Introducing AutoGen

Enabling LLM-powered agents to cooperate

In my latest article, we’ve introduced the concept of Agents as a type of LLM application that are powered with a set of external tools or plug-ins that allow them to “do stuff”. In ther words, agents can be seen as AI systems that, given a user’s query, are able to interact with the surrounding ecosystem to the extent to which we allow them to. The perimeter of the ecosystem is delimited by the tools we provide the agents with, for example the possibility of searching the web, rather than the ability to write files within you File System.

Recently, Microsoft released a new project about agents called AutoGen, which is bringing agents’ ability to the next level.

What is AutoGen?

AutoGen is a framework to develop LLM-powered applications using multiple agents that are able to communicate and orchestrate among each others. You can literally think about it as a think tank full of experts, each one with a different domain of knowledge, yet all of them extremely capable in advanced reasoning, working together to solve a complex, multidisciplinary task: the mathematical expert might come up with an algorithmic model to represent and solve the issue, then socialize it with the geopolitical expert, who will notice how the model doesn’t take into account possible…