AI Referrals Are Small, but GA4 May Miss How AI Shapes Buying Decisions
GA4 referral reports can make AI-assisted discovery look negligible. New analyses summarized by Marie...
Tutorials
Docs as Code with Confluence
Documentation drifts the moment it leaves the repository. The code gets a pull request, a review...
Por que os Guardrails não bastaram para limitar o escopo do meu chat com Amazon Bedrock
Criei um chat usando o Amazon Bedrock e percebi que Guardrails não bastam para limitar o escopo. Conto como usei o system prompt da Converse API, em Java, para manter o chat focado...
How I Built an Autonomous, Zero-Hallucination Micro-AI on an Entry-Level 4GB GPU
Inside the Astrocyte-Neuron architecture: Combining Ampere CUDA Tensor Cores, SymPy exact math, AST syntax self-repair, and 4-tier persistent SQLite memory on an NVIDIA RTX 2050.
Run Your Coding Agent in a Container With an Egress Allowlist, Not the Open Internet
A devcontainer, a default-deny iptables allowlist for your registry and model API, read-only secrets, and a test that proves curl to an unknown host fails.
Plan Stamping, for Software
Other professions worked out what a signature has to mean. We're about to need their answer. A few...
Why a Search API Is Often the Wrong Abstraction for AI Agents
If you've built an AI agent that uses web search, you've probably run into this. You ask it a simple...
How I Added WebMCP to a Collaborative Sheet Music Editor
"Rewrite these two bars, then let me hear them." That is a reasonable request to make while working...
Building Scalable Webhooks with Cloudflare Workers
Handling webhooks at scale presents a unique set of engineering challenges. When a third-party...
The FDE Mindset Shift: From Code Craftsmanship to Organizational Rewiring
The FDE Mindset Shift: From Code Craftsmanship to Organizational Rewiring TLDR: The...
Hands-On AI Security: Blue Teaming and Building the Security Gateway
Construct an external security gateway in Flask to inspect incoming prompts, enforce guardrails, and...
vLLM 0.33 Adds a Lossy Speculative Verifier: Why Single-Run Accuracy Tables Cannot Tell You It Is Safe
vLLM 0.33 ships FLy, an opt-in lossy speculative decoding verifier. Speedups, why the accuracy tables prove little, and a paired gate you can run.
I built an MCP tool and the agent never called it. Here's what worked instead.
Every codebase has rules nobody wrote down. One package always checks rows.Err() after iterating....
How to run multiple coding agents in parallel without them fighting
Four coding agents in one repository is not four times the work. What actually breaks (shared checkouts, invented progress, no independent check) and the three things that fix it.
Your AI observability needs your agents' memory, not just their traces
Originally published on the Cloud ex Machina engineering blog. We run our AI coding agents on a...
LLMJacking Turns Stolen Cloud Credentials Into a Resale Market for Model Access
TL;DR LLMJacking is the theft of access to a commercial language model, through a cloud...
Fine-tuning is the wrong tool for knowledge: three training phases and the low-rank shortcut
Originally published at cchinchilla.dev. Part 10 of From code to weights, a 12-part series on ML...
Claude Code wrote almost all of my app. My job turned into saying no.
Three weeks ago I started a desktop app. Since then: 169 commits, about 48,000 lines in src/, and I...
We instrumented Claude Code for our team. Here's what the data showed
AI coding only started paying off for my team when we stopped treating it as a tool everyone uses...
Your Claude Code allowlist is wider than you think: building an auditor for the rules you forgot you wrote
Every Claude Code user has the same file, and nobody reads it. settings.json accumulates permission...
We gave 6 AI coding CLIs the same concurrency bug and 6 hidden tests. All six passed. The diffs did not agree.
Arguments about which AI coding CLI is "best" usually rest on vibes or on synthetic leaderboards. So...
How I Used Switch to Build an AI Playtest Team for Board Games
If you design board games, you know the problem. A bad rule can hide for months, because getting...
I built EDITH so AI agents can remember bad API purchases
During a Mainnet test, I paid 0.001 SUI for an API response that contained nothing useful. The API...
I thought Claude Code would make my work lighter. I became its checker instead. Here's every file I wrote to stop
I thought handing work to Claude Code would make my days lighter. I build and sell WordPress plugins...