Practical knowledge about AI, smart home and QA.https://quality-blog.eu/en-ushttps://quality-blog.eu/en/blog/llm-everyday-life-board-games/https://quality-blog.eu/en/blog/llm-everyday-life-board-games/An LLM can be a very practical helper during board games: explaining rules, resolving ambiguities, searching rulebooks, creating turn summaries, and keeping house rules consistent. The condition is simple: treat it as an assistant, not an infallible judge.Fri, 12 Jun 2026 00:00:00 GMTJulia Sielska & Grzegorz Holakaillmchatgptclaudeboard gamesproductivityhttps://quality-blog.eu/en/blog/why-not-skip-qa-in-projects/https://quality-blog.eu/en/blog/why-not-skip-qa-in-projects/QA isn't an add-on. Skipping quality assurance leads to delays, bugs, chaos and lost user trust. Here's why it almost never pays off.Thu, 11 Jun 2026 00:00:00 GMTGrzegorz Holakqaqualityprocessteamhttps://quality-blog.eu/en/blog/goal-claude-code-session-target/https://quality-blog.eu/en/blog/goal-claude-code-session-target/How /goal in Claude Code enforces completion through a session-scoped Stop hook. Pros, cons, when to use it, how to phrase the condition, and why it matters for QA.Wed, 10 Jun 2026 00:00:00 GMTGrzegorz Holakclaude-codeaiworkflowqahttps://quality-blog.eu/en/blog/issues-per-release-code-maturity-metric/https://quality-blog.eu/en/blog/issues-per-release-code-maturity-metric/How to roll out Issues per Release from scratch, why it's a metric of the development process and not just QA, and how it reshapes the conversation with the Engineering Manager. Article 4 of 9.Tue, 09 Jun 2026 00:00:00 GMTFilip Barszczqametricsleadershipreportinghttps://quality-blog.eu/en/blog/ai-smart-home-llm-vision/https://quality-blog.eu/en/blog/ai-smart-home-llm-vision/The first part of a mini-series about connecting AI with smart home systems. We move from simple motion detection to visual interpretation: who is at the gate, what happened on the driveway, and when a notification is actually worth sending.Mon, 08 Jun 2026 00:00:00 GMTJulia Sielska & Grzegorz Holakaismart homehome assistantllm visioncomputer visionhttps://quality-blog.eu/en/blog/holak-scale-where-it-fails/https://quality-blog.eu/en/blog/holak-scale-where-it-fails/Every model is a tool, not a truth. Six places where the Holak Scale actually fails when working with teams, plus reader feedback to address in version 3.Fri, 05 Jun 2026 00:00:00 GMTGrzegorz Holak & Konrad Gomulskiaiadoptionholak-scaleself-criticismhttps://quality-blog.eu/en/blog/multi-agent-orchestration-when-one-agent-is-enough/https://quality-blog.eu/en/blog/multi-agent-orchestration-when-one-agent-is-enough/Level 10 on the Holak Scale is attractive for a CV, expensive to maintain. A skeptical take on agent teams: when you actually need many, when one well-configured agent wins, and how to spot orchestrating mediocrity.Wed, 03 Jun 2026 00:00:00 GMTGrzegorz Holakaiagentsclaude-codeholak-scaleorchestrationhttps://quality-blog.eu/en/blog/escaped-bugs-problems-full-spectrum/https://quality-blog.eu/en/blog/escaped-bugs-problems-full-spectrum/Bugs in the code are only part of the story. The full taxonomy of escaped problems - code, infrastructure, configuration, integrations, regressions - the cost of each type and how to measure it. Article 3 of 9.Tue, 02 Jun 2026 00:00:00 GMTFilip Barszczqametricsleadershipreportinghttps://quality-blog.eu/en/blog/mcp-when-it-helps-when-overengineering/https://quality-blog.eu/en/blog/mcp-when-it-helps-when-overengineering/MCP is a tool, not a status. Each connector is maintenance, risk and attack surface. Criteria for when MCP pays off, when CLI / slash command / hook is better, a decision tree, and the CLI → MCP migration path.Mon, 01 Jun 2026 00:00:00 GMTGrzegorz Holakaimcpcliclaude-codetoolingholak-scalehttps://quality-blog.eu/en/blog/agents-md-claude-md-cursorrules-comparison/https://quality-blog.eu/en/blog/agents-md-claude-md-cursorrules-comparison/Three context-file formats for