Hashnode

Anthropic says 90% of its code is now written by AI. Microsoft and Google are at 25–30% and climbing. The part that didn't make the headline: the bugs are climbing too. 📈 The 2026 reports are blunt. 43% of AI-generated changes still need debugging in prod, after they passed QA and staging. Incidents per merged PR are running about 3x the pre-AI baseline. We're writing code faster than ever. We're shipping bugs faster too. And the one role meant to catch them is the one nobody owns. Open any mature codebase and you'll find a test that's been skipped for months. A TODO sits above it. Whoever wrote the TODO doesn't work here anymore. QA is everyone's responsibility, which means it's no one's job. So the suite rots. One skipped check, one "we'll fix the flake later," and the team trains itself to scroll past red. Then something breaks in prod that a test you already wrote would have caught. It was just turned off. This isn't a tooling problem. It's an ownership problem. And AI just made it 3x more expensive. Most teams can't justify a full-time QA hire. So we built the owner instead. Bug0's engineers run your coverage end to end: planning, writing, triage, keeping it green. Passmark, our open-source engine, does the heavy lifting underneath. https://lnkd.in/gpUu5gm7 How it actually works: 1. Steps are written in plain English and compiled to Playwright. Every passing step is cached, so runs stay fast, cheap, and deterministic. When the UI changes and a step breaks, the model re-resolves it against intent and re-caches it. That's the healing. No brittle selectors to maintain. 2. Assertions never trust one model. Claude and Gemini each judge them, and a third breaks ties. We check against the video of the run, not just the final DOM, so a success toast that flashes for half a second still counts. 3. Then a human reviews every run and decides what's a real bug. The engine gives leverage. The engineer gives judgment. That second half is the 43% the tools keep missing. Passmark is closing in on 1,000 stars 🌟, the fastest-growing AI Playwright library on GitHub. 100% coverage in four weeks. 0% flake. Less than the cost of one QA hire. The AI writes the code now. Someone still has to own whether it works.

Running a model on every browser action: 4 to 8 seconds of latency per step, $0.02 to $0.05 in tokens. At 50 steps across 200 tests per nightly run, that's $200 to $500 a night just in inference. Across environments and branches, the bill exceeds the QA hire it was supposed to replace. Every AI testing tool faces the same paradox. The LLM is what makes it work. The LLM is also what makes it economically impossible. A cheaper model doesn't fix this. A different architecture does. One where the LLM isn't on the hot path. We've been building toward this for 9 months. The Bug0 core is now open source as Passmark (https://lnkd.in/gpUu5gm7, 800+ ⭐). Three primitives: 1. Cache-first execution. The first successful run resolves an action and caches it in Redis. Every subsequent run replays from cache. Zero AI calls until something breaks. 2. Auto-heal on cache miss. When a cached action fails because the DOM drifted or the UI got refactored, the AI re-resolves and updates the cache. The test self-repairs. 3. Multi-model consensus on assertions. A single model hallucinates. So we run Claude and Gemini in parallel. If they agree, the assertion ships. If they disagree, an arbiter model decides. Hallucination becomes a probability you design around. You don't wait for a vendor to solve it for you. There's a fourth piece. For the small fraction of steps that need pixel-level reasoning (sliders, canvases, drag-and-drop) you can flip to OpenAI's computer-use agent for that one step. Cheap snapshot path and expensive visual path inside a single test. Most tools force you to pick one upfront. The principle: the LLM is a coprocessor, not a CPU. Every browser testing tool will converge on this. The ones that don't won't survive a budget review next year. Bug0 is a forward-deployed engineering team running on top of Passmark. We embed senior engineers with you, bring the infra (the executor, the caching layer, the model orchestration), and own the outcome. 100% coverage of your critical user flows in weeks, not months. The suite, the maintenance, the on-call: all on us. If you're the engineering leader who'll own this decision in the next 12 months and want to walk through the architecture, not the sales pitch, that's bug0.com/join-pilot.

Shipped passmark 1.0.14 today. We kept hitting the same problem: screenshots are great for static UI, but they completely miss the stuff that flashes and disappears. Toast notifications, snackbars, transient error states - the agent would take a screenshot a half-second too late and the assertion would silently pass (or fail) for the wrong reason. So, we added video assertions. Set `video: true` on any assertion in runSteps, and passmark records the full test execution, and evaluates the assertion against the entire recording. The model sees everything that happened, not just one frame. A few details:  - Recording spans the whole runSteps call  - Local file is deleted after the model consumes it  - Default dir is /tmp/passmark-recordings, override via configure({ videoDir })  - As of now, we call gemini under the hood. So, you need to set `GOOGLE_GENERATIVE_AI_API_KEY` if you want to use video assertions. This was unblocked by page.screencast API landing in Playwright 1.59. Big thanks to the playwright team. If you're writing e2e tests using Passmark and always wondered if your assertions are silently missing the toast that flashes for 1s, then this update is for you. https://passmark.dev

Hiring 5 full-stack engineers and 1 experienced lead delivery head at Bug0. In the next 5 days. Skills: - Proficient in JS/TS, Node.js. (React/Next is a plus) - Playwright is a must. - Must know how to use Claude Code/Codex and other AI coding tools. Only apply if you're familiar with the stack above. Only apply if you can join immediately. Experience: - Full-stack engineer: Fresher/1-2 years of experience - Lead delivery head: 2-3 years of experience Location: - India only Perks: - Generous AI credits of top LLMs - Fully remote - Remote work desk setup - Work at a high-growth startup fazle[at]bug0.ai Reposts appreciated 🙏

🎉 passmark@1.0.9 now supports CUA mode! Until now, passmark drove the browser through ARIA accessibility snapshots - fast and reliable when the DOM is well-structured, but it can struggle with canvas-heavy apps, custom elements, or markup that doesn't expose a clean a11y tree. After working with a lot of customers, we realized that the winning combo is ARIA snapshot + CUA.                                                                                                             In CUA mode, the agent sees screenshots, clicks coordinates, and types like a human - powered by the new OpenAI gpt-5.5.    Snapshot mode is still the default and what we recommend for most flows. CUA is the escape hatch for when the accessibility tree isn't enough. One flag to switch: configure({ ai: { mode: "cua" } }); Requires an OPENAI_API_KEY. Would love feedback from anyone testing flows that snapshot-based agents have trouble with. Passmark is OSS. Check it out and contribute: https://lnkd.in/gbG7HrSu Shout-out to Ipseeta Priyadarshini for the PR!

passmark is so close to 500 stars… check out the most stable and reliable open-source AI regression testing library built on Playwright by the Bug0 team built for QA and engineering teams https://lnkd.in/gpUu5gm7

We just launched browsers.bug0.com. It lets you spin up cloud browsers instantly for automation, testing, and agentic workflows. I'm excited about how well this fits with our open-source tools: - Passmark for AI-powered regression testing / automation - Bug0 browsers for browser infrastructure that scales Put together, you get a much simpler stack to automate browser tasks end to end - from tests, to repetitive workflows, to full agent-driven actions. The goal is straightforward: make browser automation feel easy again. Try it here: https://browsers.bug0.com