ego(lite) articles
Everything you need to know about browser automation
Guides, insights, comparisons, and reviews across Playwright MCP, Browser Use, Chrome DevTools MCP, coding agents, and the browsers they drive.
Insights
Playwright MCP token problem: why snapshots eat your context
High MCP token usage isn't a settings problem, it's the architecture: every action returns the page's accessibility tree into your context. We trace where the tokens go and rank the three escape routes.
Oct 15, 2026 · 9 min read
Insights
WebMCP explained: how it changes browser automation (and where it doesn't)
WebMCP lets a website publish structured tools to an in-browser agent. We tested the official hotel demo in Chrome 152 to see what worked, where a human stayed in control, and why application-side validation still matters.
Sep 11, 2026 · 11 min read
Insights
Computer Use agent: how it works and how to control it
A vendor-neutral guide to agents that operate browsers and desktop apps: the control loop, architecture choices, safety gates, and production evaluation that matter.
Sep 9, 2026 · 13 min read
Insights
Browser agent security risks: threats and controls
Browser automation security starts with secrets and session scope; AI agents add untrusted-page instructions and autonomous actions. Three architectures, real incidents, and a checklist you can run.
Sep 8, 2026 · 16 min read
Insights
GPT-6 Astra Computer Use: capabilities, limits, alternatives
OpenAI's GPT-6 Astra brings computer use to the cloud. Here's what official sources and early testers say, and how that approach compares to local browser agents for logged-in work, form filling, and data scraping.
Sep 6, 2026 · 12 min read