AI agents aren't chaos - each has a niche. What each agent reads, what to put in each, how to keep them in sync, and what not to copy 1:1.Fri, 29 May 2026 00:00:00 GMTGrzegorz Holakaiagents-mdclaude-codeholak-scalecontexthttps://quality-blog.eu/en/blog/prompt-library-anti-pattern/https://quality-blog.eu/en/blog/prompt-library-anti-pattern/If you copy prompts from a document, you have a phase-4 problem, not a phase-3 one. Why prompt fetishism is a symptom of stalled evolution, and how to break a 200-line prompt down into custom instructions and project context.Thu, 28 May 2026 00:00:00 GMTGrzegorz Holakaiprompt-engineeringholak-scaleanti-patternshttps://quality-blog.eu/en/blog/ai-maturity-individual-vs-organisation/https://quality-blog.eu/en/blog/ai-maturity-individual-vs-organisation/Most companies measure the maximum instead of the median. How to detect a gap between individual and organisational maturity, how to compute the median, and what to actually do if you're a level-9 engineer in a level-2 company.Wed, 27 May 2026 00:00:00 GMTGrzegorz Holakaiadoptionholak-scaleteamsgovernancehttps://quality-blog.eu/en/blog/defect-detection-ratio-measure-qa-effectiveness/https://quality-blog.eu/en/blog/defect-detection-ratio-measure-qa-effectiveness/A deep guide to Defect Detection Ratio - basic and weighted formula, interpretation thresholds, historical data, seasonality, three traps and ready-to-use lines for the boardroom.Tue, 26 May 2026 00:00:00 GMTFilip Barszczqametricsleadershipddrhttps://quality-blog.eu/en/blog/ai-adoption-anti-patterns/https://quality-blog.eu/en/blog/ai-adoption-anti-patterns/Most teams don't get stuck because of missing tools - they get stuck on specific patterns of thinking. The seven most common anti-patterns from the Holak Scale, a recognition test, who gets caught, and how to get out.Mon, 25 May 2026 00:00:00 GMTKonrad Gomulski & Grzegorz Holakaiadoptionholak-scaleanti-patternsteamshttps://quality-blog.eu/en/blog/trust-boundary-from-8-to-9/https://quality-blog.eu/en/blog/trust-boundary-from-8-to-9/The hardest jump on the Holak Scale isn't technical. Verifiability and reversibility as a framework, a readiness checklist, and two case studies - one team that made it, one that dropped back to 2.Fri, 22 May 2026 00:00:00 GMTGrzegorz Holakaiagentsadoptionholak-scalegovernancehttps://quality-blog.eu/en/blog/ai-maturity-diagnosis-30-minutes/https://quality-blog.eu/en/blog/ai-maturity-diagnosis-30-minutes/A concrete protocol for scoring a team on the Holak Scale - 8 calibration questions, 5 minutes of live observation and a one-page report. No surveys, no workshops, no slides.Thu, 21 May 2026 00:00:00 GMTGrzegorz Holakaiadoptiondiagnosisteamsholak-scalehttps://quality-blog.eu/en/blog/claude-codex-cli-vs-desktop-vs-web/https://quality-blog.eu/en/blog/claude-codex-cli-vs-desktop-vs-web/Three access channels to the same models differ in what they can touch. A practical comparison of Claude Code and Codex CLI against desktop apps and web interfaces.Wed, 20 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codecodextoolsworkflowhttps://quality-blog.eu/en/blog/qa-metrics-business-wants-to-hear/https://quality-blog.eu/en/blog/qa-metrics-business-wants-to-hear/A complete guide to transforming QA reporting - from counting bugs to speaking the language of outcomes and business decisions. Five metrics, three pillars, one model.Tue, 19 May 2026 00:00:00 GMTFilip Barszczqametricsleadershipreportinghttps://quality-blog.eu/en/blog/holak-scale/https://quality-blog.eu/en/blog/holak-scale/12 maturity levels of AI in the workplace - from resistance, through agent workflows, to a purpose-built agentic OS for concrete business outcomes. Version v2.1e splits the enterprise path from the private one.Mon, 18 May 2026 00:00:00 GMTGrzegorz Holak & Konrad Gomulskiaiadoptionenterprisestrategygovernancehttps://quality-blog.eu/en/blog/holak-scale-private/https://quality-blog.eu/en/blog/holak-scale-private/12 