You're using AI to be more productive. So why are you more exhausted than ever? The paradox every engineer needs to confront.
Not prompts. Not models. Feedback loops. The engineering discipline that separates teams thriving with AI from teams drowning in reviews is called backpressure.
I read Claude Code's leaked source. Not magic, just good engineering. 10 patterns that show what actually matters when building AI tools.
A technical guide to the control plane behind production coding agents: workload selection, identity, sandboxes, context, workflow graphs, CI, observability, and human control.
Agent coding tools need to make their work reviewable, not just generate more code.
Under partial failure, retry loops can rearrange history. If order, duplication, or staleness matters, retry needs state.
Agents need delegated access, not inherited human access. Put policy between the agent and the tool before agents touch real systems.
What four years at Gitpod and Ona taught me about public work, trust, messy ownership, and getting closer to rare work.
Netflix spent years building their experiment platform. You have the tools and a weekend. The hard part is not spinning things up. It is tearing them down cleanly when the idea fails.
agent-trace shipped two months ago as a debugging tool. People started asking how to run it in production. v0.4.0 and v0.5.0 are the answer.
I turned down two roles at global tech companies this year. Not because of the money. Because of relocation. The assumption global companies keep getting wrong about hiring in India.
Your team fills a Google Form. The agent reads it, picks a restaurant, builds a Swiggy cart per person, and waits for you to confirm.
The Bitwarden CLI supply chain attack explicitly hunted Claude Code, Cursor, and Codex CLI configs. The same week, DPRK confirmed slopsquatting works in the wild. Here is what happened and what to do.
The Vercel breach did not start at Vercel. It started at Context.ai. And the fix is not rotating credentials. It is a different credential model for AI tools entirely.
There's a moment in every long review cycle where you quietly check out. It doesn't look like giving up. It looks like being collaborative.
Stripe merges 1,000+ agent PRs per week. Spotify vetoes 25% of agent sessions. Cursor runs hundreds of agents in parallel. Dashboards show the model layer. Traces show the system layer. You need both.
Most AI content teaches you how to write prompts. This is not that. I've spent three years at Ona...
Nobody told me that ambition has a tax. Not the long hours or the missed weekends. The quieter kind.
We have better observability for a Node.js microservice than for an agent that just rewrote half a codebase. Here is what is missing.
Fifty approval prompts or full shell access. Nothing in between. The permission model needs infrastructure, not prompts.
Gitpod started as an open-source project. Long before “AI productivity” became a thing, the core...
Where containers stop being simple Containers are sold as a solved abstraction. You...
Bought my first home. Gave my first international conference talk. Shipped AI tools used by Fortune 500 companies. My honest 2025 wrap.
A deep dive into semantic deduplication for LLM context windows If you're building with RAG...
Finding vulnerable code is only half the battle. When a critical CVE drops, engineering teams face a...
Why traditional access control fails for AI agents, and how relationship-based authorization provides...
The $10M question nobody's asking While the industry obsesses over model parameters and...
Introduction AWS S3 Vectors promises "billions of vectors with sub-second queries" and up...
TL;DR: While building AgentFlow, an open source orchestration engine for AI agents, I discovered...
This analysis is based on official pricing documentation and straightforward cost calculations. ...
Competence earns respect, but originality creates legacy.
Whatever you do, care. Care enough to notice. Care enough to act. Care enough to finish things well.
Your AI teacher is free, available 24/7, and infinitely patient. Stop asking for permission to learn.
Organizations will always reward perceived value over hidden value. The question is whether you'll play the game as it is.
LLM inference is shifting from compute-bound to memory-bound. Treating GPU memory like an OS does RAM is the path forward.
A technical examination of production-grade LSP-MCP integration After spending months analyzing AI...
Most people think you build skills, then market them. It turns out this is backwards. The market is always watching, and the feedback loop is so long you don't notice.
You spend time setting up Claude Code with specific instructions in your CLAUDE.md file. Maybe you...
Prompt engineering optimizes the question. Context engineering optimizes the information the model sees before it answers. Here's why the latter wins.
Claude Code is a powerful AI development tool, but it comes with a rate limit if you're on the Pro...
API keys give all-or-nothing access. AI agents need fine-grained, task-scoped, auditable authorization. Here's how to build it with OpenFGA.
Model Context Protocol (MCP) is a protocol created by Anthropic designed to enable AI models to...
Documentation remains a critical resource for developers, serving as the definitive guide and...
AI coding agents like Cline and RooCode are powerful but unpredictable. A simple misconfiguration...
AWS Lambda is the go-to serverless computing service for developers who love event-driven...
Our CI pipeline’s integration tests were running sluggishly. The primary bottleneck wasn't the tests...
Introduction When working with large RAG (Retrieval-Augmented Generation) systems, getting...
Amazon S3 server access logs are a treasure trove of valuable information, detailing requests made to...
This is a submission for the DevCycle Feature Flag Challenge: Feature Flag Funhouse What I...
Imagine rushing to grab your morning coffee, only to find the barista needs to boot up the espresso...
Sometimes, the simplest solutions yield the most dramatic improvements. In a recent private project,...
Running self-hosted GitHub Actions runners on the cloud provides great control, but the costs can...
When you think about Docker, what comes to mind? Is it containerized apps for production? Maybe...
The looming change On November 5, 2024, GitHub announced a significant change that will...
If you've ever scratched your head over unexpected timeouts in your AWS ECS Service Connect...
tl;dr; High memory consumption during k6 load tests is often a result of high cardinality...
tl;dr; Migrating image data from Cloud SQL to GCS significantly improved database...
Introduction Large Language Models (LLMs) have revolutionized natural language processing...