How do you let an AI agent read Drupal data without misreading it?

Native Observability started as a way to look inside Drupal with a dashboard of its own: route timings, cache and slow queries, measured by the site and read by a person on an admin page. Now an AI agent reads the same data. Ask Claude Desktop "why is this page slow?" and it fetches the numbers through the Model Context Protocol, read-only.
Handing a model the numbers is not enough, though. It reads them with common sense, and on Drupal metrics common sense fails in specific places. In my first blind comparison, 4 answers out of 5 took a drop caused by the page cache for lost traffic, even with the right instructions in front of them.
Better instructions alone did not fix it. The site now computes the signals the model would get wrong, and explains the rest with a vocabulary checked sentence by sentence against the code. In the last round, with the vocabulary on, Claude reached the right conclusion in 30 answers out of 30.
What leaves the site follows a simpler rule than a list of forbidden words: route names go out, never a URL or a parameter value. This article covers the measurements, the mistakes I found along the way, the questions you can ask and what you need to connect an agent to your own site.
Why AI builds better and faster on the shoulders of giants

The best code your AI writes is the code it never has to write.
When building on top of Drupal there is luckily a lot of that.
Drupal's Role in Digital Sovereignty Beyond the CMS
What University Drupal Projects Reveal About the Limits of Vendor Independence
Benchmarking Drupal: Mitigating Synchronous Database Locking in High-Concurrency Environments
Drupal’s architecture provides a highly refined routing and rendering ecosystem. When deployed behind caching layers like Varnish or Redis, serving read-heavy content is a solved problem. However, engineering mission-critical platforms, such as SLA-backed procurement portals, ticketing engines, or high-volume transaction systems, requires shifting the architectural focus from read-heavy delivery to high-concurrency write stability.
When utilizing Drupal for state management or complex relational entity saves during peak traffic, default synchronous mechanisms become a critical bottleneck.
The Core Culprit: Synchronous Key-Value UpsertsIn a standard deployment, Drupal manages temporary data, system variables, and specific configurations through the State API. By default, this API utilizes the database-backed Key-Value store.
The architectural vulnerability lives directly inside \Drupal\Core\KeyValueStore\DatabaseStorage::doSet(), which handles the underlying database execution for the public set() method.
Goose 0.19: Watch Your Load Test While It Runs
Goose 0.19, the latest release of Tag1's open source load testing tool, lets you watch a load test in your browser while it runs. Response times, errors and active users update every second, so when a site starts to slow down you see it as it happens. Alongside it, goose-eggs 0.7 adds helpers for load testing WordPress and WooCommerce sites, and Goose itself can now fail a CI build when a site gets slower, keeps every response time to the microsecond, and runs in a quarter of the memory or less.
We compared Goose against k6 and Locust, all three in the same configuration of 1,000 users over HTTPS, running on the same two cores against the same web server. Goose sent 21,400 requests a second, against 15,800 for k6 and 8,400 for Locust, using less CPU per request than either and a fraction of the memory. The full results, and how we ran each tool, are found in this blog under the heading Compared with k6 and Locust.
An overview of what's new in Goose 0.19. Watch a Load Test in Your BrowserThere's no new code to write. Any Goose 0.19 load test gets the live web dashboard once you turn on the experimental dashboard feature in Cargo.toml:
Drupal and n8n integration: connect forms, content, and business systems
A Drupal n8n integration can send form submissions to a CRM, create Drupal drafts from approved content in other systems, and trigger downstream work after publication. Learn which modules and APIs to use and how to keep the workflows dependable. Inside the Drupal AI Demo: Testing the Northmoor University Site
Théodore Biadala on Building Drupack, Simplifying Drupal Hosting and What Comes Next
Hello World
Long overdue. Turns out building your own blog with your own product is a good way to find things to fix.
A look under the hood of how Drupal CMS 2.2 recipes speak your language too
Did you know that before Drupal CMS 2.2, if you set up Drupal CMS in German and applied a recipe, its content types, views and roles stayed in English? Recipes are a big part of how Drupal CMS delivers features, so this was a sizable hole in the multilingual experience. Until a few months ago, recipes could not even be translated on localize.drupal.org. So we did a few things to make this possible ahead of DrupalCon Rotterdam. Here are the details.
