Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles last week

What I learned:

• A developer showed me his new AI solution for enterprise HR teams. His tool uses audio as the input method (i.e., people talk to the software, and it talks back). I asked what powers his tool, and he told me about Pipecat and Livekit. These two open-source, orchestration frameworks can be used to build real-time voice and multimodal AI agents (e.g., phone bots, web voice assistants, or software that the user interacts with solely via voice). “Multimodal” means able to handle multiple input/output methods (text, audio, video, etc.). These tools let you build agents that can accept spoken questions or instructions from a user > convert that speech to text (STT) > feed that text to an LLM (which processes it and provides a text response) > convert that text to speech (TTS), and speak to the user (e.g., answer questions or respond to instructions).

That’s what I learned and struggled with last week.