# Browser Automation

Browser automation is the programmatic remote control of web browsers, commonly used by developers and testers to automate browser-based tests and tooling.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Browser Use blocked 100/100, and batch your Jev calls

DevFeed: [Browser Use blocked 100/100, and batch your Jev calls](<https://devfeed.tech/articles/browser-use-blocked-100-100-and-batch-your-jev-calls-137103.md>)

Original publisher: [Read original article](<https://jevdaily.com/issues/2026-11-16-w7>)

Author: Jev Weekly

Published: 2026-11-16T17:00:00Z

Content type: news

Language: en

Sources: [Jev Daily](<https://devfeed.tech/sources/jev-daily.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [also-on-the-timeline](<https://devfeed.tech/tags/also-on-the-timeline.md>), [api](<https://devfeed.tech/tags/api.md>), [autoresearch](<https://devfeed.tech/tags/autoresearch.md>), [batching](<https://devfeed.tech/tags/batching.md>), [browser](<https://devfeed.tech/tags/browser.md>), [built-with-it](<https://devfeed.tech/tags/built-with-it.md>), [bun](<https://devfeed.tech/tags/bun.md>), [captcha](<https://devfeed.tech/tags/captcha.md>), [captchas](<https://devfeed.tech/tags/captchas.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [decisions-api](<https://devfeed.tech/tags/decisions-api.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [detection](<https://devfeed.tech/tags/detection.md>), [editor](<https://devfeed.tech/tags/editor.md>), [fable-5](<https://devfeed.tech/tags/fable-5.md>), [gemini-decisions-api](<https://devfeed.tech/tags/gemini-decisions-api.md>), [hetzner](<https://devfeed.tech/tags/hetzner.md>), [ilias](<https://devfeed.tech/tags/ilias.md>), [jev](<https://devfeed.tech/tags/jev.md>), [someone-measured-it](<https://devfeed.tech/tags/someone-measured-it.md>), [the-case-against](<https://devfeed.tech/tags/the-case-against.md>), [writing-criteria](<https://devfeed.tech/tags/writing-criteria.md>)

### AI overview

A report says Browser Use was blocked in 100 of 100 separate runs, while another test blocked all 5 fresh Browser Use Cloud sessions on US residential proxies using solveCaptchas=true; rotate-image captchas remained unsolved after 120 seconds. Separately, Jev's input pricing charges for state once plus the questions, making parallel batching cheaper than sequential calls that resend state. An account of a self-hosted Postiz alternative describes a single Bun process with bun:sqlite WAL, 20 MCP tools across 27 providers, and $0 monthly cost on an existing Hetzner server. Other excerpted reports cover Gemini Decisions API pricing and benchmark claims, and a context-summary skill tuned to match its author's taste 80% of the time.

### Source excerpt

sahir says one bot gate blocked Browser Use on 100 of 100 separate runs, and Gregor Zunic agreed it got them 5/5 on his own attempt. The cheaper lesson of the...

## Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents

DevFeed: [Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents](<https://devfeed.tech/articles/whose-agent-are-you-multi-layer-fingerprinting-and-attribution-of-autonomous-web-agents-131938.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.20910>)

Author: Dayeon Kang, Hyejun Jeong, Jade Sheffey, Pubali Datta, Amir Houmansadr

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [TLS (Transport Layer Security)](<https://devfeed.tech/topics/tls.md>), [frontend security](<https://devfeed.tech/topics/frontend-security.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-web](<https://devfeed.tech/tags/ai-web.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [autogen](<https://devfeed.tech/tags/autogen.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [bot](<https://devfeed.tech/tags/bot.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsing](<https://devfeed.tech/tags/browsing.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [content](<https://devfeed.tech/tags/content.md>), [content-protection](<https://devfeed.tech/tags/content-protection.md>), [crawlers](<https://devfeed.tech/tags/crawlers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

The paper presents a multi-layer fingerprinting method to distinguish autonomous web agents from human visitors and traditional crawlers. A logging framework on an instrumented domain combines network characteristics, including TLS and HTTP behavior, with browser interaction patterns. Tested on AutoGen, Browser Use, Claude, Gemini, ChatGPT, and Skyvern, the features reveal differences in request construction, connection setup, and browser actions. A decision tree classifier reportedly achieved 100% accuracy in the study, identifying agent architectures and separating their traffic from human and legacy-crawler baselines. The authors propose cross-layer tracking as a way to support content protection and web security policy enforcement; the supplied abstract does not detail the evaluation conditions or limits of that accuracy result.

### Source excerpt

arXiv:2606.20910v2 Announce Type: replace-cross Abstract: As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and security challenge. Existing defenses, such as robots.txt and active bot-blocking, are insufficient, as they are widely violated and easily circumvented. In this work, we demonstrate that AI web agents can be effectively distinguished from humans and traditional crawlers using a multi-layer fingerprint based on both network layer characteristics (e.g., TLS, HTTP) and browser interaction behavior. We implement this mechanism as a programmatic logging framework that can be deployed on a live, instrumented domain. By analyzing six prominent agent frameworks (AutoGen, Browser Use, Claude, Gemini, ChatGPT, and Skyvern), we uncover latent structural differences in how these systems assemble HTTP requests, establish TLS/HTTP connections, and execute autonomous browser actions. Feeding these multi-layer features into a decision tree classifier, our framework achieves high-fidelity identification (100% accuracy), successfully isolating distinct agent architectures and differentiating agent traffic from both human browsing baselines and legacy crawlers. Our findings demonstrate that cross-layer agent tracking provides a robust approach to content protection and web security policy enforcement.

## Hitting hCaptcha in 2026: What Developers Can Still Use

DevFeed: [Hitting hCaptcha in 2026: What Developers Can Still Use](<https://devfeed.tech/articles/hitting-hcaptcha-in-2026-what-developers-can-still-use-123547.md>)

Original publisher: [Read original article](<https://hackernoon.com/hitting-hcaptcha-in-2026-what-developers-can-still-use?source=rss>)

Author: NoneCap

Published: 2026-11-09T05:54:35Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [good-company](<https://devfeed.tech/tags/good-company.md>), [hcaptcha](<https://devfeed.tech/tags/hcaptcha.md>), [hcaptcha-token](<https://devfeed.tech/tags/hcaptcha-token.md>), [node](<https://devfeed.tech/tags/node.md>), [nodejs](<https://devfeed.tech/tags/nodejs.md>), [nonecap-hcaptcha-solver](<https://devfeed.tech/tags/nonecap-hcaptcha-solver.md>), [python](<https://devfeed.tech/tags/python.md>), [scraper](<https://devfeed.tech/tags/scraper.md>), [test](<https://devfeed.tech/tags/test.md>), [test-automation](<https://devfeed.tech/tags/test-automation.md>), [token](<https://devfeed.tech/tags/token.md>), [web-scraping](<https://devfeed.tech/tags/web-scraping.md>)

### AI overview

For hCaptcha on an app you control, the excerpt recommends hCaptcha's test keys so end-to-end tests can pass without a solving service. For other sites, it describes token solving: read the sitekey and URL, request a token, then submit it through the response field or callback. Tokens are single-use and expire after about two minutes; some sites also require the submitting browser's User-Agent to match the solver's. NoneCap accepts Python or Node requests, supports invisible and enterprise sitekeys with rqdata, and does not charge for failed solves. Its wait parameter can return a 202 with a null token, requiring polling. The excerpt also says rejected tokens can be reported by solve ID, and existing 2Captcha or CapSolver-style clients can use compatibility endpoints with a NoneCap key. It reports that 2Captcha removed hCaptcha API documentation and CapSolver's page returned 404 around January 2025.