Gábor Hojtsy Wed, 11/04/2026 - 11:17Manufacturing Website Design: What the Fortune 500 Ships, and Where Drupal Fits
Drupal 10 end of life: upgrade to Drupal 11 before 9 December
Drush Deployment Hooks vs. Drupal Update Hooks: Choosing the Right Tool
Drupal deployments often involve more than deploying code and importing configuration. Sometimes we need to update existing content, migrate stored data, or perform operations that depend on newly deployed configuration.
Drupal provides update hooks for these tasks, but their execution order introduces an important limitation. Drush deployment hooks address that limitation by allowing code to run after configuration has been imported.
Understanding when each hook executes helps prevent deployment failures and makes updates more predictable.
Understanding Drupal's deployment sequenceThe drush deploy command provides a standardized deployment workflow. In current versions of Drush, the essential sequence is:
drush updatedb
drush config:import
drush cache:rebuild
drush deploy:hookThree types of hooks participate in this process:
HookExecutionPrimary purposehook_update_N()During updatedbDatabase schema and low-level updateshook_post_update_NAME()After update hooks, before config importEntity and data updates using Drupal APIshook_deploy_NAME()After config importOperations requiring newly deployed configurationThe distinction matters because Drupal's active configuration may be different at each stage of deployment.
From Malloc to Match (Part 2): The Evolution of PHP Through the Lens of a Systems Programmer
This is Part 2 of a two-part series. Part 1 traced PHP's evolution from a C library wrapper through Drupal 7, where the procedural model hit its ceiling. This part covers the Java-fication of Drupal, the engine-level work that saved PHP from itself, and what Drupal and PHP are getting right about performance now.
The year Drupal 8 development started, we were publishing Drupal Watchdog, a print magazine that we shipped to subscribers around the world. I mention this because the magazine's lifespan, 2011 through 2016, almost exactly tracks the development of Drupal 8. We started it because the Drupal ecosystem felt like it could sustain anything. By the time we wound it down, the community had been through the most disruptive transition in the project's history.
Elevating Multilingual Precision in Drupal 12: Configuration Language Consistency
Companies embrace multilingual functionalities to connect more deeply with global audiences. As an enterprise-level CMS, Drupal provides robust multilingual capabilities, making it simple to manage content, interface elements, and underlying configuration across multiple languages.
Why your Drupal bug backlog keeps growing: the triage bottleneck explained
A growing bug backlog rarely means that your Drupal platform suddenly has too many bugs. More often, it means that too much work enters the system without triage, ownership, approval, and protected capacity. That is where even a capable agency can get stuck. Node2Shell: Updating npm Packages Won’t Fix This Node.js Flaw
A Brotli decoder flaw in Node.js can lead to remote code execution. Updating npm packages doesn’t replace the runtime, so check the Node.js version wherever it runs: containers, build pipelines, a Drupal site’s decoupled front end, and DDEV.
Vibing Drupal - My Tips and Tricks for 10x Drupal Development using AI
Looking back on a year of AI experimentation, I want to document my tips and tricks for using AI with Drupal development. Early in this journey, after reading books like Beyond Vibe Coding, listening to the creator of Claude Code, and attending Drupal events, I saw and heard how people using AI dramatically increased their productivity.
I keep coming back to Kent Beck's quote: "The value of 90% of my skills just dropped to $0. The leverage for the remaining 10% went up 1000x. I need to recalibrate." It led me to conclude that my goal when using AI is to 10x my productivity by focusing on that remaining 10%: experience, judgment, and understanding of how Drupal works.
Here are my tips and tricks to 10x my productivity using the remaining 10% of my skills. I am highlighting those that can 2x productivity and lead you toward 10x and beyond.
Funny side note: when I asked AI to review this post, it was really unhappy that the 2x tips math didn't add up to 10x, but you get the goal of this post. My hope is that you'll scan or consume this list, take something away, and keep up with our fast-moving times.
AI
Models
I like the output and price of GPT-5.6 Luna. I’d heard that in Ultra mode it rivals the more expensive models, but when I tried it, the code was worse and it took longer.
Drupal User Session Control: Balancing Security and User Experience
To make sure your Drupal website security is as comprehensive as possible, you need to address a critical potential vulnerability: inactive or abandoned user sessions. Leaving them open may quietly create a back door for unauthorized access.
