Building an Intelligent Agent

First draft in public 😱 😆🤓

What’s the best way for an agent to build a semantically sound and syntactically correct knowledge base?

Dog fooding my course material means the first step is to define the task environment.

/Checks notes

Task Environment: The description of Performance, Environment, Actuators, and Sensors (PEAS). This provides a complete specification of the problem domain.

So how can I implement this 🤔

First I need to think on the domain, something different to the examples (e.g. Taxi Driver) - maybe Cyber Threat Intelligence.

With that domain I’ll go through PEAS in reverse order - it makes more sense to me, possibly because I have done this in various other ways, so it’s an idea domain to learn but will server well enough.

Sensors:

• Dark web text and image ingester/reader (e.g. onion forums and telegram chat)

Actuators:

• Decomposer and Decontextualiser
• Entity Extractor

Environment:

• Internet

Performance:

• Correct identification of Cyber Attacks?

I’m going to let this sit there a while and let is mull in the back of my mind… 🤔✌🏼