/ blog

All posts

We share knowledge about AI, smart home and QA. Claude Code, MCP, local LLMs, Home Assistant, prompt engineering and test automation - no paywalls, no marketing fluff.

01 Jul 29, 2026 9 min read

A Tester in Code Review: What You Can Contribute Even If You Don't Write Code Every Day

What a tester should look for in submitted changes, a checklist for your first reviews, and a plan for joining the process without stepping on developers' toes or slowing the team down.

qa code-review
Grzegorz Holak
02 Jul 27, 2026 9 min read

AI in Smart Home, Part 8: A Home That Keeps Watch - Cameras, Privacy, and Local Event Analysis

The eighth part of the AI in smart home mini-series. We assemble local monitoring: Frigate for detection, a vision model for event descriptions, Home Assistant for notifications - and we draw the privacy boundaries a camera should never cross.

ai smart home
Julia Sielska & Grzegorz Holak
03 Jul 24, 2026 9 min read

AI for Flaky Test Analysis: From CI Chaos to a List of Root Causes

A workflow where an agent collects CI run history, groups failures by error signatures, classifies the root causes of flaky tests, and sets the order of fixes.

ai qa
Grzegorz Holak
04 Jul 23, 2026 9 min read

Evals for Regular People: How Do You Know Your Prompt Works at All?

A minimal prompt evaluation process without a framework: a golden set of ten cases, binary criteria, an A/B comparison table, and three traps that ruin the measurement.

ai prompt-engineering
Grzegorz Holak
05 Jul 22, 2026 9 min read

Test Debt: How to Measure It, Show It to the Business, and Pay It Down Without Stopping the Team

An operational definition of test debt, six measurable signals, pricing in hours and risk, and a repayment strategy that does not require halting delivery for a fix-it sprint.

qa test-debt
Grzegorz Holak
06 Jul 21, 2026 15 min read

Argus and Hephaestus: Two AI Agent Teams, One Builds, One Inspects

How I built two teams of specialized subagents in Claude Code: Hephaestus delivers software, Argus hunts bugs. Roles, coordinators, how they cooperate, and when orchestration is overkill.

ai agents
Grzegorz Holak
07 Jul 20, 2026 9 min read

AI in Smart Home, Part 7: A Home That Plans - Energy Optimization with Forecasts

The seventh part of the AI in smart home mini-series. We build an energy planner: electricity prices, solar production forecasts, and the calendar as inputs, an LLM as a constrained planner, a decision log, and an honest profitability calculation.

ai smart home
Julia Sielska & Grzegorz Holak
08 Jul 17, 2026 10 min read

Back Up Home Assistant Before It's Too Late - a Step-by-Step Recovery Strategy

A complete Home Assistant backup strategy: automatic backups, off-device storage, encryption key handling and the restore test that tells you the truth about whether you have a backup at all.

smart-home home-assistant
Grzegorz Holak
09 Jul 16, 2026 9 min read

Context Engineering: Why Your Agent Gets Dumber in a Long Session

Three mechanisms of context degradation (lost in the middle, instruction dilution, growing cost) and four habits that keep the token budget under control: compacting, clean starts, subagents, and pointers instead of data.

ai context-engineering
Grzegorz Holak
10 Jul 15, 2026 9 min read

The Test Pyramid in 2026: What's Left of It After a Decade of Microservices and Agent-Written E2E

Which floors of the classic test pyramid still make sense, where the drawing plainly lies, and what a healthy test distribution looks like in a typical web project - no dogma, just heuristics.

qa testing
Grzegorz Holak
11 Jul 14, 2026 14 min read

3 anti-patterns that destroy QA credibility

The series finale. Overloaded dashboards, numbers without context and jargon at the table with business. Three sins of quality reporting, all practiced first-hand, and a way out of each. Article 9 of 9.

qa metrics
Filip Barszcz
12 Jul 13, 2026 9 min read

AI in Smart Home, Part 6: A Home That Notices - Anomaly Detection Instead of Fixed Thresholds

The sixth part of the AI in smart home mini-series. We teach the home to recognize deviations from its own baseline: from the statistics built into Home Assistant, through domain rules, to a language model acting as a periodic data analyst.

ai smart home
Julia Sielska & Grzegorz Holak
13 Jul 10, 2026 9 min read

An Agent Fixes E2E Tests: A Playwright + Claude Code Workflow Step by Step

How to build a workflow where an agent diagnoses failed e2e tests and opens a PR with a fix - plus the four agent mistake patterns you need to know before you trust it.

