I gave AI agents a harm budget instead of trust and ran 19 experiments
I run Xonta, a small marketplace where developers list AI agents with a description and a price. Pretty soon people looking at the listings started…
Testing & QA
⚑ Сообщить о проблемеПоследние новости Testing & QA от Tech News
Все темы
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
95% recall, 80% answers: what LongMemEval retrieval scores don't tell you
Memory layers for AI agents love to quote LongMemEval. You will see 94%, 95%, 96%. Those numbers are real, but they usually measure retrieval: was o…
Замена Lens, которую целиком написала модель: что получилось и где мы проигрываем
Sextant — бесплатный open-source клиент Kubernetes на Rust и Tauri 2: всё, что вы делали в Lens, но без аккаунта, подписки и телеметрии. Его код цел…
Pin baseUrl in the Gateway, Not in the Agent's Prompt
The other day an agent I was testing kept hitting production. Not on purpose, not because it was being clever. It was reading the OpenAPI spec we ha…
Я пустил ИИ-агента на рабочий кластер 1С. Он нашёл 119 ГБ srvinfo, бэкап-призрак и не нашёл тормозов
«Утром никто не может зайти: начало сеанса запрещено». «Пользователь ушёл домой ещё вчера, а его сеанс до сих пор висит и держит лицензию». «rphost…
Triglav: orchestrating Claude Code and Codex agents for long-running work and layered review
AI coding agents can write code. Longer tasks still need coordination and quality control. Someone has to keep track of the objective, settle the op…
An agent timeout is not a cancelled action: building Mothership
An agent asks to save a report. The request needs your approval. You step away, the client times out, and the server restarts. When you return, shou…
Building a Google Merchant Center MCP server: what the Merchant API doesn't tell you
I run GSC Wizard , an SEO tool with an MCP server that already exposed Search Console and GA4 to Claude and ChatGPT. This month I added Google Merch…
Deploying MCP Servers on Kubernetes
Most MCP servers start life as a local, stdio-based process — the client spawns the server as a child process, messages flow over stdin and stdout.…
AI Growth Engine Competitor Website Watch Agent: Architecture, Tool Schemas & Integration Guide
Why conversational agent prompts fail in production—and the exact typed tool schemas, MCP servers, and dry-run safeguards required for Grok Bot Arch…
11 MCP Servers That Prove MCP Isn't Dead
Disclosure: I'm the founder of PDFHaul, which is #5 on this list. Originally published on the PDFHaul blog , where the full source list with links l…
REA Hit 248K Stars. The Real Story Is Scarier.
REA Hit 248K Stars. The Real Story Is Scarier. A week ago, morluto/rea had fewer than 10,000 GitHub stars. Today it has over 248,000 — making it one…
A list of MCP servers (100 active ones), and why your agent needs a list, not ten pages
Ask an agent for "every MCP server on GitHub with more than 500 stars that was pushed to in the last month" and watch what happens. It searches. It…
I built a tiny MCP notes server in Python — here's the whole thing, free
Most MCP (Model Context Protocol) examples are either toy "hello world" servers or sprawling frameworks. I wanted the smallest useful thing: a notes…
I built dot-mcp: it gives ChatGPT a computer (shell, files, memory, browser)
I'm the author of dot-mcp, an open-source MCP server written in Python. You install it with pip install dot-mcp , and it runs on your own machine. I…
A web crawler for AI agents with no LLM in the crawl loop
When an AI agent needs an answer that lives a few clicks deep on a website, there are two common ways to get it. Dump everything. A crawler fetches…
Give your AI agent a brand: on-brand images from Claude or Cursor via MCP
AI-assisted draft. I wrote and verified the setup against the current Brandiseer MCP endpoint and developer docs. Disclosure: I work on Brandiseer.…
Red Flags in the Ledger - hf26 Challenge
TinyGuard AI — Simple AI Powered Expense Anomaly Detector This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Wh…
From a URL to Markdown: a first collection and MCP setup with DeepSFetch
I'm building DeepSFetch, a hosted service for collecting web content and connecting it to applications and AI tools. We have published a developer k…
Connect Claude Code to an Anti-Detect Browser over MCP: Setup, Tools and Guardrails
Veilus runs many browser profiles on one computer, each with its own fingerprint, cookies and proxy. It also ships an MCP server, so an AI assistant…
A Developer's Tour of IP99: Free IP Lookup, pDNS, CT and an MCP Endpoint in One Place
If you've ever needed to answer "where is this IP, and is it acting like a proxy right now?", you've probably used several tools to do it: one for g…
Claude Code's hook matcher mcp__lab fired 0 times in 42 calls, though the same string worked as a permission rule
Across 14 headless runs of Claude Code 2.1.289, a hook whose matcher was the server prefix mcp__lab fired 0 times in 42 calls to that server's tools…
From 22 to 23: Evasion Detection, Elicitation, and 231 New Tests
In my last post , I walked through the architecture of AegisGate MCP — a standalone MCP server framework with 22 security layers, zero external Go d…
Sharing agent memory across machines without a server (or merge conflicts)
We run coding agents on more than one machine — a workstation, a laptop, a small server — and they kept forgetting things when we switched hosts. Ch…
Hotel MCPs Test
Building AI travel products, finding a hotel data source is a persistent problem. Integrate an OTA and the barrier is high with heavy commission. Bu…
Stop the read-then-exfiltrate chain: session taint for AI agents
Most AI agent incidents people worry about are not one bad tool call. They are two ordinary ones in a row. The agent reads a file. Maybe it is .env…
MCP Security: Where to Put the Authorization Boundary
An MCP tool call passes through the model, the client, possibly a proxy, and the server before anything happens. Only one of those places sees every…
People Are Already Using Obsidian as Their Agent's Memory. Here's the Production Version.
A post this week walks through using Obsidian plus Claude Code as a shared memory stack the author actually runs. Not a thought experiment. Develope…
One memory across AI agents: what it actually takes
The memory built into a coding agent lives inside that vendor's tools. What I tell one agent stays with that agent, and the next one I open in the s…
The Agentic AI Foundation's Standards Stack: MCP, A2A, and Goose
The Agentic AI Foundation is building a standards stack to solve a problem most teams hit after their first agent proof-of-concept: how do you wire…