### Source excerpt

2Captcha and CapSolver stopped documenting hCaptcha in early 2025. How token-based solving fits a scraper or test suite, with Python and Node examples.

## WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

DevFeed: [WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis](<https://devfeed.tech/articles/worldcoder-bench-benchmarking-physically-grounded-3d-world-synthesis-124434.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.01869>)

Author: Shuo Lu, Yinuo Xu, Kecheng Yu, Siru Jiang, Yongcan Yu, Yubin Wang, Haitao Yang, Yuxiang Zhang, Bin Wang, Ran He, Jian Liang

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [application](<https://devfeed.tech/tags/application.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [browser](<https://devfeed.tech/tags/browser.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [execution](<https://devfeed.tech/tags/execution.md>), [fast](<https://devfeed.tech/tags/fast.md>), [generation](<https://devfeed.tech/tags/generation.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [integrate](<https://devfeed.tech/tags/integrate.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [language](<https://devfeed.tech/tags/language.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>)

### AI overview

WorldCoder-Bench evaluates whether language models can generate physically grounded, interactive 3D worlds, not just interfaces judged by pixels or DOM nodes. It contains 2,026 curated tasks spanning Simulation, Rendering, and Application scenarios, with optional .glb assets and hidden behavioral contracts. Its StateProbe protocol runs generated programs in a controlled browser and checks mutation-hardened contracts across runtime states and transitions. Across nine models, best verification coverage was 27.8% on WorldCoder-Benchcore; across five models, it was 19.9% on WorldCoder-Benchrob. Failures most often involved state-schema drift and broken interaction chains rather than missing scene elements. The reported Return on Automation and Time Efficiency Multiplier suggest cheaper or faster models can still offer value on easier domains.

### Source excerpt

arXiv:2606.01869v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language. Browser-native 3D, commonly built with Three.js, is a natural next frontier: generated programs must integrate assets, obey spatial and physical constraints, and keep user-facing controls synchronized with hidden runtime state. Existing web-generation benchmarks and evaluators, however, largely observe only pixels or DOM nodes, while the mechanics of a Three.js world unfold inside an opaque . We introduce WorldCoder-Bench, a benchmark for autonomous, physically grounded 3D world synthesis. WorldCoder-Bench contains 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, with optional .glb assets and hidden behavioral contracts. We further propose StateProbe, an execution-based protocol that probes generated programs in a controlled browser and verifies hidden, mutation-hardened contracts over runtime states and transitions. Beyond verification coverage, we report Return on Automation and Time Efficiency Multiplier to estimate quality-adjusted cost and time utility. The best verification coverage is 27.8% across nine models on WorldCoder-Benchcore and 19.9% across five on WorldCoder-Benchrob, with failures dominated by state-schema drift and broken interaction chains rather than missing scene elements. Utility metrics further show that cheap or fast models can still provide substantial value on easier domains. WorldCoder-Bench is available at https://github.com/shuolucs/WorldCoder-Bench.

## Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents

DevFeed: [Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents](<https://devfeed.tech/articles/broken-gates-re-evaluating-web-bot-defenses-in-the-age-of-llm-agents-122774.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.18659>)

Author: Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud, Dillan Bailey, Amin Kharraz

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Bot Management](<https://devfeed.tech/topics/bot-management.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [reCAPTCHA](<https://devfeed.tech/topics/recaptcha.md>), [Web](<https://devfeed.tech/topics/web.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bot-defenses](<https://devfeed.tech/tags/bot-defenses.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-agents](<https://devfeed.tech/tags/browser-agents.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [crawlers](<https://devfeed.tech/tags/crawlers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [identity](<https://devfeed.tech/tags/identity.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [model](<https://devfeed.tech/tags/model.md>), [recaptcha](<https://devfeed.tech/tags/recaptcha.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

In the authors' testbed, commercial solver services achieved 100% success against challenge-based defenses but averaged 23% on reCaptcha v3. LLM browser agents faced a different obstacle: verifier responses depended on browser and account state. An established consumer account and persistent Chrome state strongly affected reCaptcha v2/v3 acceptance, while Cloudflare Turnstile was more sensitive to the browser control path. Reconstructing an established browser environment let previously rejected agents pass without model retraining, and that environment transferred across tested agents and defenses without measurable defense-specific marginal cost. The findings highlight a tradeoff in non-interactive defenses: signals accessible to ordinary users can also be acquired, reproduced, and transferred for automated abuse. These conclusions are limited to the services, agents, and defenses evaluated.

### Source excerpt

arXiv:2607.18659v2 Announce Type: replace Abstract: The rapid emergence of web automation across commercial crawlers, solver services, and LLM-based browser agents has created new challenges for defenses that must distinguish legitimate automated activity from scalable abuse. In response, modern bot defenses increasingly replace explicit challenges with risk-based decisions over browser, session, identity, and behavioral signals. This paper explores how current automation stacks can bypass these defenses end-to-end, evaluating seven commercial solver services and eight LLM-based browser agents against four widely deployed defenses. We find that solver services largely defeat challenge-based defenses with a 100% success rate, but collapse to an average 23% success rate on reCaptcha v3. Browser agents encounter a different bottleneck: the browser and account state presented to the verifier. Controlled experiments across browser configurations show that an established consumer account and persistent Chrome state strongly affect reCaptcha v2/v3 acceptance in our deployments, whereas Cloudflare Turnstile exhibits substantially greater sensitivity to the agent's browser control path. Reconstructing the established browser environment enables previously rejected agents to pass without model retraining. Once established, this trusted environment transfers across the agents and defenses in our testbed, adding no measurable defense-specific marginal cost to the surrounding workflow. These results expose an inherent security tension in modern non-interactive defenses: to eliminate friction, the signals they trust must be accessible to everyday human users, yet this accessibility inherently guarantees that adversaries can acquire, reproduce, and transfer the same identity signals to scale automated abuse.

## 19 Agent Skills Test Your Web App With Playwright and Real Browsers

DevFeed: [19 Agent Skills Test Your Web App With Playwright and Real Browsers](<https://devfeed.tech/articles/19-agent-skills-test-your-web-app-with-playwright-and-real-browsers-122636.md>)

Original publisher: [Read original article](<https://hackernoon.com/19-agent-skills-test-your-web-app-with-playwright-and-real-browsers?source=rss>)

Author: Quality Assurance Career Development Resources

Published: 2026-11-08T16:00:02Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Playwright](<https://devfeed.tech/topics/playwright.md>)

Tags: [agent-browser](<https://devfeed.tech/tags/agent-browser.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [codex-cli](<https://devfeed.tech/tags/codex-cli.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [hackernoon](<https://devfeed.tech/tags/hackernoon.md>), [install](<https://devfeed.tech/tags/install.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [playwright-agent](<https://devfeed.tech/tags/playwright-agent.md>), [playwright-skill](<https://devfeed.tech/tags/playwright-skill.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [qa-testing](<https://devfeed.tech/tags/qa-testing.md>), [repo](<https://devfeed.tech/tags/repo.md>), [skills](<https://devfeed.tech/tags/skills.md>), [software-testing](<https://devfeed.tech/tags/software-testing.md>), [test](<https://devfeed.tech/tags/test.md>), [test-your-app-agent](<https://devfeed.tech/tags/test-your-app-agent.md>), [test-your-web-app-agent](<https://devfeed.tech/tags/test-your-web-app-agent.md>), [web-app](<https://devfeed.tech/tags/web-app.md>)

### AI overview

The 19 open-licensed QA skills guide AI agents to write tests, use a real browser to click through web app flows, and report failures. They are packaged in Cuttlefish.MD's QA & Testing plugin and follow the open Agent Skills standard, supporting Claude Code, Codex CLI, and 30+ other tools. Install the plugin with the provided marketplace commands, or copy the skills folder into a compatible agent's skills directory. Skills that use agent-browser require Vercel's agent-browser CLI. Each skill retains its license and attribution.

