Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Playwright
Cloud Browser: A Secure Remote Browser Platform for Any AI Agent
A reference design for a model-neutral remote browser service: gateway, workers, WebRTC live view, approvals, SSRF guards, replay, and every config setting.
32 min readWhy Coding Agents Keep Reinventing the Browser
Why long-running coding agents converge on browser-shaped tooling: helper scripts, cookies as memory, compact page views, HTTP fallbacks and training-data bias.
12 min readWhat Agentic Testing Changes for QA and Where It Still Falls Short
Scripted and self-healing suites break when the UI shifts. Intent-driven browser agents cut maintenance, but regulated flows and odd UIs still need care.
7 min readWire LM Studio to MCP Servers for Files, GitHub and a Browser
Step-by-step mcp.json configs that let a local model use the filesystem, GitHub OAuth tools and Playwright, with model picks and fixes for common errors.
7 min readTurning Playwright HAR Traffic into Security Findings with an MCP Scanner
A passive TypeScript scanner turns Playwright HAR files into security findings on headers, cookies, CORS and secrets, exposed to AI over MCP and a CI gate.
7 min readPlaywright and TypeScript Without Knowing TypeScript: An Engineer, an AI Layer and Four Gates
A QA engineer coming from Selenium and C# builds a Playwright framework in TypeScript with AI help: structure, architecture rules, hooks and four ticket gates.
25 min readShift-Left Testing With Coding Agents: Choosing the Lowest Reliable Test Layer
Shift-left testing with coding agents: QA engineers read the repo, pick the lowest reliable test layer per scenario and cut slow browser tests. With an example.
7 min readThree Playwright Agents: Planner, Generator and Healer on a Live Cart App
A Playwright framework where one agent plans coverage, one generates specs from live browser sessions and one heals failures, giving 22 parallel tests in about 16 seconds.
8 min readPlaywright or Browser Agents? Where Scripted Automation Still Wins
Playwright scripts vs MCP-driven browser agents: brittleness, determinism and cost, one invoice task done both ways, the security risks and when each wins.
8 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.