maturity levels of everyday AI use - home, learning, finance, smart home, life organization. The private version of the Holak Scale, parallel to the enterprise track.Sun, 17 May 2026 00:00:00 GMTGrzegorz Holak & Konrad Gomulskiaiadoptionsmart-homeprivatehttps://quality-blog.eu/en/blog/custom-subagent-claude-code-example/https://quality-blog.eu/en/blog/custom-subagent-claude-code-example/Part two of the subagent series. We build a blog-post-writer agent from scratch - what to put in the frontmatter, how to write a description that actually triggers, and how to dodge two classic traps.Fri, 15 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codesubagentsautomationhttps://quality-blog.eu/en/blog/advisor-claude-code-second-opinion/https://quality-blog.eu/en/blog/advisor-claude-code-second-opinion/The advisor() tool forwards the full transcript to a stronger model and returns an opinion. When to call it before work, when NOT for every step, how not to turn it into endless consultation.Thu, 14 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codeadvisorworkflowhttps://quality-blog.eu/en/blog/prompt-master-skill-claude-code/https://quality-blog.eu/en/blog/prompt-master-skill-claude-code/Instead of writing prompts to Midjourney, Sora, Suno or Cursor by hand, you have a Claude Code skill that does it. How it works, where it won't replace knowing the target tool.Wed, 13 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codeskillpromptshttps://quality-blog.eu/en/blog/subagents-claude-code-what-and-why/https://quality-blog.eu/en/blog/subagents-claude-code-what-and-why/One Claude vs many specialists invoked through Agent. Why subagents, how Claude picks which one to use, when NOT to use them, and why this isn't 'one window with more context'.Tue, 12 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codesubagentsautomationhttps://quality-blog.eu/en/blog/zigbee-home-assistant-zha-z2m-separate-server/https://quality-blog.eu/en/blog/zigbee-home-assistant-zha-z2m-separate-server/Three real-world Zigbee deployments in HA: built-in ZHA, Zigbee2MQTT as an add-on, and Z2M+MQTT on a separate host. Failure isolation, MQTT attack surface, multi-coordinator, PoE coordinators.Mon, 11 May 2026 00:00:00 GMTGrzegorz Holaksmart-homehome-assistantzigbeezigbee2mqttzhamqtthttps://quality-blog.eu/en/blog/open-webui-frontend-for-local-llm/https://quality-blog.eu/en/blog/open-webui-frontend-for-local-llm/Local Ollama only gives you a CLI. LM Studio is single-user. Open WebUI is the missing piece: a ChatGPT-like UI with RAG, web search and tools - running in one Docker command.Fri, 08 May 2026 00:00:00 GMTGrzegorz Holakaillmollamaopen-webuiraglocal-modelshttps://quality-blog.eu/en/blog/llm-models-2026-mac-mini-m4/https://quality-blog.eu/en/blog/llm-models-2026-mac-mini-m4/A review of the current models worth pulling onto 16 GB unified memory: gpt-oss-20b, Gemma 4 e4b, Qwen3-Coder, Phi-4. What works, what doesn't, and why.Thu, 07 May 2026 00:00:00 GMTGrzegorz Holakaillmollamamodelscodinglocal-modelshttps://quality-blog.eu/en/blog/mac-mini-m4-local-llm-lm-studio-ollama/https://quality-blog.eu/en/blog/mac-mini-m4-local-llm-lm-studio-ollama/Does the cheapest M4 Mac make sense as a machine for local language models? Hardware reality check, LM Studio vs Ollama comparison, and where the sanity line is.Wed, 06 May 2026 00:00:00 GMTGrzegorz Holakaillmollamalm-studiomaclocal-modelshttps://quality-blog.eu/en/blog/context7-mcp-up-to-date-docs-llm/https://quality-blog.eu/en/blog/context7-mcp-up-to-date-docs-llm/How one small MCP solves the biggest pain of working with LLMs on code: stale library knowledge. Setup, real-world cases, limitations.Tue, 05 May 2026 00:00:00 GMTGrzegorz Holakaimcpclaude-codedocumentationtoolinghttps://quality-blog.eu/en/blog/caveman-plugin-tokens-ai/https://quality-blog.eu/en/blog/caveman-plugin-tokens-ai/How a Claude Code plugin that makes the model talk like a caveman changed my token bill - and which tasks