Writing
Blog
Thoughts on LLM agent architecture, cloud infrastructure, AI systems in production, and lessons from building teams and products at scale. Published weekly or biweekly.
Fable 5 vs Opus 5: Picking a Frontier Model for Real Engineering Work
Anthropic shipped two frontier-tier models seven weeks apart, and Opus 5 lands at half of Fable 5's price. The interesting question isn't which is smarter — it's where the premium actually pays for itself.
Prompt Injection Is a Systems Problem
Two years of trying to solve prompt injection at the prompt layer has produced no reliable defense. The teams shipping agents safely stopped trying — and constrained the blast radius instead.
Context Engineering Beats Prompt Engineering
Million-token context windows didn't kill retrieval. They moved the problem: from 'what can we fit' to 'what should be in there', which is a much harder question.
Automating the Boring 80%
The AI automation projects that worked weren't the ambitious ones. They were narrow, boring workflows with a human at the end — and that pattern is not an accident.
You Don't Have a Prompt Problem, You Have an Eval Problem
Every team stuck in a prompt-tweaking loop is stuck for the same reason: they can't measure whether a change helped. Here's how I build eval infrastructure, and why I now do it first.
The Real Cost Curve of LLM Inference at Scale
Per-token prices have collapsed. Production AI bills haven't. Here's where the money actually goes, and the four levers that moved it on systems I've worked on.
MCP and the End of Bespoke Tool Glue
For two years every AI integration I built was hand-rolled glue. Standardized tool protocols changed the economics of that work — but not in the way most write-ups suggest.
One Interface, Five Voice Providers
I integrated five AI voice agent vendors into a single production app. The hard part wasn't the APIs — it was deciding what the abstraction was allowed to know.
Building LLM Agents That Don't Break in Production
Most LLM agent demos look clean. Production is a different story. Here's how I think about designing agent systems that are actually reliable.
What I Learned as a Founding CTO
Five years leading engineering at a startup taught me things no university or senior role at a big bank could. Here's what actually matters when you're the one accountable for everything.