### Source excerpt

Nineteen open-licensed agent skills let an AI agent test a web app the way a person would: write the test first, open a real browser, & click through the flows.

## Automating Shadow DOM in Selenium WebDriver

DevFeed: [Automating Shadow DOM in Selenium WebDriver](<https://devfeed.tech/articles/automating-shadow-dom-in-selenium-webdriver-122666.md>)

Original publisher: [Read original article](<https://www.baeldung.com/selenium-webdriver-automate-shadow-dom>)

Author: baeldung

Published: 2026-11-08T13:20:05Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Selenium](<https://devfeed.tech/topics/selenium.md>), [Document Object Model (DOM)](<https://devfeed.tech/topics/dom.md>), [webDriver](<https://devfeed.tech/topics/webdriver.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [ui-testing](<https://devfeed.tech/topics/ui-testing.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [selectors](<https://devfeed.tech/topics/selectors.md>), [Front end](<https://devfeed.tech/topics/frontend.md>), [geckodriver](<https://devfeed.tech/topics/geckodriver.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [api](<https://devfeed.tech/tags/api.md>), [automation](<https://devfeed.tech/tags/automation.md>), [automation-tools](<https://devfeed.tech/tags/automation-tools.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [components](<https://devfeed.tech/tags/components.md>), [elements](<https://devfeed.tech/tags/elements.md>), [java-web](<https://devfeed.tech/tags/java-web.md>), [java-web-testing-javascript-selenium](<https://devfeed.tech/tags/java-web-testing-javascript-selenium.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [root](<https://devfeed.tech/tags/root.md>), [selenium](<https://devfeed.tech/tags/selenium.md>), [testing](<https://devfeed.tech/tags/testing.md>), [webdriver](<https://devfeed.tech/tags/webdriver.md>)

### AI overview

Selenium 4 accesses shadow DOM by locating a shadow host, calling getShadowRoot(), then querying within the returned SearchContext; ordinary driver.findElement() cannot cross the boundary, and XPath is unsupported for shadow roots and their children in the described ChromeDriver and GeckoDriver implementations. For older Selenium, JavaScriptExecutor can retrieve the root or target elements, including through nested roots, but longer scripts can be harder to diagnose, so the article favors reliability over request-count or speed gains. Behavior also varies by driver for closed roots: ChromeDriver allowed queries but reported elements as non-interactable, while GeckoDriver allowed access and interaction in the reported experiments. Keyboard navigation via Actions is offered as a potentially flaky workaround when direct closed-root access is unavailable. The example waits for page navigation but does not validate search results; Google may show a bot check.

### Source excerpt

Learn how to access shadow DOM elements with Selenium, understand shadow-root boundaries, and compare native WebDriver support with JavaScript-based approaches. The post Automating Shadow DOM in Selenium WebDriver first appeared on Baeldung.

## Leapwork Play Reaches GA with Governance for Playwright Tests

DevFeed: [Leapwork Play Reaches GA with Governance for Playwright Tests](<https://devfeed.tech/articles/leapwork-play-reaches-ga-with-governance-for-playwright-tests-119505.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/leapwork-play-playwright/>)

Author: Mark Silvester

Published: 2026-11-05T15:56:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Playwright](<https://devfeed.tech/topics/playwright.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [audit](<https://devfeed.tech/topics/audit.md>)

Tags: [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [audit](<https://devfeed.tech/tags/audit.md>), [automated-testing](<https://devfeed.tech/tags/automated-testing.md>), [continuous-delivery](<https://devfeed.tech/tags/continuous-delivery.md>), [continuous-integration](<https://devfeed.tech/tags/continuous-integration.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [governance](<https://devfeed.tech/tags/governance.md>), [leapwork](<https://devfeed.tech/tags/leapwork.md>), [leapwork-play-playwright](<https://devfeed.tech/tags/leapwork-play-playwright.md>), [news](<https://devfeed.tech/tags/news.md>), [play](<https://devfeed.tech/tags/play.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [portable](<https://devfeed.tech/tags/portable.md>), [tests](<https://devfeed.tech/tags/tests.md>), [traceability](<https://devfeed.tech/tags/traceability.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Leapwork Play reached general availability on September 30, 2026, adding governance around standard Playwright tests. Teams can import existing suites unchanged and run them in their CI pipelines or Leapwork's hosted service. Tests can be linked to requirements, tickets, or documents, with authoring history, approvals, and execution logs retained for review; role-based permissions and approval workflows manage who can create and run tests. Leapwork says connected Jira, Git, and product documentation provide context for generated tests, and repository changes can prompt suggested test updates. Its product page separately describes self-healing of broken test steps, but the sources do not explain approval or audit handling for locator repairs. Full governance, security, and audit capabilities require an enterprise package; availability of individual controls in the free tier is unspecified. Play's focus on cross-team provenance and approvals complements Playwright Trace Viewer's diagnostics for investigating individual runs.

### Source excerpt

Leapwork Play adds requirement traceability and approval workflows around portable Playwright tests. Full governance and audit capabilities require an enterprise package. By Mark Silvester

## Beyond the Landing Page: Website Blocking, Tracker Visibility, and Human Alignment in Automated Web Crawls

DevFeed: [Beyond the Landing Page: Website Blocking, Tracker Visibility, and Human Alignment in Automated Web Crawls](<https://devfeed.tech/articles/beyond-the-landing-page-website-blocking-tracker-visibility-and-human-alignment-in-automated-web-crawls-118704.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06197>)

Author: A H M Nazmus Sakib, Mahsin Bin Akram, Raveen Wijewickrama, Igor Bilogrevic, Murtuza Jadliwala

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Web Scraping](<https://devfeed.tech/topics/web-scraping.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [1-7](<https://devfeed.tech/tags/1-7.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automation](<https://devfeed.tech/tags/automation.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-automation](<https://devfeed.tech/tags/browser-automation.md>), [browsing](<https://devfeed.tech/tags/browsing.md>), [can](<https://devfeed.tech/tags/can.md>), [compare](<https://devfeed.tech/tags/compare.md>), [consent](<https://devfeed.tech/tags/consent.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [tracker](<https://devfeed.tech/tags/tracker.md>), [visibility](<https://devfeed.tech/tags/visibility.md>), [web](<https://devfeed.tech/tags/web.md>), [website](<https://devfeed.tech/tags/website.md>)

### AI overview

Across 2,000 popular websites, standard browser automation faced more denials beyond landing pages, while a detection-resistant framework largely prevented that increase without recording more tracking. On the same URLs, agentic crawlers recorded tracking from 1.5-1.7 times as many third-party organizations as non-agentic crawlers, especially on consent-managed pages. They captured 82-87% of tracker organizations seen by 26 participants, versus 58-68% for non-agentic crawlers, but about half of agentic crawlers' observations were absent from participant visits. The findings show that limiting website interventions, increasing tracker visibility, and matching human observations are distinct measurement goals; crawlers should be selected and validated accordingly.

