Blog
Measured notes on browser automation for AI agents. Every number comes from a run you can repeat.
Run a website task every day with zero AI cost
Let your AI agent learn a browser task once, then let cron or Windows Task Scheduler run it every day with no model calls. Real output, exit codes and scripts.
Why browser agents fail on real websites: 7 causes
Late content, slow confirmations, iframes, cookie banners, dialogs, ambiguous selectors and captchas: what breaks AI browser agents, and what we changed in Dejo for each.
One AI agent, three signed-in roles: customer, vendor, admin
How to let an AI agent act as several users on one site without signing out and back in, compared with Playwright's saved login files.
Can Claude log in to websites? Three ways that work
Claude in Chrome, Playwright MCP and Dejo each keep you signed in differently. What each one does with your login, and which to pick.
Self-healing Playwright automation: repair one step, not the run
Two kinds of self-healing: Playwright's healer agent fixes the test file, fallback locators fix the step at run time. How each works, and why every step needs a check.
Browser agent memory: why your agent re-reads every website
Every new chat, your AI agent learns the same website again. We measured what that costs over 90 Claude sessions, and what changes when the browser remembers the route.