Как интегрировать нейросети в работу тестировщика
Эта статья основана на реальном опыте использования Claude в работе QA-инженера. Все оценки времени — практические, не теоретические. Рабо…
Testing & QA
⚑ Report a ProblemLatest Testing & QA news from Tech News
All topics
agents
ai
api
architecture
automation
aws
beginners
career
claude
cybersecurity
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
# Building a Confluence MCP Server for Claude Code: From Setup to Skills
Automate your Confluence workflow directly from Claude Code — publish pages, sync content, and upload images without leaving your terminal. GitHub: ht…
ИИ-агенты в автоматизации тестирования: собираем воркфлоу из скиллов, MCP и разных LLM
Привет! На связи команда QA Automation СВОЙ Тех . Сегодня мы хотим поднять тему, которая за последний год превратилась из хайпового «вайб-кодинга» в с…
The lesson, stated plainly
If you persist embeddings, you must persist the embedder. A vector index is only meaningful next to the exact model that produced it. It's an easy mis…
Building Production Multi-Agent Systems with Claude
Building Production Multi-Agent Systems with Claude Meta: Learn how to architect production-grade multi-agent systems using Claude API. Covers orchest…
Anthropic выпустили Fable 5 самую мощную AI в истории. Через 72 часа её заблокировали
Первый раз мы заговорили с другом о возможности симбиоза человека и машины где-то в 2018 году. Говорили о внедрении чипов в голову. Модернизация за сч…
Save 60-90% of Your Claude Code Tokens With Two Tools
TL;DR: Two tools cut Claude Code token usage at two different layers. RTK is a shell proxy that compresses command output before it ever reaches the c…
I built a dating site where the users are AI agents and the humans are the audience
The pitch is exactly that. The users are autonomous agents. Humans don't get profiles, don't swipe, don't message. They watch. The site is live at htt…
Two tiny Claude Code skills that fixed my two biggest agent problems
Two open-source skills for Claude Code. Each is a single prompt file, Apache-2.0, no dependencies. Repos at the bottom. Working with a coding agent, I…
Stop Burning Through Claude Tokens: Practical Tips Every Developer Should Know
Stop Burning Through Claude Tokens: Practical Tips Every Developer Should Know If you've integrated Claude into your workflow or your app, you've prob…
Claude Fable 5 lasted three days. Then the US government pulled it.
On Tuesday this week I was reading launch coverage that told me to try Claude Fable 5 soon. By Friday night it was gone. Not deprecated, not rate-limi…
The Paradox of Power: Why Anthropic Released and Then Restricted Claude Fable 5
On June 9, 2026, Anthropic released Claude Fable 5, which was described as the most capable AI model publicly available at the time. Within 72 hours, …
What I learned building a Claude Code plugin for MV3 Chrome extensions
Claude Code writes extension code fine. That was never the problem. Ask it for a content script that highlights matched text, or a background service …
The claude -p playbook for June 15 — rebuilding your AI workflows inside interactive sessions
On June 15, Claude's claude -p (headless mode) and the Agent SDK stop drawing from your subscription and move to a separate metered credit. If you've …
His Today Was Yesterday: a timezone bug, a blast radius, and what AI missed
I lead a multi-tenant booking platform where venues sell activities. There's a customer-facing website where users book them. On the main page we show…
Loopers, Robovacs and the Death of the /Prompt
A Weekend Gonzo Field Guide to /loop Engineering Another weekend piece of satire, devoid of real-life advice but stacked with enough cyberpop residue …
Linkloom - AIWebReader
LinkLoom A web scraping and content extraction toolkit for TypeScript/Bun. Pass a URL, get clean markdown. That's the core. But LinkLoom also handles …
Two unrelated Claude Code Opus 4.8 failures hit the same week: token burn and fabricated tool results
In late May 2026, operators running Claude Code on Opus 4.8 ( claude-opus-4-8 ) filed two structurally different failures within the same few days. On…
Anthropic’s Claude in 2026: When Frontier AI Stopped Being Just Software
In 2026, Claude stopped looking like a normal AI product and started looking like infrastructure. Anthropic’s latest models are no longer interesting …
The Claude Code hook that ended --no-verify commits forever
Here's a small thing that drove me up the wall using Claude Code on a real codebase. I have a pre-commit hook. It runs the linter and the type-checker…
MCP Apps vs OpenAI Apps SDK: are they competing standards?
If you have started building tools for AI chat hosts, you have probably hit the same fork in the road. There are two ways to add a user interface to a…
I watched an AI agent refactor 14 files, fix failing tests, and open a PR, while I was in a meeting. Here's what that actually means for us.
It was a Tuesday afternoon in March 2026. A senior engineer, let's call her Priya, was three slides into a quarterly planning meeting when her phone b…
Борьба с галлюцинациями и 27 часов работы: практический опыт тестирования калькулятора трудозатрат с помощью ИИ
Сразу честно, чтобы вы понимали, с кем имеете дело: я из тех душнил, которые закатывают глаза, когда в сотый раз слышат «а давайте это все сделает ней…
Claude Can Do All of This. Most People Have No Idea.
Claude can do a lot more than most people think. This guide covers all of it—where to find each feature, how to turn it on, and a prompt you can use i…
Токен-оптимизация агентов: на что уходит контекстное окно MCP
Чем больше задач берёт на себя агент, тем чаще он упирается не в качество модели, а в контекстное окно: туда нужно уместить инструкции, историю диалог…
How I Ship 10x Faster with Claude Code: The 5-Layer Workflow System
After 8 months of daily Claude Code use, I've distilled my workflow into a 5-layer system. Each layer builds on the previous one. Skip one, and the wh…
Diagnose Node.js CommonJS vs ESM Errors with Claude: A Copy-Paste Prompt Kit (ERR_REQUIRE_ESM, ERR_MODULE_NOT_FOUND)
By the end of this article you'll have a small Node.js script that pipes a module-resolution error ( ERR_REQUIRE_ESM , ERR_MODULE_NOT_FOUND , Cannot u…
Why everyone is talking about loop-engineering and how is it changing agentic ai workflows? Claude Code and Web Scraping examples
A couple of weeks ago I published a walkthrough of my agentic coding setup , the plan-first discipline, the four-agent team, the model routing, the CL…
PDLC 1.1: two things v1.0 got wrong about artifact shape
Three months after starting a project with PDLC, a team member asked a simple question: "What does the system look like right now?" There was no good …
Выпустили, но в наморднике: разбираем как Mythos стал Fable 5
Когда компания выпускает продукт, всё просто: построил — продал. Вышел новый айфон — он лежит на полке. Появилась нейросеть — вот вам API, пользуйтесь…