### Source excerpt

arXiv:2611.06197v1 Announce Type: new Abstract: Web tracking studies largely rely on automated crawlers, yet their measurements can differ from what people encounter while browsing. Conventional crawlers follow predefined navigation rules, whereas LLM-driven agents decide how to navigate and interact with websites, potentially changing the tracking they encounter. We compare agentic and non-agentic crawlers to examine how websites respond to them, what tracking they record, and how closely their observations match human browsing. Across 2,000 popular websites, we evaluate different navigation strategies, automation frameworks, and stealth configurations, alongside browsing data from 26 participants. We find that website denials increase beyond landing pages for standard browser automation, while a detection-resistant automation framework largely prevents this escalation without increasing recorded tracking. On the same URLs, agentic crawlers record tracking activity from 1.5-1.7 times as many third-party organizations, particularly on consent-managed pages. Agentic crawlers recover 82-87% of tracker organizations observed by participants, compared with 58-68% for non-agentic crawlers, yet roughly half of their own observations are absent from human participant visits. These findings show that avoiding website interventions, increasing tracking visibility, and achieving closer agreement with human observations do not necessarily go hand in hand, highlighting the need to select and validate crawlers according to the measurement objective.

## Performance, Scalability and Maintenance: An Experimental Study of RPA vs. Autonomous Agents in the Healthcare Domain

DevFeed: [Performance, Scalability and Maintenance: An Experimental Study of RPA vs. Autonomous Agents in the Healthcare Domain](<https://devfeed.tech/articles/performance-scalability-and-maintenance-an-experimental-study-of-rpa-vs-autonomous-agents-in-the-healthcare-domain-116182.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03853>)

Author: Daniel Schulz, Pedro Cabral Buchaim, Bernardo Soares, Fernando Rafael Ensslin Schwengber, Lorenzo Farias, Daniela Duarte da Silva Bagatini, Ana Paula Wernz da Cunha M\\"uller

Published: 2026-11-04T05:00:00Z

Content type: comparison

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [information-systems](<https://devfeed.tech/tags/information-systems.md>), [interface](<https://devfeed.tech/tags/interface.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [legacy](<https://devfeed.tech/tags/legacy.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-scalability](<https://devfeed.tech/tags/performance-scalability.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [robotic-process-automation](<https://devfeed.tech/tags/robotic-process-automation.md>), [rpa](<https://devfeed.tech/tags/rpa.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [study](<https://devfeed.tech/tags/study.md>)

### AI overview

In this laboratory-portal study, Playwright RPA outperformed the APA agent setup on a stable interface: across two rounds, RPA achieved 98.90% accuracy and 98.27% F1, compared with APA's 96.49% and 94.48%. Both had 100% step success, but APA varied more over time. RPA took an average of 16.07 seconds per patient versus 207.21 seconds for APA and cost USD 0.030 versus USD 0.187 per report. The comparison used Playwright for RPA and browser-use, LangGraph, and Gemini 2.5 Flash-lite for APA; retrieved reports were treated only as informational artifacts.

### Source excerpt

arXiv:2611.03853v1 Announce Type: cross Abstract: Healthcare information systems are fragmented, and retrieving data from legacy web portals is a recurrent need. Robotic Process Automation (RPA) is deterministic but sensitive to interface changes, whereas autonomous agents based on large language models (Agent Process Automation, APA) promise adaptability at a higher computational cost. Following Design Science Research, we developed and compared an RPA solution (Playwright) and an APA solution (browser-use, LangGraph and Gemini 2.5 Flash-lite) to retrieve mammography and breast ultrasound reports from a laboratory portal, treating reports solely as informational artifacts. Across two rounds (T and T+7), RPA reached 98.90% accuracy and 98.27% F1-score versus 96.49% and 94.48% for APA, was about 13 times faster (16.07 s vs. 207.21 s per patient) and cost about six times less per report (USD 0.030 vs. 0.187). Both reached 100% step success rates; APA varied more over time. For a stable interface, RPA was superior.

## Verifying my web archives with Playwright

DevFeed: [Verifying my web archives with Playwright](<https://devfeed.tech/articles/verifying-my-web-archives-with-playwright-110763.md>)

Original publisher: [Read original article](<https://alexwlchan.net/2026/verifying-web-archives/>)

Published: 2026-11-01T14:11:41Z

Content type: tutorial

Language: en

Sources: [alexwlchan](<https://devfeed.tech/sources/alexwlchan.md>)

Topics: [Playwright](<https://devfeed.tech/topics/playwright.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [synthetic monitoring](<https://devfeed.tech/topics/synthetic-monitoring.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [archive](<https://devfeed.tech/tags/archive.md>), [assets](<https://devfeed.tech/tags/assets.md>), [audit](<https://devfeed.tech/tags/audit.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automated-testing](<https://devfeed.tech/tags/automated-testing.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [computers-and-code](<https://devfeed.tech/tags/computers-and-code.md>), [content-security-policy](<https://devfeed.tech/tags/content-security-policy.md>), [csp](<https://devfeed.tech/tags/csp.md>), [css](<https://devfeed.tech/tags/css.md>), [css-images](<https://devfeed.tech/tags/css-images.md>), [dark-mode](<https://devfeed.tech/tags/dark-mode.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [web](<https://devfeed.tech/tags/web.md>), [web-archiving](<https://devfeed.tech/tags/web-archiving.md>)

### AI overview

The author uses Playwright to check whether locally archived pages load without errors or external dependencies. The helper opens a fresh page, records requests, and fails on uncaught exceptions, console warnings or errors, non-GET requests, or external URLs; it also triggers reflow to catch some lazy-loaded images and fonts. Separate browser contexts can test settings such as light/dark mode, and the author also checks 1x/2x pixel densities, caching results because each run takes at least a second. This is best-effort: viewport choices, appearance settings, and interactions can reveal different assets, so multiple contexts or scripted actions improve coverage at a time cost. For the author's mostly simple, JavaScript-stripped pages, initial-load checks suffice. The same request auditing could be applied to CSP checks, login screens, or analytics flows.

### Source excerpt

I check my local web archive is self-contained by opening each page in Playwright, and checking the list of outgoing requests.

## GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at max effort

DevFeed: [GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at max effort](<https://devfeed.tech/articles/gpt-6-1-terra-vs-claude-opus-5-5-cheaper-and-faster-in-three-tests-at-max-effort-109950.md>)

Original publisher: [Read original article](<https://thenewstack.io/gpt-6-1-terra-vs-claude-opus-5-5/>)

Author: Jessica Wachtel

Published: 2026-10-31T14:00:00Z

Content type: comparison

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>)

Tags: [ai-models](<https://devfeed.tech/tags/ai-models.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [claude-opus-5](<https://devfeed.tech/tags/claude-opus-5.md>), [claude-opus-5-5](<https://devfeed.tech/tags/claude-opus-5-5.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [effort](<https://devfeed.tech/tags/effort.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-1](<https://devfeed.tech/tags/gpt-6-1.md>), [gpt-6-1-terra](<https://devfeed.tech/tags/gpt-6-1-terra.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [max](<https://devfeed.tech/tags/max.md>), [openai](<https://devfeed.tech/tags/openai.md>), [opus](<https://devfeed.tech/tags/opus.md>), [opus-5](<https://devfeed.tech/tags/opus-5.md>), [opus-5-5](<https://devfeed.tech/tags/opus-5-5.md>), [software-testing](<https://devfeed.tech/tags/software-testing.md>), [terra](<https://devfeed.tech/tags/terra.md>), [tests](<https://devfeed.tech/tags/tests.md>), [vs](<https://devfeed.tech/tags/vs.md>)

### AI overview

In the author's three final API runs at each vendor's max effort, GPT-6.1 Terra tied Claude Opus 5.5 on release triage, scored 48/50 versus 43.5/50 on synthetic cell tracking, and completed a 50-question CI data audit with 47/50 while Opus returned no final answer before its per-response output limit. Estimated uncached costs were $25.99 for Terra and $214.96 for Opus across the runs; Terra also finished sooner overall. The tests used different tasks from OpenAI's cited benchmarks, were run once after revisions, and max effort does not impose equivalent reasoning budgets. The author cautions that these results do not establish repeatability or a general model ranking; Terra also made errors on the large-table task.

