ИИ-агент 4 месяца дежурит на наших прод-логах: 113 алертов, 2 галлюцинации и фикс за 3,5 часа
Пользователи почти не сообщают о багах: напишет 1 из 0, остальные молча уйдут. На прод-логи мы посадили автономного ИИ-агента: 300 тысяч строк в сутки…
Testing & QA
⚑ Report a ProblemLatest Testing & QA news from Tech News
All topics
agents
ai
api
architecture
automation
aws
backend
beginners
career
claude
cybersecurity
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Building a Production-Safe AI Remediation Firewall for Amazon EKS
A reproducible multi-AZ resilience walkthrough: spread a service across simulated zones, kill one under load, and measure the dropped requests — plus …
Why Must AIOps Move from Processing Alerts to Understanding Business Service Relationships?
The alerts have been processed, but the business problem remains A critical business system begins responding slowly, and the monitoring environment i…
I Spent a Week Fixing the Wrong Skill (And Other Lessons from Evaluating an AI PR Reviewer)
TLDR The baseline model (Claude Opus, no guidance) already catches ~65% of textbook bugs. The plugin's value comes from false positive suppression and…
Evaluating Kimi 2.5 vs Kimi 2.6: What happens to agent skills when the model gets smarter?
When a stronger model ships, there are two questions every skill author should want answered, and evals are the only honest way to answer either: Whic…
How I Built an Autonomous Incident Investigation Agent That Reduced MTTR by 65%
Series: AI-Native SRE Table of Contents The Problem Every On-Call Engineer Knows What FRIDAY Does Architecture Overview Key Design Decisions The Tool-…
Introducing *beta* Remogram: forge facts for agents, without the workflow baggage
If you've ever pointed an AI coding agent at a pull request and watched it confidently merge based on a stale title, a truncated API response, or pros…
When the conclusion comes first
A sponsored benchmark is just an experiment with a sponsor. So read it like one. I read a lot of vendor benchmarks. Most are fine. They are marketing,…
Scarab Field Test #022 — Playwright Worker Response Header Hang
Target: microsoft/playwright Issue: microsoft/playwright#39948 Status: local patch prepared and validated Patch commit: 269228a88 — fix(chromium): res…
Turning OpenClaw Governance Into an Operating Layer
In my last article, I wrote about a practical lesson from end-to-end testing inside OpenClaw: proving that a command exists is not the same thing as p…
JaisCloud — A Free, Single-Binary AWS Emulator in Go
Why We Built JaisCloud — A Free, Single-Binary AWS Emulator in Go If you've ever tried to test AWS-dependent code locally, you've probably reached for…
I Injected Three Faults. The Agent Found All of Them.
Overview Let's get our hands dirty. This part covers the full setup and the actual demo: deploy PayLedger to both regions, wire up Route 53 failover, …
Runbooks Don't Investigate. AWS DevOps Agent Does.
Overview I finished the DR Toolkit thinking I had covered the important parts of disaster recovery: runbooks, RTO/RPO targets, post-mortems. Then I ma…