Philip Kiely, software developer relations lead at Baseten, speaks with host Jeff Doolittle about multi-agent AI, emphasizing how to build AI-native software beyond simple ChatGPT wrappers. Kiely advocates for composing multiple models and agents that take action to achieve complex user goals, rather than just producing information. He explains the transition from off-the-shelf models to custom solutions, driven by needs for domain-specific quality, latency improvements, and economic sustainability, which introduces the engineering challenge of inference engineering. Kiely stresses that AI engineering is primarily software engineering with new challenges, requiring robust observability and careful consideration of trust and safety through evals and alignment. He recommends an approach of iterative experimentation to get started with multi-agent AI systems. Brought to you by <a href="https://www.computer.org/" target="_blank" rel="noopener">IEEE Computer Society</a> and <a href= "https://www.computer.org/software" target="_blank" rel= "noopener">IEEE Software magazine</a>.

Podurama

Home

Trending

Personal

Your Podcasts

New Episodes

My Files

Favourite Episodes

Tags (Folders)

Recently Played

Bookmarks

Followed Playlists

SE Radio 697: Philip Kiely on Multi-Model AI

Software Engineering Radio - The Podcast for Professional Software Developers

AI Chapters

AI Insights

Reviews