### Source excerpt

OpenAI launched GPT-6.1 Terra on October 26, and included two direct comparisons with Opus 5.5 in its marketing materials. It The post GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at max effort appeared first on The New Stack.

## Daytona runs the code, Notte runs the browser

DevFeed: [Daytona runs the code, Notte runs the browser](<https://devfeed.tech/articles/daytona-runs-the-code-notte-runs-the-browser-109773.md>)

Original publisher: [Read original article](<https://www.daytona.io/dotfiles/daytona-runs-the-code-notte-runs-the-browser>)

Author: Lucas Giordano Co-founder; CTO; Notte

Published: 2026-10-30T00:00:00Z

Content type: article

Language: en

Sources: [Dotfiles Insider](<https://devfeed.tech/sources/dotfiles-insider.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Chromium](<https://devfeed.tech/topics/chromium.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Web app](<https://devfeed.tech/topics/webapp.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bot-detection](<https://devfeed.tech/tags/bot-detection.md>), [bot-protection](<https://devfeed.tech/tags/bot-protection.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-based-ide](<https://devfeed.tech/tags/browser-based-ide.md>), [browser-ide](<https://devfeed.tech/tags/browser-ide.md>), [captchas](<https://devfeed.tech/tags/captchas.md>), [cdp](<https://devfeed.tech/tags/cdp.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud-coding](<https://devfeed.tech/tags/cloud-coding.md>), [cloud-dev-environment](<https://devfeed.tech/tags/cloud-dev-environment.md>), [cloud-development-environment](<https://devfeed.tech/tags/cloud-development-environment.md>), [cloud-editor](<https://devfeed.tech/tags/cloud-editor.md>), [cloud-ide](<https://devfeed.tech/tags/cloud-ide.md>), [cloud-programming](<https://devfeed.tech/tags/cloud-programming.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [code](<https://devfeed.tech/tags/code.md>), [code-in-cloud](<https://devfeed.tech/tags/code-in-cloud.md>), [code-on-web](<https://devfeed.tech/tags/code-on-web.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-environment](<https://devfeed.tech/tags/coding-environment.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [cookies](<https://devfeed.tech/tags/cookies.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [guide](<https://devfeed.tech/tags/guide.md>), [here](<https://devfeed.tech/tags/here.md>), [ide-editor-online](<https://devfeed.tech/tags/ide-editor-online.md>), [ide-in-browser](<https://devfeed.tech/tags/ide-in-browser.md>), [ide-online](<https://devfeed.tech/tags/ide-online.md>), [online-code-editor](<https://devfeed.tech/tags/online-code-editor.md>), [online-ide](<https://devfeed.tech/tags/online-ide.md>), [online-programming](<https://devfeed.tech/tags/online-programming.md>), [online-web-dev-ide](<https://devfeed.tech/tags/online-web-dev-ide.md>), [online-web-development-ide](<https://devfeed.tech/tags/online-web-development-ide.md>), [sde](<https://devfeed.tech/tags/sde.md>), [standardised-development-environment](<https://devfeed.tech/tags/standardised-development-environment.md>), [stories-insights](<https://devfeed.tech/tags/stories-insights.md>), [web-based-coding](<https://devfeed.tech/tags/web-based-coding.md>), [web-ide](<https://devfeed.tech/tags/web-ide.md>)

### AI overview

Daytona's bundled Chromium is the simplest choice for testing an agent's app or browsing unprotected pages: it reaches sandbox localhost directly, but shares memory with the code. Five reference pages used about 600 MB; five news or shopping pages used 1,030-1,170 MB, for which the text recommends a 2 GiB sandbox. Notte runs the browser remotely, keeping sandbox use around 85-115 MB in the described runs and offering persistent login profiles, residential proxy routing, captcha solving, and session viewing and replay. The agent drives it through the Notte CLI or Playwright over CDP, which requires outbound access to Notte's API. For a sandbox app, Daytona's guide serves the app on a port, obtains a signed preview URL, then tests it with a Notte session; the remote browser needs no auth header for that URL. The guide requires Daytona and Notte API keys and the Notte CLI. The text describes this split as useful when agents both test their own apps and work with other sites.

### Source excerpt

Agents in Daytona sandboxes can run Chromium beside their code or use a Notte browser for bot checks, captchas and logins. A Daytona guide shows how.

## Bug0 Releases QA Agent to Automate Regression Testing With Cached Playwright Replays

DevFeed: [Bug0 Releases QA Agent to Automate Regression Testing With Cached Playwright Replays](<https://devfeed.tech/articles/bug0-releases-qa-agent-to-automate-regression-testing-with-cached-playwright-replays-106419.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/bug0-agent-testing-cached-replay/>)

Author: Bruno Couriol

Published: 2026-10-29T15:17:00Z

Content type: release

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Playwright](<https://devfeed.tech/topics/playwright.md>), [ui-testing](<https://devfeed.tech/topics/ui-testing.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [automate](<https://devfeed.tech/tags/automate.md>), [browser](<https://devfeed.tech/tags/browser.md>), [bug0-agent-testing-cached-replay](<https://devfeed.tech/tags/bug0-agent-testing-cached-replay.md>), [ci](<https://devfeed.tech/tags/ci.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [library](<https://devfeed.tech/tags/library.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [news](<https://devfeed.tech/tags/news.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [qa](<https://devfeed.tech/tags/qa.md>), [qa-agent](<https://devfeed.tech/tags/qa-agent.md>), [regression](<https://devfeed.tech/tags/regression.md>), [regression-testing](<https://devfeed.tech/tags/regression-testing.md>), [source](<https://devfeed.tech/tags/source.md>), [testing](<https://devfeed.tech/tags/testing.md>), [user-interface](<https://devfeed.tech/tags/user-interface.md>), [verification](<https://devfeed.tech/tags/verification.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

Bug0 QA Agent is a source-available Playwright library that combines natural-language test steps with cached browser actions. On the first run, its agent uses the accessibility tree and screenshots to perform requested actions; successful single-action steps are compiled into Playwright operations and cached in memory for faster replays. If a UI change breaks a replay, the cache is invalidated and the agent tries again. Complex multi-action steps are not cached and run through the agent each time. Assertions are also uncached: Claude and Gemini evaluate each one, with a third model resolving ties, and video models can check transient UI defects. The library supports disposable email testing through mailsink and community adapters to retrieve OTPs and magic links. The excerpt notes that autonomous testing remains limited by assertion verifiability and grounding, and that Bug0's Functional Source License 1.1 is source-available, with non-compete restrictions for the first two years.

