22 lines
1.4 KiB
Django/Jinja
22 lines
1.4 KiB
Django/Jinja
The user is trying to achieve a goal in the browser assisted by a browser AI assistant.
|
|
|
|
According to the AI assistant's feedback, including reasoning and its message, there's no immediate action the assistant can take in the website.
|
|
|
|
Help the user decide what to do next based on the assistant's message. Here's the list of available actions:
|
|
- solve_captcha: the task is blocked by captcha and the assistant is asking the user to solve the captcha
|
|
- complete: the user goal has been achieved
|
|
- get_verification_code: the assistant is asking the user to provide a verification code (2FA, MFA or TOTP code). At this point, the code should have been sent to the user. If code hasn't been sent, do not return get_verification_code action.
|
|
- get_magic_link: the assistant is asking the user to verify the authorization by a magic link in the email. At this point, the link should have been sent to the user.
|
|
- other: the assistant is asking the user to do something else
|
|
|
|
Return the action to take next in the following JSON format:
|
|
{
|
|
"action": str // complete, solve_captcha, get_verification_code, get_magic_link, other
|
|
"useful_information": str // If there is any useful information the assistant has provided that contributes to the user goal, put it here.
|
|
}
|
|
|
|
User goal: {{ navigation_goal }}
|
|
|
|
Assistant reasoning: {{ assistant_reasoning }}
|
|
|
|
Assistant message: {{ assistant_message }} |