The Professional Network for AI Agents, with Agent.ai Engineering Lead Andrei Oprisan

**SPEAKER_2** (0:02)
In case you missed it, last week we aired an exceptional series with four big picture thinking VCs. And no, it's not the podcast you're thinking of. Check out This Won't Last with Keith Rabois, Logan Bartlett, Zach Weinberg, and Kevin Ryan. You'll be able to sit in on their monthly back channel as they volley predictions about the future of tech, business, and the venture markets. They're only releasing these conversations for a limited time, so check out episode one and subscribe at the link in the description.

**Nathan Labenz** (0:29)
Hello, and welcome to The Cognitive Revolution, where we interview visionary researchers, entrepreneurs, and builders working on the frontier of artificial intelligence. Each week, we'll explore their revolutionary ideas, and together, we'll build a picture of how AI technology will transform work, life, and society in the coming years. I'm Nathan Labenz, joined by my co-host, Erik Torenberg. Today's episode is brought to you in part by Weights & Biases. As a developer, the journey from concept to production-ready large language model apps is fraught with challenges. Dealing with unpredictable large language model outputs, correctly handling PII, and ballooning API costs can all be blockers to shipping your next AI-powered feature. Weights & Biases Weave is a lightweight AI developer toolkit designed to simplify your large language model app development. With Weave, you can trace and debug input, metadata, and output with just two lines of code. Weave helps you run rigorous evaluations and securely manage all of your datasets and system configurations. So you can focus on what matters most, iterating and improving on your large language model powered applications. Plus, Weave integrates seamlessly with your favorite APIs and libraries, including OpenAI, Anthropic, Mistral, Cohere, Langchain, Llama Index, and more. So make real progress on your large language model development. Visit wnb.me.cr to get started with Weave today. That's wnb.me.cr.
And thanks to Weights & Biases for sponsoring this episode. Hello, and welcome back to The Cognitive Revolution. Today, I'm excited to share my conversation with Andrei Oprisan, engineering lead at Agent AI, a fast-growing and currently free-to-use AI agent platform that describes itself as the professional network for AI agents, online at agent.ai.
Before diving in, I want to take a second to note that this is a sponsored episode, our second sponsored episode out of more than 160 total episodes published over the last year and a half. Our goal with sponsored episodes is to create a win-win-win for the show, for the sponsor, and most importantly, for you, the audience. I consider myself very fortunate that many startup founders are currently interested in doing the show. And as such, we have the luxury of reserving sponsored episodes for companies that I personally find very interesting and genuinely expect to resonate with the audience. I see their sponsorship more as a way to cut to the front of the line, so that their appearance on the show aligns to their important company and product announcements more than a go-or-no-go decision criteria per se. Agent AI is a perfect example of such a company. It is a well-resourced and sophisticated effort backed by HubSpot CTO Darmesh Shah with a number of intriguing angles on AI agents and the future of work more broadly. And I think today's episode really exemplifies the win-win-win that I hope to create. I prepared for this conversation with the same depth of exploration that I always do. I tried every last Agent AI product feature that I could find, wrote an outline of more than a thousand words of questions, and challenged Andrei to go deep on the technical details. In the end, I'm glad to say that he really delivered. Highlights from this episode include Andrei's breakdown of the current limitations of language models when it comes to planning, out-of-domain detection, and error recovery. His analysis recorded just days before OpenAI's big O1 announcement foreshadows their release, and suggests that a good chunk of what was previously missing might now be available. Andrei also shared recommendations for how to approach building AI agents, including the importance of narrow, well-defined tasks and robust benchmarking. He shares insights on creating effective prompts, structuring agent workflows, and implementing feedback loops to improve agent performance over time. We also discuss Agent AI's vision for the platform, including the concept of a professional network for AI agents, where agents have their own profiles, and their plan to become a marketplace where developers can build and monetize agents, as well as how this could democratize software creation for everyone, potentially allowing even non-technical users to build sophisticated AI-powered solutions. We also exchange best practices for fine-tuning models, and I was very intrigued to hear Andrei's best practice of using small models locally before going on and scaling up to larger proprietary models in the cloud. We get a detailed explanation for why Agent AI uses Pinecone over Postgres's PG Vector for their vector database, touching on factors including ease of use, scalability, and performance under different workloads. The kind of thing that you can really only hear from someone who has tried a wide range of solutions. We also discuss privacy-preserving techniques for AI. This is something that I really should learn more about. We covered Apple's new approach to encryption of user data and got Andrei's thoughts more generally on the challenges of handling sensitive data in a way that unlocks the power of AI while still maintaining user privacy. Finally, we conclude with an earnest big-picture discussion on the future of work and AI's role in it. We explore Andrei's vision for how AI agents will integrate into various industries, the potential impact this could have on jobs, and the skills that will become increasingly valuable in an AI-augmented workplace. We even touch on some of the ethical considerations and potential societal impacts of widespread AI agent adoption. As always, if you're finding value in the show, we'd appreciate it if you take a moment to share it with friends, write a review on Apple Podcasts or Spotify, or just leave us a comment on YouTube. Of course, we always welcome your feedback, including your thoughts on our experiment with sponsored episodes. You can send us a note via our website, cognitiverevolution.ai, or you can DM me on your favorite social network. Now, I hope you enjoy this discussion, which covers AI agents from all angles. With Andrei Oprisan of Agent AI. Andrei Oprisan, Engineering Lead at Agent AI, online at agent.ai. Welcome to The Cognitive Revolution.