building the Context Layer
How context files give your AI agent the information it needs to produce more useful, specific output — and how to build them.
Toolkit
The useful stuff
Prompts, guides, and working docs pulled out of the process and made reusable.
Projects
What I'm building
Shipped
Jones and AI website
Built by me, using an agentic development process. This personal website and publishing system powered by Next.js, MDX content, Vercel, Beehiiv newsletter capture, repo-level instructions, local skills, and a working log that keeps the build process visible.
Next.jsMDXVercelBeehiiv
In progress
Agent Native Composer
A local-first Markdown editor where each folder owns a durable AI agent, its active document, and the context needed to keep work moving over time.
CodexMarkdown editorAgent workspaceOpenKnowledge
Shipped
AI Learning Capture
A Codex skill that turns YouTube videos into evidence-aware learning reports with transcripts, claim labels, critique, and reusable templates.
CodexAgent skillYouTubePython
Shipped
Jones and AI visual system guide
A shipped brand-system project built from an AI-led brand interview, visual-direction exploration, a homepage concept, and a coding-agent-ready design spec.
Brand strategyDesign systemAI workflowHTML
Stay in the loop
One email a week. No hype.
Working notes, toolkit drops, and honest experiments on building with AI, straight to your inbox.