I think semi-automation with contextual and domain-specific tooling is the key to the best quality outcomes.

For example, with browser automation, giving the LLM raw access to the literal DOM generally results in disaster for tasks that need to be stable across more than 5-10 interactions. The better approach is to write an intermediate layer that understands each view and can provide a list of tools that are precisely tailored for each case. E.g.:

  https://myapp/Login
  - <raw dom - hundreds of kb>
  - Available Tools: <arbitrary javascript>

  https://myapp/login
  - We detected that this is the application's login page. 
  - It has the following visible elements:
    + Username
    + Password
    + Login Button
  - Available Tools:
    + PerformLogin
    + Quit

Yea I’ve been warming up to the web mcp after doing more ai browser work and hitting so many pain points: https://developer.chrome.com/docs/ai/webmcp