In this tutorial, I’ll demonstrate how I constructed an AI voice appointment setter that can perform the following tasks: - Book appointments regardless of the caller’s timezone. - Identify available time slots for different team members and assign one of them to the meeting based on their availability. - Suggest two to three free time slots to the caller if the requested time is unavailable. Here is the link to the video: https://youtu.be/g_KqJ9JXAg8?si=LRAMoLitSVn224xC

Here is my recent talk for the nlp summit 2024 where I go through how to create a ebook using code. If you are interested in learning more and writing your own ebook - drop me a comment below.

Mistral AI has announced the alpha release of its new model with agent functionality. This update allows developers to wrap models with additional context and instructions, enabling custom behavior and workflows through a simple set of instructions and examples. The agents can be used on platforms like Le Chat or via API, leveraging the advanced reasoning capabilities of Mistral Large 2. This feature aims to facilitate the creation of complex workflows that are easily shareable within organizations. Mistral AI is also working on connecting these agents to various tools and data sources. Build, tweak, repeat | Mistral AI | Frontier AI in your hands https://mistral.ai/news/build-tweak-repeat/

The idea of leveraging LLMs as agents performing autonomously is the latest rave. In general I continue to take the view that these systems are not in fact 'agents' as the definition of this concept would typically require (have a will/interest of their own), but rather that they follow a predefined sequence of steps or a DAG (directed acyclic graph), which is much more akin to execution than agency. This survey provides the systematic overview of LLM-based agent planning, covering recent works aiming to improve planning ability. It provides a taxonomy of existing works on LLM-Agent planning, which can be categorized into: - Task Decomposition - Plan Selection - External Module - Reflection and - Memory. Interesting overview of the current state of the art as it relates to agents. https://arxiv.org/abs/2402.02716

Google Deepmind, Stanford and University of Illinois at Urbana-Champaign propose a Google search based system to factually validate LLM generated outputs to decrease LLMs tendency to confabulate. I do think this is a cool idea and will make AI agents factually more reliable, but I hope the irony doesn’t escape you: a) After we have now spent many billions of dollars on the development of LLMs and RAG systems, vector stores, data centers and hardware, etc. AI agents now go and check their outputs on Google. All this effort to go back to a Google search … b) I suspect it’s not coincidence that Google co-authored this research, looking to deeply integrate search into the AI toolbox, a technology many have argued that is going to upend their dominance and business model. In reality, I’d say this quickly gets a bit tricky though, because the answer your system proposes that is then fact-checked via Google search may well include information from your proprietary RAG system, which you might not want to send into a Google search. https://arxiv.org/abs/2403.18802