We are not talking just chatbots - albeit more intelligent ones!

An AI agent/assistant can be tasked to do specific things to reach a goal and work with other agents, either in parallel, or sequential (i.e. do all these things first, then does this).

The cool thing is each AI agent can use a completely different model i.e. you don’t have to tie everything into just chatGPT/Open AI. You might find a different model or model sets beneficial for certain things.

Also, the big component is a mix of RAG (retrieval augmented generation), goal setting and external “tools” or functions where you can call out to external systems.

I will be creating a video (Just Fifteen Mins! as if I ever stick to any timeline!) to explain a few of these concepts in more details. I am also going to be creating a workshop course too! not overly technical, but mostly from a business perspective about the concepts and how they could benefit companies. Again, we are not talking just fancy chatbots!

Until next time, take care everyone!

Please consider subscribing too! It’s okay, you don’t have to pay - unless you want to of course! :) If you do pay for a subscription, you will get a free weekly update from the chief unicorn - Ulysses :)