### Source excerpt

QA Agent is a new source-available Playwright library for agentic browser regression testing. The agent associates test instructions expressed in natural language to actions on the user interface, caches those when appropriate for faster CI replays, remapping them to test specifications when the user interface changes. Verification is based on multi-model consensus and vision model evaluations. By Bruno Couriol

## 3 Ways AI Agents Already Operate in Your Browser

DevFeed: [3 Ways AI Agents Already Operate in Your Browser](<https://devfeed.tech/articles/3-ways-ai-agents-already-operate-in-your-browser-106423.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/3-ways-ai-agents-already-operate-in-your-browser/>)

Author: Sponsored by Keep Aware

Published: 2026-10-29T14:00:10Z

Content type: article

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [control](<https://devfeed.tech/tags/control.md>), [corporate](<https://devfeed.tech/tags/corporate.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [employees](<https://devfeed.tech/tags/employees.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [keep-aware](<https://devfeed.tech/tags/keep-aware.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [security](<https://devfeed.tech/tags/security.md>), [security-tools](<https://devfeed.tech/tags/security-tools.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [tools](<https://devfeed.tech/tags/tools.md>), [users](<https://devfeed.tech/tags/users.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

AI agents can operate in authenticated browsers through external control using Chrome DevTools Protocol (CDP), browser extensions or agentic browsers, and emerging website-exposed tools under WebMCP. CDP lets external applications control debuggable Chromium browsers, including tabs with corporate sessions. Extensions can read pages and interact with tabs using permissions such as scripting and debugger access; agentic browsers may fall outside existing extension controls. In both cases, actions may appear under the employee's identity, and agents can be influenced by instructions embedded in untrusted content. WebMCP lets agents invoke structured tools supplied by websites instead of interpreting pages and simulating clicks; its specification is evolving, and tool definitions can themselves be misleading or malicious. The article recommends organizations assess which agents and debuggable browsers can access corporate sessions, what data agents can send to website tools, and whether their activity is visible and controllable. It argues existing endpoint, network and application controls may not reveal what an agent reads or does inside an authenticated tab.

### Source excerpt

AI agents can control authenticated browsers, interact with corporate applications, and access sensitive data while appearing to act as legitimate employees. Keep Aware examines three ways agents operate inside browsers and why traditional security tools may struggle to distinguish their activity from human users. [...]

## Best Browser.lol Alternatives for Web Testing in 2026

DevFeed: [Best Browser.lol Alternatives for Web Testing in 2026](<https://devfeed.tech/articles/best-browser-lol-alternatives-for-web-testing-in-2026-107250.md>)

Original publisher: [Read original article](<https://testgrid.io/blog/browser-lol-alternatives/>)

Author: Yogesh Solanki

Published: 2026-10-29T11:44:38Z

Content type: comparison

Language: en

Sources: [TestGrid](<https://devfeed.tech/sources/testgrid-blog.md>)

Topics: [browser](<https://devfeed.tech/topics/browser.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>), [Firefox](<https://devfeed.tech/topics/firefox.md>), [Firefox extension](<https://devfeed.tech/topics/firefox-extension.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [staging](<https://devfeed.tech/topics/staging.md>), [Google Chrome](<https://devfeed.tech/topics/google-chrome.md>), [Edge](<https://devfeed.tech/topics/edge.md>), [Internet Explorer](<https://devfeed.tech/topics/internet-explorer.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [automated](<https://devfeed.tech/tags/automated.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [best](<https://devfeed.tech/tags/best.md>), [blog](<https://devfeed.tech/tags/blog.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-lol-alternatives](<https://devfeed.tech/tags/browser-lol-alternatives.md>), [can](<https://devfeed.tech/tags/can.md>), [cd](<https://devfeed.tech/tags/cd.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [ci-cd-pipeline](<https://devfeed.tech/tags/ci-cd-pipeline.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cross-browser-testing](<https://devfeed.tech/tags/cross-browser-testing.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [deployment-flexibility](<https://devfeed.tech/tags/deployment-flexibility.md>), [device](<https://devfeed.tech/tags/device.md>), [flexibility](<https://devfeed.tech/tags/flexibility.md>), [testing](<https://devfeed.tech/tags/testing.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

Browser.lol provides isolated remote browser sessions, but the text says its limited sessions and browser choices, beta saved profiles, and lack of broader testing features can constrain QA teams. The alternatives serve different needs: Kasm Workspaces and Cloudflare Browser Isolation focus on secure remote browsing; Multilogin, Sendwin, and Firefox Multi-Account Containers separate account profiles; Browserling supports live manual checks across desktop browsers; TestGrid offers cloud cross-browser and mobile testing, parallel runs, Selenium Grid, and CI/CD integrations; Steel and Browserless provide programmable browser infrastructure for automation and agents; Hyperbrowser supports prompt-driven web workflows and reusable session state. Tradeoffs named include setup or learning effort, performance issues, privacy risks, and costs. The text recommends choosing by testing coverage, automation, security, deployment, and budget, but provides no independent comparative test results.

### Source excerpt

Browser.lol can be a great platform for QA engineers and software testers who need quick access to isolated browser sessions to assess website behavior. However, Browser. lol lacks automated regression testing, broad real-device coverage, CI/CD pipeline integrations, persistent browser profiles, multi-browser testing, and deployment flexibility. In this blog, we'll look at the best alternatives to [...]

## Web-Perf Wednesday 015 - Failed Modulepreloads Need to Recover

DevFeed: [Web-Perf Wednesday 015 - Failed Modulepreloads Need to Recover](<https://devfeed.tech/articles/web-perf-wednesday-015-failed-modulepreloads-need-to-recover-105302.md>)

Original publisher: [Read original article](<https://csswizardry.com/2026/10/web-perf-wednesday-015-failed-modulepreloads-need-to-recover/>)

Author: Harry Roberts

Published: 2026-10-28T12:00:00Z

Content type: article

Language: en

Sources: [CSS Wizardry](<https://devfeed.tech/sources/css-wizardry.md>)

Topics: [WebKit](<https://devfeed.tech/topics/webkit.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Resilience](<https://devfeed.tech/topics/resilience.md>), [retry](<https://devfeed.tech/topics/retry.md>), [Firefox](<https://devfeed.tech/topics/firefox.md>), [webDriver](<https://devfeed.tech/topics/webdriver.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [HTML](<https://devfeed.tech/topics/html.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [caching](<https://devfeed.tech/tags/caching.md>), [failed](<https://devfeed.tech/tags/failed.md>), [failure](<https://devfeed.tech/tags/failure.md>), [faster](<https://devfeed.tech/tags/faster.md>), [firefox](<https://devfeed.tech/tags/firefox.md>), [import](<https://devfeed.tech/tags/import.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [perf](<https://devfeed.tech/tags/perf.md>), [performance](<https://devfeed.tech/tags/performance.md>), [recover](<https://devfeed.tech/tags/recover.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [safari](<https://devfeed.tech/tags/safari.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [webkit](<https://devfeed.tech/tags/webkit.md>)

### AI overview

Safari Technology Preview 255 fixes a WebKit recovery bug: when a `modulepreload` failed, a stale failed cache entry could make a later `import()` reject without another network request. The fix checks the error before preload shortcuts so the module can be requested again; the excerpt says this is in Technology Preview and does not confirm stable Safari availability. To verify recovery, fail a route chunk request once, restore it, then check both the import rejection and whether a later attempt sends another request. Also consider CDN and service-worker behavior, and avoid unbounded retries. The excerpt also reports corrected throttled response timings in Safari Web Inspector, a Firefox 159 WebDriver polling memory-leak fix affecting timed-out commands, and Mozilla's claim that its desktop PDF viewer starts up to 45% faster, without published test conditions.

### Source excerpt

WebKit fixes failed modulepreloads that could block recovery, while Safari and Firefox improve performance tooling and browser responsiveness.

