What the Dev?

In this episode originally published on Get With IT, Dave interviews Idit Levine, founder and CEO of solo.io, about kagent, a framework for running agents in Kubernetes. They discuss:Why kagent was createdWhat led solo.io to open source the project and donate it to the CNCFDifficulties with deploying AI agents in large organizations

Jenn Wei, Senior Vice President of Product at LaunchDarkly, dives into the vital role of nurturing a culture for AI experimentation. She emphasizes the shift from merely building features to managing dynamic learning systems. Jenn discusses balancing speed and control in AI deployments, and the evolving mindset around 'failing fast.' She highlights leadership's crucial role in cultivating innovation and shares practical strategies, like weekly demos and hackathons, to enhance engagement in AI initiatives.

In this episode, Dave interviews Brian Douglas, head of developer experience at Continue, about the importance of rules for AI tools.They discuss: How to implement rules for AI assistantsUsing rules to replace lengthy promptsPreventing technical debt when using AI-generated code

In this episode, Jenna interviews Wade Wegner, chief ecosystem and growth officer at DigitalOcean, about the importance of developer advocacy.They discuss:The relationship among developer advocacy, developer relations, and technology evangelismEffective strategies for engaging with developersMetrics to track to know that advocacy is contributing to product growth

In this episode, Jenna interviews Dr. Manny Ahmed, co-founder and CEO of OpenOrigins, the company behind Human-Oriented Proof System (HOPrS), which can be used to determine if an image or video has been altered or is AI-generated.They discuss:How it works and how it differs from other tools that try to do thisHow it can be used to address concerns around AI-generated contentIts recent acceptance into the Linux Foundation Decentralized Trust Lab

In this episode, Dave interviews Justin Cantrall, AI engineer and architect at OpenText, about specialized language models.They discuss:The difference between specialized language models and large language modelsThe benefits and disadvantages of choosing specialized language modelsOpen weight models 

In this episode, Jenna interviews Maya Palfreyman, product marketing director at Quickbase, who leads the company's research on gray work.They discuss:What gray work is and what sort of tasks qualify How it affects software developersThe impact of unaccounted gray work in planning cycles

In this episode, Dave interviews Jack Pertschuk, principal engineer for Algorithms and Platform at Pinecone. They discuss:What semantic search is and where it falls shortThe difference between sparse and dense vectorsHow search technology powers AI

In this episode, Jenna interviews Julianna Lamb, co-founder and CTO of Stytch, about MCP and how it handles authorization. They discuss:Where MCP gets it right and where more work is neededIssues with traditional auth in agentic workflowsDesigning auth flows for agents vs humans

In this episode, Jenna Barron interviews Tammuz Dubnov, founder and CTO of AutonomyAI, a company that makes AI agents for software development. They discuss:What vibe coding isThe risks associated with itWhere it can be used and where it should be avoided