As well as being economically efficient (when building and whatnot).
If you have ever worked with LLMs, you know they are stateless. That is, they have no short-term memory. To make sure the LLM can pull up the right facts, understand previous conversations, and connect information, we need to build some fairly complex systems.
An AI knowledge agent can dig through internal documentation — websites, PDFs, random docs — and answer employees in Slack (or Teams/Discord) within a few seconds. I will go through what it takes to build one using using LlamaIndex and Modal.
Did you know there are dozens of open-source agentic frameworks out there? I have briefly tested some of the more popular ones to get a feel for how they work and how easy they are to get started with.
One of the interesting areas into these Agentic AI systems is the difference between building a single versus multi-agent workflow, or perhaps the difference between working with more flexible vs controlled systems.