Tag feed

#browser-automation

46 posts2 followers

Explore Hashnode

Alternatives

Trending tags this week

MSManu Shuklaecorpit.hashnode.dev1d ago · 14 min read

Claude's browser use tool costs 6,600 input tokens per request before a screenshot: the 19 August 2026 release

Claude's browser use tool costs 6,600 input tokens per request before a screenshot: the 19 August 2026 release Summary. Anthropic released browser_toolset_20260801 on 19 August 2026, generally availab

0

MSManu Shuklaecorpit.hashnode.dev2d ago · 15 min read

Claude computer use went GA on 19 August 2026: seven changes that break an existing agent loop

Claude computer use went GA on 19 August 2026: seven changes that break an existing agent loop Summary. Anthropic made computer use generally available on the Claude API on 19 August 2026 as the compu

0

DFDwayne from Samelogicsamelogic.hashnode.dev4d ago · 12 min read

AI Agent Observability Is Not Enough for Browser Outcomes

AI agent observability is the practice of making an agent's reasoning process, model calls, tool use, latency, cost, errors, and outputs inspectable across a run. That is the short definition. In prod

2

K

ATAnakin Techanakinwriters.hashnode.devAug 5 · 7 min read

Login Automation Fails When the Session Becomes the Account

A password is not an account, and cookies are not a login. Systems that blur those facts usually work in the demo, then fail when the same customer has two accounts on one portal, a password rotates i

0

TWTang Weigangdoramagic.hashnode.devJul 16 · 1 min read

Before an AI Agent Gets a Browser, Verify agent-workspace-linux's Isolation Contract

agent-workspace-linux is useful because it changes the target of automation. Instead of driving the host desktop, it provisions a hidden Linux X11 workspace with its own window manager, browser, clipb

0

ATAnakin Techanakinwriters.hashnode.devJul 14 · 7 min read

Firecrawl, Browserbase, and Bright Data: Choose by Failure Mode, Not Feature List

The wrong way to choose web access infrastructure is to compare scraping vendors feature by feature. AI agents do not fail because one API had fewer SDK examples. They fail because the page required s

0

ATAnakin Techanakinwriters.hashnode.devJul 13 · 7 min read

Treat browser agents as a fallback, not the data plane

The expensive part of browser automation is not only Chromium. It is the decision to treat a rendered interface as the system of record. Once a data pipeline depends on layout, modals, timing, screens

0

SPSandeep Pandabug0.comJul 2 · 9 min read

Playwright MCP and CLI now redact secrets from console logs

tldr: Playwright MCP 0.0.77 and Playwright CLI 0.1.15 shipped within a day of each other in the last week of June, and both close the same gap: secrets you loaded for your AI agent could still leak in

0

SPSandeep Pandabug0.comJun 27 · 9 min read

Playwright MCP gets high-resolution screenshots: what it means for AI test agents

tldr: A pull request merged into Playwright on June 25 adds a scale: device mode to the MCP browser_take_screenshot tool. On a Retina screen, that doubles the linear resolution AI agents work with. It

0

SPSandeep Pandabug0.comJun 26 · 13 min read

Playwright CLI vs. Playwright MCP: which one should drive your AI browser tests?

tldr: Microsoft ships two ways to hand an AI agent a browser: Playwright MCP and the newer Playwright CLI. Both shipped fresh releases on June 10, 2026, and they answer the same question with opposite

2

DJ

#browser-automation

Search Hashnode

#browser-automation

Explore Hashnode

Trending tags this week

Claude's browser use tool costs 6,600 input tokens per request before a screenshot: the 19 August 2026 release

Claude computer use went GA on 19 August 2026: seven changes that break an existing agent loop

AI Agent Observability Is Not Enough for Browser Outcomes

Login Automation Fails When the Session Becomes the Account

Before an AI Agent Gets a Browser, Verify agent-workspace-linux's Isolation Contract

Firecrawl, Browserbase, and Bright Data: Choose by Failure Mode, Not Feature List

Treat browser agents as a fallback, not the data plane

Playwright MCP and CLI now redact secrets from console logs

Playwright MCP gets high-resolution screenshots: what it means for AI test agents

Playwright CLI vs. Playwright MCP: which one should drive your AI browser tests?