Isabelle Williams of WorkOS demonstrates how to make an application ready for agent users, using a travel app called Waypoint. She covers the auth.md protocol for anonymous agent access and claim flows, ID-JAG identity assertions that let an agent's provider vouch for a user without a signup form, and scoped, revocable agent tokens that keep agent permissions auditable and bounded.
Alex Danilowicz, co-founder of Magic Patterns (YC W23), walks through the company's origin as an attempt to make design accessible to front-end engineers and non-designers, demos the new MagicOS canvas and its MCP integration with coding agents, and reviews several AI-built startup landing pages to explain what makes a site feel vibe coded and how to make AI-generated design more intentional.
Martin Keen explains loop engineering as the next step beyond prompt engineering: designing systems where AI agents act, observe, adjust, and repeat toward verifiable goals. The discussion covers goal design, triggers, context and persistent state, tools via MCP and APIs, verifier subagents, and why humans must remain in the loop to manage comprehension debt, intent debt, and cognitive surrender.
Sam, CTO at Gravity, argues that AI agent governance must be enforced in infrastructure rather than in prompts or policy documents. Through five live demos against a hotel-booking agent, he shows a gateway blocking destructive tool calls, preventing data exfiltration, rate-limiting runaway agents, serving cached semantic responses, and rejecting oversized prompts before any LLM call. He also covers observability, vendor decoupling via LLM routing, trimming bloated MCP tool lists, and managing shadow AI.
Thorsten Hans shows how to build MCP servers and AI agents with Spin, the open-source WebAssembly framework, and run them on Akamai Functions, a globally distributed serverless platform with no cold starts. The talk explains why WebAssembly suits edge-native AI workloads, live-codes MCP servers with wasmcp in TypeScript and Rust, deploys them worldwide with one command, and closes with a Vercel AI SDK agent backed by a Linode GPU model and memory snapshots that keep apps warm.
Gil Feig, co-founder and CTO of Merge, explains why agents need a company-wide context graph rather than a few MCP connections. Using the question of which customers were upset last week, he shows why live API lookups fail across large datasets and why synced local copies, routing, summarization, skills, memory, and traceable provenance are needed to build a reliable company brain.