## I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It

DevFeed: [I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It](<https://devfeed.tech/articles/i-broke-a-browser-agent-on-purpose-spotting-the-fault-was-not-the-same-as-fixing-it-102453.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/i-broke-a-browser-agent-on-purpose-spotting-the-fault-was-not-the-same-as-fixing-it/>)

Author: Abdullahi Dattijo

Published: 2026-10-27T15:30:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [browser](<https://devfeed.tech/topics/browser.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [browser](<https://devfeed.tech/tags/browser.md>), [clicks](<https://devfeed.tech/tags/clicks.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [first](<https://devfeed.tech/tags/first.md>), [half](<https://devfeed.tech/tags/half.md>), [i](<https://devfeed.tech/tags/i.md>), [inside](<https://devfeed.tech/tags/inside.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [llm-evaluation](<https://devfeed.tech/tags/llm-evaluation.md>), [model](<https://devfeed.tech/tags/model.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [simple](<https://devfeed.tech/tags/simple.md>)

### AI overview

A browser check can identify an action fault without enabling the agent to recover when the parser or executor keeps sending the same wrong action. In a small experiment, the author replayed 80 previously successful Claude Haiku 5.5 decisions through four deliberately broken browser paths. Generic page-state checks missed half of wrong clicks and falsely warned on every successful embedded-frame click; screenshot comparison found few corrupted searches and warned on every working search. Outcome checks, tailored to each requested result, detected all injected faults without false alarms in this setup. Yet retries through unchanged broken code still failed on searches and clicks. Checks helped when the agent could use new evidence: they prevented unnecessary frame clicks and prompted another chart observation, raising chart completion from 56/60 to 60/60, though the estimated gain ranged from 0 to 15 percentage points. The study used one simple site, one model and prompt, and 20 layouts for completion; its counts do not establish performance on other websites. The practical lesson is to log the model's request, image and viewport dimensions, action sent, target state, and resulting;

### Source excerpt

I replayed correct model decisions through four broken browser actions. A simple page check missed half of the wrong clicks, and raised a false alarm on every click that worked inside an embedded page. The post I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It appeared first on Towards Data Science.

## webframe: evaluated as a scraper and a sandbox

DevFeed: [webframe: evaluated as a scraper and a sandbox](<https://devfeed.tech/articles/webframe-evaluated-as-a-scraper-and-a-sandbox-101045.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Oct/26/webframe-evaluation/>)

Author: Simon Willison

Published: 2026-10-26T16:15:00Z

Content type: article

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [browser](<https://devfeed.tech/topics/browser.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [WebView2](<https://devfeed.tech/topics/webview2.md>), [console](<https://devfeed.tech/topics/console.md>), [Shell](<https://devfeed.tech/topics/shell.md>), [ClojureScript](<https://devfeed.tech/topics/clojurescript.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [browsers-108](<https://devfeed.tech/tags/browsers-108.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus-5-5](<https://devfeed.tech/tags/claude-opus-5-5.md>), [console](<https://devfeed.tech/tags/console.md>), [go](<https://devfeed.tech/tags/go.md>), [go-54](<https://devfeed.tech/tags/go-54.md>), [headless](<https://devfeed.tech/tags/headless.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [javascript-769](<https://devfeed.tech/tags/javascript-769.md>), [jeff-lindsay](<https://devfeed.tech/tags/jeff-lindsay.md>), [jeff-lindsay-4](<https://devfeed.tech/tags/jeff-lindsay-4.md>), [library](<https://devfeed.tech/tags/library.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [program](<https://devfeed.tech/tags/program.md>), [prototypes](<https://devfeed.tech/tags/prototypes.md>), [report](<https://devfeed.tech/tags/report.md>), [research](<https://devfeed.tech/tags/research.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [scraper](<https://devfeed.tech/tags/scraper.md>), [scraping](<https://devfeed.tech/tags/scraping.md>), [shot-scraper](<https://devfeed.tech/tags/shot-scraper.md>), [shot-scraper-72](<https://devfeed.tech/tags/shot-scraper-72.md>), [url](<https://devfeed.tech/tags/url.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

webframe runs a URL or local file in a hidden headless web view, sending `console.log()` output to standard output and exceptions to standard error. Written in Go on the glaze library, it uses the system browser--WKWebView on macOS, WebKitGTK on Linux, or WebView2 on Windows--so it does not bundle a browser engine. The excerpt compares it with shot-scraper JavaScript as a smaller tool without a Playwright dependency, but provides no results from the proposed sandboxing or scraping evaluation.

### Source excerpt

Research: webframe: evaluated as a scraper and a sandbox webframe is a neat little project from Jeff Lindsay which lets you "run a web page like a program" - you point it at a URL or file and it executes it in a hidden headless web view and outputs console.log() to standard output and any exceptions to standard error. It's written in Go on top of the glaze library, which provides access to a system browser ("WKWebView on macOS, WebKitGTK on Linux, WebView2 on Windows") so it doesn't need to bundle its own browser engine. It reminds me of my own shot-scraper javascript tool, albeit in a much smaller package that doesn't depend on Playwright. I had Claude Opus 5.5 put it through its paces and prepare a research report for me. Here's the prompt I used: Explore https://github.com/tractordev/webframe try running it and put it though its paces, build a few exploratory prototypes, then evaluate it as a potential sandboxing tool and as a tool for scraping web pages using the same patterns encouraged by the "shot-scraper JavaScript" command (see simonw/shot-scraper on GitHub, docs directory) Tags: browsers, go, javascript, jeff-lindsay, shot-scraper

## Building End-to-End Cypress Tests Across Browser, API, and Worker Boundaries

DevFeed: [Building End-to-End Cypress Tests Across Browser, API, and Worker Boundaries](<https://devfeed.tech/articles/building-end-to-end-cypress-tests-across-browser-api-and-worker-boundaries-96393.md>)

Original publisher: [Read original article](<https://hackernoon.com/building-end-to-end-cypress-tests-across-browser-api-and-worker-boundaries?source=rss>)

Author: Raju Dandigam

Published: 2026-10-22T18:20:13Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Cypress](<https://devfeed.tech/topics/cypress.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [API](<https://devfeed.tech/topics/api.md>), [Back end](<https://devfeed.tech/topics/backend.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [health check](<https://devfeed.tech/topics/health-check.md>), [hosting](<https://devfeed.tech/topics/hosting.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [api-testing](<https://devfeed.tech/tags/api-testing.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [audit](<https://devfeed.tech/tags/audit.md>), [backend](<https://devfeed.tech/tags/backend.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-security](<https://devfeed.tech/tags/browser-security.md>), [cypress](<https://devfeed.tech/tags/cypress.md>), [cypress-cy-request](<https://devfeed.tech/tags/cypress-cy-request.md>), [cypress-cy-session](<https://devfeed.tech/tags/cypress-cy-session.md>), [docker](<https://devfeed.tech/tags/docker.md>), [e2e](<https://devfeed.tech/tags/e2e.md>), [effects](<https://devfeed.tech/tags/effects.md>), [end-to-end-testing](<https://devfeed.tech/tags/end-to-end-testing.md>), [integration-testing](<https://devfeed.tech/tags/integration-testing.md>), [react-application-testing](<https://devfeed.tech/tags/react-application-testing.md>), [state](<https://devfeed.tech/tags/state.md>), [test-automation](<https://devfeed.tech/tags/test-automation.md>), [tests](<https://devfeed.tech/tags/tests.md>), [ui](<https://devfeed.tech/tags/ui.md>), [worker](<https://devfeed.tech/tags/worker.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

For consequential workflows, verify three outcomes: what the user saw, what the system committed, and which asynchronous side effect occurred. The refund example uses HTTP requests to create fixtures and establish a session, the browser to approve the refund, and API checks to confirm durable state and an audit event. Poll worker-produced events with a bounded retry window based on service expectations, and use correlation IDs to avoid matching another parallel test. For GraphQL, check HTTP status, response errors, and business data separately. `cy.request()` synchronizes cookies but bypasses browser CORS and cannot be observed with `cy.intercept()`, so it cannot prove frontend request behavior. A Docker Compose test stack can preserve separate app and worker boundaries and use health checks for readiness; pin the Cypress image. Keep test endpoints isolated or narrowly authorized. This pattern verifies only the selected workflow and side-effect sink; it does not replace contract, load, security, or monitoring tests.

