Claude code
We track 21 posts about Claude code from 14 engineering blogs. Most active: Nicolas Fränkel, Real Python, Pulumi. Latest post: Sep 29, 2026.
Companies writing about Claude code
Recent posts
Integrating Claude Code with Auth0 APIs (opens on the source site)
Auth0 ·
Pair Claude Code with the Auth0 MCP Server to audit JWT configs, scaffold M2M apps, and refactor auth code from the terminal — with scoped access and security guardrails.
Route every Claude Code message to the right model with Jev (opens on the source site)
Pulumi ·
Not every message you send to Claude Code needs the most capable model. A quick question about a Git command runs on the same model as a refactor across three services, unless you remember to switch models first. Jev, a new model from TypeSafe AI, can make that decision for you in a few hundred milliseconds and for a fraction of a cent. So I built jev-router, an open source router that asks Jev which Claude model each of your messages needs, and sends it there. What Jev is After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?I’ve spent the last 2…
10 tips to improve your coding agent game (opens on the source site)
Pulumi ·
In May I told you to trim the root instruction file until it fits on one screen. I also said anything that needs a hard guarantee belongs in a hook. In June I argued that the model that wrote the code shouldn’t be the one grading it. Several papers published this summer tested related questions. Most of the findings support that advice, while the research on subagent costs calls for more caution. Below are ten tips for working with any coding agent. Each one is checked against what the research measured, which is sometimes narrower than the abstract suggests. Instructions kept only in chat…
AI-assisted genealogy, a follow-up (opens on the source site)
I got a lot of feedback on my post AI-assisted genealogy, some good, some not so good. In any case, I felt the subject was interesting to a lot of people. Meanwhile, I continue working on my tree, and I have deepened my understanding of the subject. In this post, I want to share again. Trust, but verify Let’s address the not-so-good feedback first. The gist of it was: AI can hallucinate. It’s true in theory: when you ask a question, it provides any answer.
Claude Code always produces something. That’s the hard part. (opens on the source site)
I've been using Claude Code several hours a day for months, and I'm having a blast. But an agent does what you tell it, not what you meant — which is why validating your results now matters more than the results themselves. The post Claude Code always produces something. That’s the hard part. appeared first on LernerPython.
Build an AI Agent (From Scratch) (opens on the source site)
Facts 10 chapters$29.29 (at the time of this writing)315 pages Chapters Building your first LLM agentWhat is an AI agent?
Spotify’s Backstage Portal cut my Claude Code token usage by 90% (opens on the source site)
Spotify ·
Most of what an AI coding agent does for me isn't thinking. It's I/O. The post Spotify’s Backstage Portal cut my Claude Code token usage by 90% appeared first on Spotify Engineering.
Portal by Spotify cut my Claude Code token usage by 90% (opens on the source site)
Spotify ·
Most of what an AI coding agent does for me isn't thinking. It's I/O. The post Portal by Spotify cut my Claude Code token usage by 90% appeared first on Spotify Engineering.
Quit Blabbing, Claude Code! Shorter Answers with Output Styles (opens on the source site)
A note from the author: Just before this post was set to be published, a new feature was released on Claude Code that makes this post somewhat obsolete: Claude’s new “Concise” output style. I was sick of scanning through walls of text each time I asked Claude Code a question. Skills like I have ADHD […] The post Quit Blabbing, Claude Code! Shorter Answers with Output Styles appeared first on Atomic Spin.
AI-assisted genealogy (opens on the source site)
My son recently came to me to brag about using AI to find our ancestors. While the results were correct, I didn’t learn anything new, as it stopped at my grandparents. I was never very interested in my genealogy, but I decided to see if AI would be a good tool for this. TL;DR: Yes, it is, and even more than that. In a little less than one month, I managed to gather more than 600 individuals and get back 12 generations in some branches.
Quiz: Getting Started With Claude Code (opens on the source site)
Test your Claude Code basics: install it, set it up, work with CLAUDE.md, and use Git to stay in control of your changes.
Graft for Claude Code: Cutting Token Use by 42% in Practice (opens on the source site)
Graft is open-source hooks for Claude Code that reduce task tokens by 42% in controlled benchmarks (8,070 to 4,650 mean tokens), cutting cost from $0.0429 to $0.0292 per task. Hooks intercept grep calls, optimize context, improve SWE-bench Verified from 54% to 66%. Article explains how Graft works, install/config, and whether the 42% claim applies to your workflow. Continue reading Graft for Claude Code: Cutting Token Use by 42% in Practice on SitePoint.
How to Use Claude Code to Write and Debug Python (opens on the source site)
Learn how to use Claude Code to build and debug Python projects with natural-language commands right from your terminal.
Quiz: How to Use Claude Code to Write and Debug Python (opens on the source site)
Test your understanding of Claude Code by working through installation, plan mode, diff review, and debugging a Python project.
Claude Code Routines: A Third Way Beyond /goal and /loop (opens on the source site)
There's a third way to automate Claude Code, and unlike /goal and /loop, it doesn't need your laptop open at all. Anthropic just shipped routines: cloud-hosted automations triggered by a schedule, an API call, or a GitHub event. Read more
DO_NOT_TRACK Breaks Claude Code Remote Control (opens on the source site)
My .zshrc from my world famous dotfiles has a couple of lines with the comment "because we can't have nice things". Both are for privacy with the command-line tools I use. One is specific for GitHub's gh, the other is a bit more generic, but allegedly utilized by Claude Code. As I sink deeper into the AI psychosis, I've been dabbling more and more with unattended sessions. I primarily run them outside of my personal user account. Sometimes on separate machines altogether. All of which are outside of the influence of my dotfiles. That is, until this past week. My latest workflow has been to…
AI gateways: why and how (opens on the source site)
Before working for 2 years on the Apache APISIX API gateway, I was mainly oblivious to API gateways. It’s only by working with them that I understood their value. Decoupling the client and the server unlocks a lot of options: moving authentication to the API Gateway, securing APIs, deduplicating API requests, etc. In this post, I want to describe how the same pattern applies to AI. AI gateways AI gateways work in a similar way.
Android Skills: Expert Instructions for Your AI Agent (opens on the source site)
Blundell's Android Tutorials ·
Google just published a set of Android skills a collection of expert, AI-optimised instructions covering the most common and painful Android development workflows. (Upgrading to AGP 9, migrating XML layouts to Compose, wiring up Navigation 3.) AI automated step-by-step procedures grounded in official Android best practices. The GitHub repo defaults to wiring them into Gemini […] The post Android Skills: Expert Instructions for Your AI Agent first appeared on Blundell.
Implementing a clear room Z80 / ZX Spectrum emulator with Claude Code (opens on the source site)
Antirez ·
Anthropic recently released a blog post with the description of an experiment in which the last version of Opus, the 4.6, was instructed to write a C compiler in Rust, in a “clean room” setup. The experiment methodology left me dubious about the kind of point they wanted to make. Why not provide the agent with the ISA documentation? Why Rust? Writing a C compiler is exactly a giant graph manipulation exercise: the kind of program that is harder to write in Rust. Also, in a clean room experiment, the agent should have access to all the information about well established computer science…
Some Thoughts About Claude Code (opens on the source site)
Claude code is a powerful AI toolset that runs right in your terminal. While providing a lot of impressive utility, it also suffers from the issues that arise from similar AI toolings with the addition of an expensive pricing model. Context is Important To me, the main selling point for Claude Code is its ability to read through your entire codebase; a big shortcoming of many AI workflows is the model only partially understanding an issue due to it not having enough of the project's context and convention to be effective. Claude Code has the ability to access all of the files in the directory…
Using Claude Code with Google Sheets (opens on the source site)
Let’s get Claude Code to connect to Google Sheets. We’ll use this Google Sample Spreadsheet. Go to the Google Cloud Console, create a new project, and enable the Google Sheets API on it. Install the Google Cloud CLI. brew install google-cloud-sdk Choose the newly created project on the command line. ~$ gcloud config set project gsheetscli Updated property [core/project]. Login again, but this time enable Google Drive access. gcloud auth login --enable-gdrive-access You can now access the spreadsheet with curl. curl -H "Authorization: Bearer $(gcloud auth print-access-token)" \…
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.