The Pragmatic Engineer

“The Pragmatic Engineer” delves into the intricacies of architecting enterprise-level solutions with a focus on knowledge base infrastructure, generative AI, and data augmentation for machine learning. It explores the challenges of moving beyond static data libraries to interact with living data, emphasizing the importance of understanding over mere indexing. The document discusses the implementation of secure semantic memory layers, multi-tenant pipelines, and the utilization of advanced technologies like Spark, EMR, and Airflow to build fault-tolerant and responsive systems. Additionally, it addresses the significance of context, precision in search mechanisms, and the role of vector embeddings in enhancing semantic understanding.

Visit The Pragmatic Engineer

The Pulse #191: a new trend of CPU shortages

For compute-intensive services: it’s worth reserving more compute now. Also: growth dreams end for more COVID-era unicorns, engineers losing touch with systems when AI handles incidents, and more

Building Codex with Tibo Sottiaux

The Pragmatic Engineer

OpenAI’s Tibo Sottiaux shares how Codex was built and how it’s reshaping software development.

What is happening with code reviews?

The Pragmatic Engineer

AI generates more code than devs can track in 2026, so will the code review process have to adapt – or is it doomed? A look into this decades-old practice and the approaches that could replace it

The Pulse: tech companies move to open AI models

The Pragmatic Engineer

Cost-saving efforts reveal that moving simpler workloads to open AI models is the easiest way to save ~50% on AI bills. Also: automated software maintenance experience, and more

The Pragmatic Engineer: Five years

The Pragmatic Engineer

As the newsletter reaches its fifth birthday, we reflect on how the publication has changed, and what to expect. Also: the launch of the ‘How Software Engineering is Changing’ essay contest

The Pulse: Meta wanted to reduce teams by 60% because of AI

The Pragmatic Engineer

We find out why Meta destroyed its standout engineering culture: it feared AI-native startups doing more with less. Also: thoughts on Ramp’s AI infra, GitHub’s load doubles in four months, and more

Why performant code matters (but gets widely ignored), with Casey Muratori

The Pragmatic Engineer

Casey Muratori explains why software performance matters, how developers can write faster code, and why he challenges conventional engineering practices.

Why Ramp built its own in-house coding agent, Inspect

The Pragmatic Engineer

A fintech company rejected the easy route and homebrewed its own coding agent – and is now a step ahead of coding agents from frontier AI labs. An in-depth look

The Pulse: We need to talk about migrations with AI

The Pragmatic Engineer

Asana completed a testing framework migration in two weeks, that they would have delayed for years more, and they’re not alone. Also: AI startups could make Gartner much less relevant, and more

From Chrome DevTools to AI Engineering, with Addy Osmani

The Pragmatic Engineer

Addy Osmani shares lessons from 14 years at Google and how AI agents are reshaping software engineering, developer workflows, and the skills engineers need to succeed.

Headed for the Exit: the Great Engineering Leader Career Break

The Pragmatic Engineer

Trend: more CTOs, VPEs, and Heads of Engineering are walking away from their high-status, in-demand positions. There are many reasons, mostly related to AI, and to "founder mode"

The Pulse: Meta’s self-inflicted resignation-wave

The Pragmatic Engineer

The social media giant is offering $1M+ retainer equity grants to staff who are leaving: and even this is not effective. Also: is Grok Bot the “OpenClaw moment” for managed AI agents?