Distributed Systems

Software Engineering

System Design Concepts

Software Development

Latency

Explore recommended reads, summarized by AI

Software Performance and System Design

Technical writing on optimizing latency, throughput, and reliability in software systems and architectures.

Performance Optimization and System Design

Popular this week

In

Zepto TechXPress

by

Zepto Tech

Building a Lightning-Fast Search Relevance Ranker

Casatrick - Web3 Trading Systems

I Rewrote My Polymarket Trading Bot in Rust-Here’s What Changed in Execution Latency

Kevin Tung

All 20 Pool Connections Sat Idle in Transaction. Health Checks Succeeded Only 20–27% of the Time.

Keshavvv

Latency and Throughput in Backend Engineering: What Makes an API Actually Fast?

cybersecbella

Cache eviction methods to degrade a GPU’s performance

Latest stories

Kevin Tung

All 20 Pool Connections Sat Idle in Transaction. Health Checks Succeeded Only 20–27% of the Time.

Nitisha Aggarwal

The Hidden Delays Behind Your AI Response

In

GoPenAI

by

Rashmi

The Hidden Cost of AI Agents: Tokens, Latency, Retries, and Tool Calls

In

Towards AI

by

“The AI Engineer”

Your p99 Latency Belongs to Someone Else

Kevin Tung

Every Request Took 44ms. curl -w Showed the Server Wasn’t Doing Anything for 43 of Them.

See more stories

Who to follow

Popular this week

In

Zepto TechXPress

by

Zepto Tech

Building a Lightning-Fast Search Relevance Ranker

Casatrick - Web3 Trading Systems

I Rewrote My Polymarket Trading Bot in Rust-Here’s What Changed in Execution Latency

Kevin Tung

All 20 Pool Connections Sat Idle in Transaction. Health Checks Succeeded Only 20–27% of the Time.

Keshavvv

Latency and Throughput in Backend Engineering: What Makes an API Actually Fast?

cybersecbella

Cache eviction methods to degrade a GPU’s performance

Latest stories

Kevin Tung

All 20 Pool Connections Sat Idle in Transaction. Health Checks Succeeded Only 20–27% of the Time.

Nitisha Aggarwal

The Hidden Delays Behind Your AI Response

In

GoPenAI

by

Rashmi

The Hidden Cost of AI Agents: Tokens, Latency, Retries, and Tool Calls

In

Towards AI

by

“The AI Engineer”

Your p99 Latency Belongs to Someone Else

Kevin Tung

Every Request Took 44ms. curl -w Showed the Server Wasn’t Doing Anything for 43 of Them.

See more stories

Who to follow