it actually fits, which ones it quietly ruins.Mon, 04 May 2026 00:00:00 GMTGrzegorz Holakaiclaude-codetokenstoolingpluginshttps://quality-blog.eu/en/blog/skill-for-bug-reports-in-jira/https://quality-blog.eu/en/blog/skill-for-bug-reports-in-jira/How to build a skill that turns your „hey, something's broken on checkout” into a complete Jira ticket - with evidence, dedupe, and without polluting the project. No autopilot agent, a deliberate human confirm in the middle.Thu, 30 Apr 2026 00:00:00 GMTGrzegorz Holakaiqaagentsskillsmcpjirahttps://quality-blog.eu/en/blog/from-article-to-video-hyperframes/https://quality-blog.eu/en/blog/from-article-to-video-hyperframes/When a post deserves a thirty-second video explainer, how to build the script, and how to reuse the same material across five channels at once.Wed, 29 Apr 2026 00:00:00 GMTGrzegorz Holakaicontentvideohyperframeshttps://quality-blog.eu/en/blog/evaluating-agent-output/https://quality-blog.eu/en/blog/evaluating-agent-output/Five dimensions for evaluating agent output, a checklist you can walk in fifteen minutes, and situations where you just send the result back without a lengthy debate.Tue, 28 Apr 2026 00:00:00 GMTGrzegorz Holakaiqaagentsreviewhttps://quality-blog.eu/en/blog/hacs-in-home-assistant-os/https://quality-blog.eu/en/blog/hacs-in-home-assistant-os/Why HACS belongs in Home Assistant OS, what to watch out for, how to install it step by step, and what to enable first - an honest walkthrough.Mon, 27 Apr 2026 00:00:00 GMTGrzegorz Holaksmart-homehome-assistanthacshttps://quality-blog.eu/en/blog/10-ai-workflows-for-test-architect/https://quality-blog.eu/en/blog/10-ai-workflows-for-test-architect/Ten concrete workflows - from test strategy review to the decision not to automate - each deployable in a week and usable every day.Fri, 24 Apr 2026 00:00:00 GMTGrzegorz Holakaiqatest-architectworkflowshttps://quality-blog.eu/en/blog/first-mcp-for-qa-search-fetch/https://quality-blog.eu/en/blog/first-mcp-for-qa-search-fetch/How to start with MCP in QA from the simplest possible pair of tools - search and fetch over evidence. No autonomy, no loops, just a structure you can maintain.Thu, 23 Apr 2026 00:00:00 GMTGrzegorz Holakaiqaagentsmcpevidencehttps://quality-blog.eu/en/blog/agents-md-for-test-automation/https://quality-blog.eu/en/blog/agents-md-for-test-automation/What to put in AGENTS.md for a test automation repo, common pitfalls, templates for Playwright, Cypress, and API tests, and how to tell if the file actually helps.Wed, 22 Apr 2026 00:00:00 GMTGrzegorz Holakaiqaagentsagents-mdtest-automationhttps://quality-blog.eu/en/blog/zwave-zigbee-wifi-matter/https://quality-blog.eu/en/blog/zwave-zigbee-wifi-matter/Four protocols, one decision. When Wi-Fi is enough, when Zigbee still wins, who actually needs Z-Wave, and what Matter-over-Thread really changes.Tue, 21 Apr 2026 00:00:00 GMTGrzegorz Holaksmart-homezigbeezwavematterthreadwifihttps://quality-blog.eu/en/blog/ai-glossary-for-testers/https://quality-blog.eu/en/blog/ai-glossary-for-testers/Five concepts that get confused most often in QA conversations about AI - plus a simple decision model for what to use when.Sun, 19 Apr 2026 00:00:00 GMTGrzegorz Holakaiqaagentsmcphttps://quality-blog.eu/en/blog/ai-maturity-model/https://quality-blog.eu/en/blog/ai-maturity-model/From resistance to orchestration - 11 levels of AI utilisation in an organisation. Find out where you and your team stand.Wed, 15 Apr 2026 00:00:00 GMTGrzegorz Holakaiadoptionteamshttps://quality-blog.eu/en/blog/home-assistant-2026/https://quality-blog.eu/en/blog/home-assistant-2026/A complete beginner's guide - from choosing hardware to your first automation.Sun, 12 Apr 2026 00:00:00 GMTGrzegorz Holaksmart-homehome-assistanthttps://quality-blog.eu/en/blog/ai-prompts/https://quality-blog.eu/en/blog/ai-prompts/Proven prompt engineering techniques you can apply right away.Wed, 08 Apr 2026 00:00:00 GMTGrzegorz Holakaiprompt-engineering