In this discussion, Alex Salazar, co-founder and CEO of Arcade.dev, shares insights from his impressive background, including roles at Okta and Stormpath. He explains the critical need for secure infrastructure in AI agents, addressing why many fall short of real-world application. Salazar highlights how Arcade enables seamless integration with tools like Gmail and Notion while maintaining user-specific authorization. He also emphasizes the importance of developer-centric solutions and the broader implications of AI agents in the workforce, drawing parallels to the internet boom.
52:32
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
question_answer ANECDOTE
Alex Salazar's Background
Alex Salazar shares his background in authentication and authorization from Okta and Stormpath.
His expertise shaped Arcade.dev's mission to enable secure AI agent actions on behalf of users.
volunteer_activism ADVICE
Secure User Authentication
Use OAuth flows to securely authenticate AI agents acting on behalf of users.
Always require explicit user authorization before agent accesses third-party services.
question_answer ANECDOTE
Agent Hallucination Risk
Alex relates a story where a coding agent hallucinated and tried to delete his root directory.
This illustrates the risks of unrestricted AI agent permissions without proper safeguards.
Get the Snipd Podcast app to discover more snips from this episode
In this episode of Eye on AI, host Craig Smith sits down with Alex Salazar, co-founder and CEO of Arcade.dev, to explore what it really takes to build secure, scalable AI agents that can take real-world actions. While everyone’s talking about the future of autonomous agents, most never make it past the demo stage. Why? Because agents today lack secure infrastructure to connect with real tools like Gmail, Slack, Notion, GitHub—and do so on behalf of users without breaking authentication protocols. Alex shares how Arcade solves the missing layer in AI agent development: secure tool execution, user-specific authorization, OAuth flows, and production-ready consistency. Whether you're building with GPT‑4, Claude, or open-source models, Arcade handles the hard part—making agent actions actually work. Stay Updated: Craig Smith on X:https://x.com/craigss Eye on A.I. on X: https://x.com/EyeOn_AI (00:00) Why AI Agents Can’t Take Action (Yet) (01:27) Meet Alex Salazar: From Okta to Arcade (03:39) What Arcade.dev Actually Does (05:16) Agent Protocols: MCP, ACP & Where Arcade Fits (07:36) Arcade Demo: Building a Multi-Tool AI Agent (11:16) Handling Secure Authentication with OAuth (14:40) Why Agents Need User-Tied Authorization (19:25) Tools vs APIs: The Real Interface for LLMs (23:41) How Arcade Ensures Agents Go Beyond Demos (25:48) Why Arcade Focuses on Developers, Not Consumers (27:55) The Roadblocks to Production-Ready Agents (31:15) How Arcade Integrates Into Agent Workflows (33:16) Tool Calling & Model Compatibility Challenges (34:49) Arcade’s Pricing Model Explained (36:20) Competing with Big Tech: IBM, AWS & Others (38:38) Future of Agents: From Hype to Workflow Automation (41:58) Real Use Cases: Email Agents, Slack Bots, Finance & More (46:17) Agent Marketplaces & The Arcade Origin Story