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.

Browser agent verification illustration: ego(lite) considers an unfinished terminal task list.

Guides

Browser agent verification: prove task completion

A green success message can appear while a request remains Draft. Our controlled task shows what to check after a browser agent acts and how to keep proof of the result.

Nov 14, 2026 · 22 min read

Browser Use knot logo and pi symbol on a bright blue sky

Guides

Browser Use Pi: packages, setup, and session tradeoffs

Identify @browser_use/pi and the separate Pi extensions before choosing a browser route. The retained 30-run benchmark measured browser tools, not the current SDK.

Nov 12, 2026 · 13 min read

Pixel-art terminal agent reading a browser skill guide beside a mountain lake

Guides

Browser automation agent skills: install and verify

Installing a browser skill gives an agent instructions. It doesn't supply a logged-in session or prove a write succeeded. We checked both questions on one owned task.

Nov 11, 2026 · 22 min read

Two browser agents holding error signs to illustrate web search failures

Guides

Why LLM agents fail at web search & how to fix it

A bad answer can begin with a missing search call, a vague query, an inaccessible page or evidence the model ignored. Inspect each stage before changing the prompt.

Nov 11, 2026 · 13 min read

Claude Code browser login: how to automate sites behind auth

Guides

Claude Code browser login: how to automate sites behind auth

The agent's browser isn't signed in to anything; that's the whole problem. Three real routes with steps and risk profiles, plus practical guidance for CAPTCHAs, OAuth loops, session expiry, 2FA, and scheduled runs.

Nov 10, 2026 · 9 min read

Context engineering for browser agents: what an observation costs

Guides

Context engineering for browser agents: what an observation costs

Almost every article on this term uses text-only examples. Across the top 24 results, 19 fetchable pages and 64,225 words, "accessibility tree", "screenshot" and "browser automation" each appear zero times. That is the gap this fills.

Nov 10, 2026 · 12 min read

A hand holding the ego(lite) comedy and tragedy masks against a blue sky, ready to take over a native prompt

Guides

Automate native file dialogs in browser automation

The OS file dialog is outside the page. Browser automation sets the input, intercepts the chooser, or saves the download. Driving AutoIt is the exception, not the method.

Nov 10, 2026 · 10 min read

How AI agents connect to your existing browser and logged-in sessions

Guides

How to connect AI agents to your existing browser

The most-requested agent capability across forums and issue trackers, mapped honestly: four routes with their mechanisms and risks, the account and permission checks each one requires, and the two questions that pick yours.

Nov 10, 2026 · 10 min read

Three white disks on a yellow platform, casting a long shadow of login, lock, key, and permission icons across a blue field

Guides

Login handoff in AI browser agents: OAuth and MFA

An agent that meets a login wall should not reach for a password store. The login handoff pattern keeps the human in the loop for exactly the steps that require a person, then lets the agent resume in the same authenticated session. This guide defines the pattern, shows a working implementation with measured runs including a timeout case, and covers what must never be automated.

Nov 9, 2026 · 13 min read