Writing

Notes from building agents in public.

Build logs and hot takes on agentic systems, retrieval, and the unglamorous infrastructure that makes AI reliable.

Filter
12 entries · roughly weekly
FeaturedAI SystemsJul 20264 min read

I Built a Deep Learning Framework From Scratch. Now I Read Every Model Differently.

The best class I took at Berkeley had me rebuild the thing under PyTorch, autodiff and layers and optimizers, from numpy up. It did not teach me deep learning so much as give me the foundation to understand everything I learned after.

Read the build log
Jul 2026
AI Systems

Your Agent Has an Exactly-Once Problem

During live telehealth sessions, stroke patients wear a mixed-reality headset while an LLM judges each rep and writes the result into their clinical record. The newest fix in that repo is a one-line database change, and it is the whole 2026 agent-infrastructure conversation in miniature.

6 min read →
Jul 2026
Distributed Systems

When Optimal Is the Wrong Answer

I spent a summer at IMDEA writing a MILP that schedules DAG workflows across fog nodes provably optimally. Then I watched it fall over at a hundred tasks. Optimal and usable turned out to be different objectives.

8 min read →
Jun 2026
AI Systems

The Model Doesn't Do Anything. Your While Loop Does.

I built two agents this week and realized the model barely does anything - it returns JSON. The loop, the memory dict, and the tool schemas do the real work. That is the actual engineering.

6 min read →
May 2026
AI Systems

Evaluating AI Agents Like You Ship Software

How I built evaluation pipelines for non-deterministic systems, and why vibes-based testing doesn't scale.

7 min read →
Apr 2026
Infrastructure

Designing Retry-Aware Infrastructure

Notes on queues, idempotency keys, and what it actually means to recover gracefully from failure.

6 min read →
Mar 2026
Product Engineering

From Prototype to Production

What changes when a demo becomes load-bearing. The cuts, the rewrites, and the thing nobody tells you.

5 min read →
Feb 2026
AI Systems

Multi-Cloud Without the Chaos

Building a single pipeline abstraction across AWS, GCP, and Azure, and why the queue lives in Postgres.

8 min read →
Jan 2026
Infrastructure

What I Learned Shipping to Researchers

Clinical and academic users break your assumptions. Notes on the UCSF Health × Stanford Medicine deployment.

4 min read →
Soon
AI SystemsWeek 2

Your Agent Has Amnesia. Here's the Dict That Fakes Memory.

LLMs are stateless and frozen. Short-term memory is just context-window management: what you keep, what you summarize, what you drop.

Coming soon
Soon
InfrastructureWeek 3

The Gap Between a Notebook Agent and a Production One.

My notebooks ran on mock dictionaries. Here is what every mocked piece becomes in a real system: retries, timeouts, persisted state, observability.

Coming soon
Soon
RetrievalDrafting

Five Ways to Chunk a Document, and When Each One Bites You.

Fixed, semantic, recursive, structure-based, LLM-based. Recursive is the sane default, but the failure modes are where the real decisions live.

Coming soon