Let's connect
Featured writing

Writing on AI engineering

Prompt engineering, system design, and building AI products that hold up past the demo. Cross-posted from Substack.

Allai engineeringarchitectureclean codeconcurrencygood codeharness engineeringlockingmoatproduct engineeringproduct tasteprompt engineeringragsaassdlcsoftware engineeringstartupsystem design
How LinkedIn Could Feed You a Feed in Under 200ms (An Essay on Scale)
· 11 min read

How LinkedIn Could Feed You a Feed in Under 200ms (An Essay on Scale)

A quick note before we start: this is not a description of LinkedIn’s actual architecture.

Read on Substack →

system design
The Math Behind Your Feed’s Order (And What It Says About the Product)
· 6 min read

The Math Behind Your Feed’s Order (And What It Says About the Product)

Every social feed you scroll runs a scoring function on every post, in real time, before you ever see it.

Read on Substack →

ai engineeringsystem design
The 8 Constraints You Need Before You Draw a Single Box
· 11 min read

The 8 Constraints You Need Before You Draw a Single Box

“Design Twitter.”

Read on Substack →

system design
AI Engineering Is Real Work. That’s Exactly Why It Won’t Stay a Category.
· 2 min read

AI Engineering Is Real Work. That’s Exactly Why It Won’t Stay a Category.

Last weekend I spoke at CodeCon Summit. The talk was called “O Guia do Mochileiro da Engenharia de IA” — the hitchhiker’s guide to AI engineering — and the premise was ambitious: walk through 42 concepts anyone entering this field needs to understand today, in one session, for a room of over 300 engineers.

Read on Substack →

ai engineeringsoftware engineering
Software Engineers Are Becoming Product Engineers, Whether They Like It Or Not
· 4 min read

Software Engineers Are Becoming Product Engineers, Whether They Like It Or Not

Writing code fast stopped being a differentiator.

Read on Substack →

product tasteproduct engineeringsoftware engineering
The Interview Question That Actually Tests Seniority (And It’s Not About the Algorithm)
· 8 min read

The Interview Question That Actually Tests Seniority (And It’s Not About the Algorithm)

“You have a 20GB CSV.

Read on Substack →

system design
Lock, check, or reserve: the concurrency decision nobody teaches
· 6 min read

Lock, check, or reserve: the concurrency decision nobody teaches

Somewhere right now, a transaction is holding a lock open while it waits on a payment gateway to respond.

Read on Substack →

concurrencysystem designlocking
Your engineers are already using AI agents. You just don’t know how.
· 5 min read

Your engineers are already using AI agents. You just don’t know how.

Fragmented adoption feels like progress.

Read on Substack →

sdlcsoftware engineering
The Hidden Cost Curve of 'Go Horse' Code
· 5 min read

The Hidden Cost Curve of 'Go Horse' Code

Every shortcut in engineering is a loan — and the interest rate is decided long before you know you’re paying it.

Read on Substack →

software engineering
The Hidden Cost of Chatty I/O
· 5 min read

The Hidden Cost of Chatty I/O

Every network call has a fixed tax.

Read on Substack →

system design
I asked 7 definitions of good code to judge the same function. they disagreed.
· 10 min read

I asked 7 definitions of good code to judge the same function. they disagreed.

There is no universal standard for good code.

Read on Substack →

clean codegood codearchitecture
Before You Scale: What Chapter 1 of Designing Data-Intensive Applications Actually Teaches You
· 8 min read

Before You Scale: What Chapter 1 of Designing Data-Intensive Applications Actually Teaches You

Everyone cites Designing Data-Intensive Applications. It’s on the reading list of every serious engineering team. Engineers drop it in interviews. CTOs reference it in system design discussions. But most people read it once, nod along, and move on without internalizing what the first chapter is actually saying.

Read on Substack →

system design
MCP + Skills: The New Interface for Engineering Work
· 5 min read

MCP + Skills: The New Interface for Engineering Work

There’s a type of cognitive overhead that engineers have normalized so completely they stopped noticing it.

Read on Substack →

ai engineeringharness engineering
Streaming in LLM Agents Isn’t Just a UX Feature. It’s an Architecture Decision.
· 4 min read

Streaming in LLM Agents Isn’t Just a UX Feature. It’s an Architecture Decision.

Most teams add streaming to their AI products because it feels faster.

Read on Substack →

ai engineeringsystem design
Building Internal Chatbots That Actually Work
· 7 min read

Building Internal Chatbots That Actually Work

Every company I’ve worked with has the same problem dressed in different clothes.

Read on Substack →

ragai engineeringsystem design
The Unit Economics of AI Products
· 12 min read

The Unit Economics of AI Products

Traditional SaaS has a comforting property: infrastructure costs are largely fixed.

Read on Substack →

ai engineering
Caveman Prompting: I Tested the Claim. The Real Finding Is Somewhere Else.
· 18 min read

Caveman Prompting: I Tested the Claim. The Real Finding Is Somewhere Else.

There’s an idea that circulates in AI engineering circles called “caveman prompting.” The premise: write your instructions in stripped-down, telegraphic English — almost no grammar, no courtesy, just the bare intent — and the model will still deliver.

Read on Substack →

prompt engineeringai engineering
Your Micro SaaS Will Be Cloned. Here’s What Actually Protects You.
· 5 min read

Your Micro SaaS Will Be Cloned. Here’s What Actually Protects You.

Everyone tells you to build the moat.

Read on Substack →

startupsaasmoat
Designing AI Products That Users Actually Trust
· 11 min read

Designing AI Products That Users Actually Trust

Getting the architecture right is necessary.

Read on Substack →

ai engineering
How to Build AI Agents That Don’t Collapse in Production
· 12 min read

How to Build AI Agents That Don’t Collapse in Production

The previous chapter made the case for workflows.

Read on Substack →

ai engineering