Practical Insights on Agents, AI Applications, and HMC
Practical lessons, tested workflows, and best practices for teams that want to adopt AI in a responsible and effective way.
Current project: aSPARK – an agile AI product team for Claude Code that takes every feature through five gates. Open source, MIT.
What You Will Find Here
The focus is actionable knowledge over hype: concise guides, deep dives, honest retrospectives, and templates you can apply directly in real projects.
-
01
Agents in Production
Real-world notes on planning, prompting, tool usage, and quality controls in agentic workflows.
-
02
Building AI Applications
From concept to operations: architecture, guardrails, data quality, and observable runtime processes.
-
03
HMC and Best Practices
Human-machine collaboration with clear roles, practical governance, and repeatable outcomes.
Latest Posts
-
From a 47-Minute Screen Recording to a Narrated Demo — Without Opening a Video Editor
How a raw recording of one aSPARK session became a captioned, branded, narrated 100-second demo the same day — planned from a hash ledger instead of a timeline, rendered with what ships with macOS, and voiced with ElevenLabs.
- claude-code
- agents
- agentic-workflows
-
Deleted Vacation Photos, Spaghetti Code, and the Question of Who Is Watching the Whole Project
How deleted vacation photos led to an open-source tool — and how building it revealed a structural problem that hits every team moving from experimenting with coding agents to using them in production at scale.
- agents
- agentic-workflows
- claude-code
-
One Person, a Whole Team: How aSPARK Turns Claude Code into an Agile Delivery Process
Why I built an agile AI team as a Claude Code plugin, how the SPARK loop works, and what happened when I ran a real feature through it.
- agents
- agentic-workflows
- claude-code