ai qa
Grzegorz Holak
14 Jul 9, 2026 9 min read

Hooks in Claude Code - the Deterministic Layer Your Agent Cannot Skip

What hooks are in Claude Code, how blocking actions with exit code 2 works, and four practical examples: blocking commits without tests, lint after every edit, a secrets guard, and session-start context.

ai claude-code
Grzegorz Holak
15 Jul 8, 2026 9 min read

Risk-Based Testing in Practice: How to Decide What NOT to Test

A simple impact-times-probability matrix, a real release walkthrough where half the scope shipped without tests, and how to communicate those decisions to the business.

qa risk
Grzegorz Holak
16 Jul 7, 2026 13 min read

Storytelling with metrics - how to turn a table into an argument

The same data can put a room to sleep or trigger a decision. The inverted-pyramid skeleton, techniques for translating numbers into business language, a narrative generator and four ready-made templates. Article 8 of 9.

qa metrics
Filip Barszcz
17 Jul 6, 2026 10 min read

AI in Smart Home, Part 5: A Home That Talks - A Voice Assistant with a Local LLM

The fifth part of the AI in smart home mini-series. We build a voice assistant on Home Assistant Assist with a local language model: the chain from wake word to speech synthesis, hardware choices, and an honest comparison with commercial assistants.

ai smart home
Julia Sielska & Grzegorz Holak
18 Jul 3, 2026 16 min read

Is it worth growing in QA if you 'already know how to test'?

Growth in QA isn't just automation. It's better understanding of the product, risk, technology, business and how a team works together.

qa growth
Grzegorz Holak
19 Jul 2, 2026 17 min read

Why QA can't stand still while the product and team move forward

Quality assurance must evolve with the product, the technology and the team. Here's why old QA approaches stop working as systems grow.

qa process
Grzegorz Holak
20 Jul 1, 2026 15 min read

Continuous growth in QA: curse, necessity, or real gain?

Continuous growth in QA can be a competitive edge - or a source of pressure and exhaustion. Here's how to grow deliberately, without chaos or burnout.

qa growth
Grzegorz Holak
21 Jun 30, 2026 16 min read

Release Confidence Score step by step

How to combine five QA metrics into a single decision indicator. Three calculation models - traffic light, weighted, with a disqualifier - an interactive calculator, and how the Confidence Score changes QA's position in the company. Article 7 of 9.

qa metrics
Filip Barszcz
22 Jun 29, 2026 13 min read

AI in Smart Home, Part 4: Is a Mini Smart Home Worth It on a Construction Site?

A smart home does not have to start after moving in. On a construction site, it can run in a mini version: tracking temperature and humidity, sending reports, detecting warning thresholds, combining sensor data with camera events, and helping document risks.

ai smart home
Julia Sielska & Grzegorz Holak
23 Jun 26, 2026 17 min read

Building Your Own AI Agents: From Personal Assistant to Specialist Team

How to build your own AI agents: from a single personal assistant to a team of specialized agents. A practical take on design, roles, and coordination, without magical thinking.

ai ai agents
Julia Sielska & Grzegorz Holak
24 Jun 25, 2026 16 min read

Why QA experience is more than years on a CV

QA experience isn't just tool knowledge. It's the ability to predict risk, ask the right questions, and recognise problems before they become bugs.

qa experience
Grzegorz Holak
25 Jun 24, 2026 11 min read

Self-learning AI: ai-slop.win - a free GenAI course built entirely by AI

Behind the self-ironic domain ai-slop.win sits a complete, free, anonymous GenAI and LLM course: six learning paths, over thirty modules, tests with safety gates, and a certificate. The whole thing was built by AI - under supervision, with requirements, code review, and tests.

ai self-learning
Grzegorz Holak
26 Jun 23, 2026 14 min read

Number of Releases - the context metric

Why the number of releases is the common denominator for every QA metric. How to normalize, the link to Deployment Frequency (DORA), and why 3 bugs across 2 releases is a crisis while 3 across 15 is a win. Article 6 of 9.

qa metrics
Filip Barszcz
27 Jun 22, 2026 9 min read

The Holak (and Gomulski) Scale 3.0 - fewer levels, more meaning

An update to the AI adoption maturity model, co-created with Konrad Gomulski. Version 3.0 simplifies the scale to five levels and stops treating a level as a label for a person - it moves the diagnosis onto a specific context: a task, a team, a process or an organisation.

