Writing

Engineering notes
on production AI.

Long-form essays on building production AI systems — agentic orchestration, tool reliability, evaluation, and the infrastructure that keeps it running at scale.

8 essays·23K words

last updated Sep 10, 2026

RSS for new essays

Sep 10, 2026·10 min read

Can We Really Make AI Safe?

Can we really make AI safe when we do not fully understand the model, and we are steadily giving it more access to the world?

ai-safetyagentscybersecurityarchitecture
read
Sep 6, 2026·14 min read

Fireworks AI ZDR: How to Set It Up Without Missing the Exceptions

Fireworks has a good zero-retention default for open-model inference. This guide covers the API settings, cache isolation, residency, and feature boundaries that decide whether that is true for your application.

llmprivacysecurityarchitecture
read
Jul 14, 2026·6 min read

Where Should the AI Actually Go?

A model can be capable of doing a task and still be placed in the wrong part of the system. I learned this while building AI for a legal workflow.

aiarchitecturemachine-learninglegal-tech
read
May 7, 2026·10 min read

The Ship You Can't Dock: Architectural Debt in the AI Era

In the fast-moving AI space, architectural debt isn't just about cutting corners—it's about reasonable decisions being invalidated by a shifting environment.

architectureaiengineeringtechnical-debt
read
Apr 29, 2026·18 min read

Scaling to 1,500 Concurrent Users: PgBouncer and Null Pooling

A deep dive into why application-level pooling fails for long-running AI workflows and how to implement PgBouncer with statement-level pooling to handle 30x the load with 10x fewer resources.

postgrespgbouncerscalabilitybackendai
read
Apr 18, 2026·12 min read

Zero Data Retention (ZDR) for LLM Providers

A practical guide to keeping your data private when using LLM APIs. Covers zero-retention endpoints, self-hosting, compliance requirements, and data protection patterns.

llmprivacysecurityarchitecture
read
Apr 5, 2026·8 min read

What Gemma 4 Actually Does Differently

Gemma 4's 31B model is outscoring systems with 10x more parameters on Arena Elo. Here's the architectural reasoning behind why that's possible.

gemmagooglearchitecture
read
Feb 15, 2026·9 min read

Injection Is Not Influence: The Illusion of LLM Memory

After three years of building LLM applications, I've learned that LLM memory is fundamentally different from human memory.

llmmemoryarchitecture
read