10+ hours of podcasts, in 5 minutes.
9 quotes from 1 episode on Practical AI, each with a timestamped link to the source.
Nick Kuhn details how enterprise AI agents operate inside strict architectural limits like physical network barriers and isolated memory services. Corporate airgaps force engineers to carry hardware directly into data centers, making public cloud providers with unexpected downtime unusable.
True enterprise airgaps lack internet access entirely, forcing engineers to manually carry equipment and code into the physical data center.
“…actually have the real airgap where we're carrying in things, you know, physically into the data center because there is no Internet access type of thing.”
From Deploying AI Agents in Airgapped and Low-Latency Enterprise Systems
Attaching memory services to specific projects keeps data isolated and limits agents to their own team history.
“…then like the memory service we have, where you can attach it, you can have, you know, you know, potentially memory of a certain project. So, you know, we kind of envision like each set of teams to have their own multiple set of agents, right? And it could be like, well, you know, Team A's agents have the access to Team A's memory.”
Software vendors build AI tools expecting continuous internet connectivity. Nick Kuhn notes that traditional corporate data centers physically block outside access and cannot tolerate consumer service outages.
“When we had vendors come in, it would always be like they would always assume that we could just go to the Internet…”
From Deploying AI Agents in Airgapped and Low-Latency Enterprise Systems
“And not to mention, if you're using some of these SaaS providers, they're maybe not the most reliable in terms of what traditional enterprises expect and demand. So you can't just have them, you know, going offline for hours.”
From Deploying AI Agents in Airgapped and Low-Latency Enterprise Systems
Isolating session state from applications allows systems to run 1,000 container instances safely. A dedicated memory service lets newly launched agents instantly read project architecture and past roadmaps.
“…where like you talk about Cloud Foundry and Tanzu Platform, it was kind of based on this premise of a 12-factor application, where like storage and state are a little, you know, decoupled cleanly from the actual apps, you could like, you know, I can I can scale up to a thousand instances and be fine, and you handle session state and things.”
“So as they come up, they know like all of this historical data of like what like the architecture of the application, the, you know, what what's been done before and all like the roadmap, that type of thing…”
Routing backend connections through a central point controls execution pathways. Gateways restrict individual agents to a specific list of approved servers and tools.
“You basically register MCP servers to this gateway, and then the gateway kind of controls access, so to speak, and regulates that. So they may say like, 'You can bind to this gateway and you only get these MCP servers, you only get these MCP tools within it.'”
From Why AI Agents Need MCP Gateways and Identity Pass-Through
“…all the different compliance tiers that you have to deal with.”
From Deploying AI Agents in Airgapped and Low-Latency Enterprise Systems
“30 or 40 MCP servers that we run.”
From Why AI Agents Need MCP Gateways and Identity Pass-Through
How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.
10+ hours of podcasts, distilled into one 5-minute read. Free, every Sunday morning.
One email a week. Unsubscribe with one click.