### Source excerpt

Learn how to use Cypress to verify UI behavior, backend state, and asynchronous side effects so that passing tests reflect real workflow outcomes.

## How to Make Your Coding Agent Check Its Work in the Browser

DevFeed: [How to Make Your Coding Agent Check Its Work in the Browser](<https://devfeed.tech/articles/how-to-make-your-coding-agent-check-its-work-in-the-browser-91210.md>)

Original publisher: [Read original article](<https://www.freecodecamp.org/news/how-to-make-your-coding-agent-check-its-work-in-the-browser/>)

Author: timothy ogbemudia

Published: 2026-10-20T09:16:48Z

Content type: tutorial

Language: en

Sources: [Free Code Camp](<https://devfeed.tech/sources/freecodecamp-programming-tutorials-python-javascript-git-more.md>)

Topics: [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-automation](<https://devfeed.tech/tags/browser-automation.md>), [bug-fix](<https://devfeed.tech/tags/bug-fix.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [frontend-development](<https://devfeed.tech/tags/frontend-development.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [testing](<https://devfeed.tech/tags/testing.md>), [web-development](<https://devfeed.tech/tags/web-development.md>)

### AI overview

For user-facing changes, verify the behavior in a running browser: derive checks from the diff, inspect final states after actions and reloads, use DOM evidence for functional claims and screenshots for visual ones, and clean up only processes and artifacts started by the review. Playwright MCP gives an agent browser access, while a separate reviewer with no author conversation history can catch missed effects. The article's katalepsis tool turns verification into HTML, Markdown and JSON reports: `run` uses the project's Playwright results as final, while `verify` uses a model for plain-English checks but requires passing browser assertions showing a new visible result before recording a pass. Unreachable previews and other constrained runs are reported as blocked; failures remain distinct. The excerpt notes limits, including preview commit uncertainty, and recommends fallback browser review for checks katalepsis cannot yet handle.

### Source excerpt

I got tired of coding agents telling me the frontend work was done when nobody had opened the frontend. You've probably seen the routine. The agent changes some code, runs the formatter, the type chec

## Meet QA.tech: HackerNoon Company of the Week

DevFeed: [Meet QA.tech: HackerNoon Company of the Week](<https://devfeed.tech/articles/meet-qa-tech-hackernoon-company-of-the-week-90146.md>)

Original publisher: [Read original article](<https://hackernoon.com/meet-qatech-hackernoon-company-of-the-week?source=rss>)

Author: Company of the Week

Published: 2026-10-19T16:00:03Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agentic-testing](<https://devfeed.tech/tags/agentic-testing.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-development-workflow](<https://devfeed.tech/tags/ai-development-workflow.md>), [hackernoon-company-of-the-week](<https://devfeed.tech/tags/hackernoon-company-of-the-week.md>), [meet-qa-tech](<https://devfeed.tech/tags/meet-qa-tech.md>), [qa](<https://devfeed.tech/tags/qa.md>), [qa-tech](<https://devfeed.tech/tags/qa-tech.md>), [qa-tech-review](<https://devfeed.tech/tags/qa-tech-review.md>), [qa-testing](<https://devfeed.tech/tags/qa-testing.md>), [tech-companies](<https://devfeed.tech/tags/tech-companies.md>), [tech-company-news-pages](<https://devfeed.tech/tags/tech-company-news-pages.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

QA.tech is presented as an AI testing platform whose agents run end-to-end, regression, and pull-request tests on web and mobile apps from plain-language goals. The article argues that independent agents can verify pull requests through the running user interface, with testing depth adjusted to risk.

### Source excerpt

Meet QA.tech, an AI platform whose agents run end-to-end, regression, and PR tests on web and mobile apps from plain-language goals, no brittle scripts.

## Modern Web Automation With Python and Selenium

DevFeed: [Modern Web Automation With Python and Selenium](<https://devfeed.tech/articles/modern-web-automation-with-python-and-selenium-83960.md>)

Original publisher: [Read original article](<https://realpython.com/modern-web-automation-with-python-and-selenium/>)

Author: Martin Breuss

Published: 2026-10-09T14:00:00Z

Content type: tutorial

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [automated-testing](<https://devfeed.tech/tags/automated-testing.md>), [elements](<https://devfeed.tech/tags/elements.md>), [headless](<https://devfeed.tech/tags/headless.md>), [model](<https://devfeed.tech/tags/model.md>), [object](<https://devfeed.tech/tags/object.md>), [page-object](<https://devfeed.tech/tags/page-object.md>), [pattern](<https://devfeed.tech/tags/pattern.md>), [python](<https://devfeed.tech/tags/python.md>), [selenium](<https://devfeed.tech/tags/selenium.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

This tutorial shows how to automate a browser with Python and Selenium, including navigating dynamic web pages, locating and interacting with elements, handling waits, and organizing code with the Page Object Model. It applies these techniques to a command-line music player that controls tracks on Bandcamp's Discover page.

### Source excerpt

Automate the browser with Python and Selenium: headless browsing, interacting with web elements, and the Page Object Model pattern.

## Asana cuts model costs 76x in browser tests with GPT-6.1 Sol

DevFeed: [Asana cuts model costs 76x in browser tests with GPT-6.1 Sol](<https://devfeed.tech/articles/asana-cuts-model-costs-76x-in-browser-tests-with-gpt-6-1-sol-84371.md>)

Original publisher: [Read original article](<https://openai.com/index/asana-browser-agent>)

Published: 2026-10-09T07:00:00Z

Content type: news

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [asana](<https://devfeed.tech/tags/asana.md>), [astra](<https://devfeed.tech/tags/astra.md>), [browser](<https://devfeed.tech/tags/browser.md>), [codex](<https://devfeed.tech/tags/codex.md>), [costs](<https://devfeed.tech/tags/costs.md>), [customers](<https://devfeed.tech/tags/customers.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-1](<https://devfeed.tech/tags/gpt-6-1.md>), [gpt-6-1-sol](<https://devfeed.tech/tags/gpt-6-1-sol.md>), [gpt-6-astra](<https://devfeed.tech/tags/gpt-6-astra.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [offer](<https://devfeed.tech/tags/offer.md>), [sol](<https://devfeed.tech/tags/sol.md>), [tests](<https://devfeed.tech/tags/tests.md>), [using](<https://devfeed.tech/tags/using.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Asana reports that changes to StackAI's browser agent cut estimated model costs and runtime in its tests. In a 144-run study across GPT-6.1 Sol and three other frontier models, GPT-6 Astra in Codex tested larger browsing-history budgets and caching and screenshot-removal policies on a task collecting six fields for 32 books. The best policy let screenshots accumulate to 20 before retaining only the latest one, keeping history stable longer for caching. On GPT-6.1 Sol, the combined changes reduced estimated cost from $1.97 to $0.47 per run; 89% of input came from cache, priced at 5% of uncached input. With the larger history budget, all 18 runs returned correct answers, versus three of 18 with the smaller budget. The optimized GPT-6.1 Sol workflow was about four minutes per run, compared with at least 22.5 minutes for the original production setup on Model B. These are results for the tested task and configurations; the excerpt says Asana released the changes to StackAI browser navigation and plans broader evaluations.

### Source excerpt

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

[Next page](<https://devfeed.tech/topics/browser-automation.md?cursor=WyIyMDI2LTEwLTA5VDA3OjAwOjAwKzAwOjAwIiwgImFmM2Y4YmE0LTBmODYtNGU0MS05ODQ4LTNmNzQ1NzE0YWI1MCJd>)