Insights & Field Notes
Written from inside real engagements — what works in production, and what only works in a demo.
I Swapped "Service" for "Agent" in a 2016 Design Doc. Most of It Still Held.
Swapping 'service' for 'agent' in a 2016 microservices design doc still reads mostly correct — except in four places where teams are now burning money.
Moving Beyond LLM Wrappers to Autonomous Agents
Most 'AI products' are a prompt and a text box. Autonomous agents need state, tools, evaluation loops and a failure budget.
How Non-Tech Companies Achieve Immediate ROI with AI Automations
You do not need a data team to save 20 hours a week. You need a process map and three well-chosen automations.
The Data Layer Your Agents Actually Need: Snowflake, dbt and Contracts
Agentic systems amplify data quality — in both directions. Contracts and lineage are what keep them honest.
Scaling an R&D Organization to 150 Engineers Without Losing Velocity
Structure follows architecture. If your teams cannot ship independently, no process framework will save you.
Agentic Coding Workflows: Upskilling a Dev Team in Six Weeks
Tools do not create leverage — habits do. A structured curriculum turns AI assistance into measurable throughput.
The Technical Due Diligence Checklist Investors Rarely Ask For
Code quality is a lagging indicator. Look at deployment frequency, ownership maps and the on-call calendar.