ai adoption
Grzegorz Holak & Konrad Gomulski
28 Jun 22, 2026 13 min read

AI in Smart Home, Part 3: A Home That Shows What Matters - Dashboards Designed with AI

The third part of the AI in smart home mini-series. We use AI to design Home Assistant dashboards: from information architecture and view structure to cards, status summaries, technical dashboards, and readable labels.

ai smart home
Julia Sielska & Grzegorz Holak
29 Jun 19, 2026 11 min read

Prompt engineering in practice - images, video, Gemini, Veo, and ChatGPT Images without mythology

Prompt engineering for images and video without the mythology: how to think about prompts for Gemini, Imagen, Veo, and ChatGPT Images. The prompt as a specification of intent, not a magic spell.

ai prompt engineering
Julia Sielska & Grzegorz Holak
30 Jun 18, 2026 18 min read

When to automate tests, and when automation is a waste of time

Test automation isn't always the right answer. Here's when it's worth automating, what to leave manual, and how to make conscious QA decisions.

qa automation
Grzegorz Holak
31 Jun 17, 2026 11 min read

Ultracode and Dynamic Workflows in Claude Code - what they really change for QA, architects, and development teams

What Ultracode and Dynamic Workflows in Claude Code actually are: a workflow with phases and subagents instead of a linear chat. What it changes for QA, test architects, and teams - and the cost risks involved.

claude-code ai
Grzegorz Holak
32 Jun 16, 2026 14 min read

Escaped Bugs per Release - find the risky release

How to detect an escaped-bug spike in a single release, run a 5-question investigation and put prevention in place. Escaped per Release vs the overall Escaped Rate. Article 5 of 9.

qa metrics
Filip Barszcz
33 Jun 15, 2026 13 min read

AI in Smart Home, Part 2: A Home That Thinks in Scenarios - Automations with AI

The second part of the AI in smart home mini-series. We explore how to use language models to design, generate, review, and document Home Assistant automations - without giving them full control over the house.

ai smart home
Julia Sielska & Grzegorz Holak
34 Jun 12, 2026 9 min read

AI in Everyday Life: LLMs as Board Game Assistants

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.

ai llm
Julia Sielska & Grzegorz Holak
35 Jun 11, 2026 17 min read

Why skipping QA on a project almost always costs more than it seems

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.

qa quality
Grzegorz Holak
36 Jun 10, 2026 8 min read

The /goal command in Claude Code - a session contract that won't let the agent give up

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.

claude-code ai
Grzegorz Holak
37 Jun 9, 2026 14 min read

Issues per Release - a code-maturity gauge

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.

qa metrics
Filip Barszcz
38 Jun 8, 2026 13 min read

AI in Smart Home, Part 1: A Home That Can See - LLM Vision in Practice

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.

ai smart home
Julia Sielska & Grzegorz Holak
39 Jun 5, 2026 6 min read

Where the Holak Scale Fails - Self-Criticism

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.

ai adoption
Grzegorz Holak & Konrad Gomulski
40 Jun 3, 2026 8 min read

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.

ai agents
Grzegorz Holak
41 Jun 2, 2026 14 min read

Escaped Bugs and Problems - the full spectrum of what reaches production

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.

qa metrics
Filip Barszcz
42 Jun 1, 2026 13 min read

MCP, CLI or hook - which tool when, and when MCP is 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.

ai mcp
Grzegorz Holak
43 May 29, 2026 8 min read

AGENTS.md vs CLAUDE.md vs .cursorrules - Which Context File for What

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.

ai agents-md
Grzegorz Holak
44 May 28, 2026 7 min read

A Prompt Library Is an Anti-Pattern. Yes, the 200-Line One

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.

ai prompt-engineering
Grzegorz Holak
45 May 27, 2026 9 min read

Individual 9, Company 2 - What to Do About AI Maturity Gaps

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.

ai adoption
Grzegorz Holak
46 May 26, 2026 15 min read

Defect Detection Ratio - how to measure effectiveness before anything reaches production

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.

qa metrics
Filip Barszcz
47 May 25, 2026 8 min read

AI Adoption Anti-Patterns - 7 Ways to Get Stuck

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.

ai adoption
Konrad Gomulski & Grzegorz Holak
48 May 22, 2026 9 min read

The Trust Boundary - How to Actually Cross from 8 to 9 on the Holak Scale

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.

ai agents
Grzegorz Holak
49 May 21, 2026 10 min read

How to Diagnose a Team's AI Maturity in 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.

