The following are common questions and answers about Ask Otto, our generative AI script assistant powered by Automox Otto AI™.
Who has access to Ask Otto?
Once enabled by the Global Admin for a zone, any users with Zone Administrator or Zone Operator can access Ask Otto.
Can I disable Ask Otto after it is enabled
Not at this time.
Is Otto AI expected to be able to evaluate the code in an existing worklet without having to put the actual code into the prompt?
No, for security reasons we don’t automatically send worklet contents through Otto AI.
Is Otto AI using data from Automox to help formulate its response?
No, Otto AI is operating on the training data incorporated in OpenAI’s models.
What is the architecture for how Otto AI is connecting to ChatGPT?
Otto AI connects to ChatGPT over HTTPS. User input and session identifiers are shared, and this can include historical input from the user as well.
What happens to data entered into Otto AI? Is there anything else or anywhere else data sharing is happening?
Data is sent to ChatGPT and stored on Automox infrastructure to facilitate providing the Ask Otto feature.
How do I know that the code generated by Otto AI is good and not malicious?
You don’t. Otto AI is a copilot assistant, and while there are soft guard rails in place to prevent things like deleting System files, we shouldn’t assume they are going to work all the time. There is no data post-processing of response returned by ChatGPT. Code parts wrapped in markdown code blocks are automatically pasted into the editor.
What if ChatGPT gets compromised? What is the exposure of my data / infrastructure?
Data from the last 30 days is retained by OpenAI. User input in that period of time would be exposed via an OpenAI compromise if that dataset was impacted as part of the breach. From OpenAI:
What happens if an Otto AI generated script breaks something in my environment?
Output from Otto AI should be validated prior to execution on a device. Refer to the agreement that all Otto AI users must accept prior to usage: