Tool descriptions tell an agent what a tool does. They don't tell it how to use five tools together, in the right order, following your conventions. That gap is where this conversation lives. Filmed at AGNTCon + MCPCon in Tokyo with Ola Hungerford, Principal Engineer for AI Enablement at Nordstrom and a maintainer of the Model Context Protocol, who spent the last several months turning a pattern everyone was quietly reinventing into an actual MCP extension.

We audited 20+ memory frameworks before building our own, and found that most aren't built to handle organizational-scale knowledge or treat context as a first-class citizen. Aperture Nexus is our answer: an open source memory and cognition layer built on ApertureDB, the same foundation already running in production at Fortune 50 scale. v0.1 is live, MIT licensed, with an honest breakdown of what ships today versus what's still on the roadmap.

A year ago, Palo Alto Networks built dashboards to track AI spend. Today those dashboards are useless, and the team that built them thinks that's the whole story. Recorded at FinOps X in San Diego, this conversation brings together Abhinav Lad, who leads cloud and AI finance at Palo Alto Networks, and Kuntal Patel, who runs the cloud engineering function behind it. They explain what happened when agents entered the picture, and AI stopped behaving like a service anyone could forecast.