ai adoption
Grzegorz Holak
50 May 20, 2026 12 min read

Claude and Codex: CLI vs Desktop vs Web - Where You Actually Ship Work

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.

ai claude-code
Grzegorz Holak
51 May 19, 2026 12 min read

QA metrics the business actually 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.

qa metrics
Filip Barszcz
52 May 18, 2026 14 min read

Holak Scale v2.1e - enterprise. An AI adoption maturity model for organizations

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.

ai adoption
Grzegorz Holak & Konrad Gomulski
53 May 17, 2026 12 min read

Holak Scale v2.1p - private. Maturity of everyday AI use

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.

ai adoption
Grzegorz Holak & Konrad Gomulski
54 May 15, 2026 9 min read

Writing your own Claude Code subagent: frontmatter, prompt, deployment

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.

ai claude-code
Grzegorz Holak
55 May 14, 2026 7 min read

Advisor in Claude Code: a second opinion from a stronger model before you commit to a path

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.

ai claude-code
Grzegorz Holak
56 May 13, 2026 7 min read

The prompt-master skill in Claude Code: a prompt generator for other AI tools

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.

ai claude-code
Grzegorz Holak
57 May 12, 2026 7 min read

Subagents in Claude Code: why orchestrate instead of writing in one window

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'.

ai claude-code
Grzegorz Holak
58 May 11, 2026 10 min read

Zigbee in Home Assistant 2026: ZHA, Z2M Add-on, or Z2M on a 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.

smart-home home-assistant
Grzegorz Holak
59 May 8, 2026 10 min read

Open WebUI - a ChatGPT-like frontend for your 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.

ai llm
Grzegorz Holak
60 May 7, 2026 11 min read

Local LLM models in 2026 - what actually runs on a Mac mini M4 16 GB

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.

ai llm
Grzegorz Holak
61 May 6, 2026 10 min read

Mac mini M4 16 GB as a local LLM workstation - LM Studio vs 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.

ai llm
Grzegorz Holak
62 May 5, 2026 11 min read

Context7 - the MCP that gives your model up-to-date docs instead of six-month-old knowledge

How one small MCP solves the biggest pain of working with LLMs on code: stale library knowledge. Setup, real-world cases, limitations.

ai mcp
Grzegorz Holak
63 May 4, 2026 10 min read

Caveman - the plugin that cuts output tokens by 75% (and where it breaks)

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.

ai claude-code
Grzegorz Holak
64 Apr 30, 2026 11 min read

A skill for filing bugs in Jira through Atlassian MCP

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.

ai qa
Grzegorz Holak
65 Apr 29, 2026 9 min read

From article to video: HyperFrames for quality-blog.eu

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.

ai content
Grzegorz Holak
66 Apr 28, 2026 9 min read

How testers should evaluate 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.

ai qa
Grzegorz Holak
67 Apr 27, 2026 15 min read

HACS in Home Assistant OS - why, when it's worth it, and how to install it step by step

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.

smart-home home-assistant
Grzegorz Holak
68 Apr 24, 2026 9 min read

10 AI workflows that actually help a Test Architect

Ten concrete workflows - from test strategy review to the decision not to automate - each deployable in a week and usable every day.

ai qa
Grzegorz Holak
69 Apr 23, 2026 11 min read

First MCP for QA: search and fetch over evidence

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.

ai qa
Grzegorz Holak
70 Apr 22, 2026 9 min read

How to write AGENTS.md for a test automation repo

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.

ai qa
Grzegorz Holak
71 Apr 21, 2026 10 min read

Wi-Fi, Zigbee, Z-Wave or Thread with Matter? A practical 2026 pick

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.

smart-home zigbee
Grzegorz Holak
72 Apr 19, 2026 8 min read

Skills, tools, agents, MCP, AGENTS.md - a concept map for testers

Five concepts that get confused most often in QA conversations about AI - plus a simple decision model for what to use when.

ai qa
Grzegorz Holak
73 Apr 15, 2026 7 min read

AI Adoption Maturity Model

From resistance to orchestration - 11 levels of AI utilisation in an organisation. Find out where you and your team stand.

ai adoption
Grzegorz Holak
74 Apr 12, 2026 5 min read

Getting Started with Home Assistant in 2026

A complete beginner's guide - from choosing hardware to your first automation.

smart-home home-assistant
Grzegorz Holak
75 Apr 8, 2026 3 min read

5 Prompts That Will Change How You Work with AI

Proven prompt engineering techniques you can apply right away.

ai prompt-engineering
Grzegorz Holak