I recorded my Kubernetes AI agent failing, on purpose

Description and use

<p>Most demos of AI-for-infrastructure tools show a clean run. I think that is exactly backwards, and I want to explain why by walking through the thirty seconds of my own demo that a normal product video would have cut.</p> <h2> The scene </h2> <p>A deployment is crash-looping. The agent has already diagnosed it. I ask it to restart the deployment.</p> <p>It stops and asks for approval. I approve. The restart runs, and the command succeeds.</p> <p>Then I ask the follow-up question: did the restart change anything?</p> <p>No. The pods fail with the same error. A restart was never going to supp

Problem

<p>Most demos of AI-for-infrastructure tools show a clean run. I think that is exactly backwards, and I want to explain why by walking through the thirty seconds of my own demo that a normal product video would have cut.</p> <h2> The scene </h2> <p>A deployment is crash-looping. The agent has already diagnosed it. I ask it to restart the deployment.</p> <p>It stops and asks for approval. I approve. The restart runs, and the command succeeds.</p> <p>Then I ask the follow-up question: did the restart change anything?</p> <p>No. The pods fail with the same error. A restart was never going to supp

Outcome

<p>Most demos of AI-for-infrastructure tools show a clean run. I think that is exactly backwards, and I want to explain why by walking through the thirty seconds of my own demo that a normal product video would have cut.</p> <h2> The scene </h2> <p>A deployment is crash-looping. The agent has already diagnosed it. I ask it to restart the deployment.</p> <p>It stops and asks for approval. I approve. The restart runs, and the command succeeds.</p> <p>Then I ask the follow-up question: did the restart change anything?</p> <p>No. The pods fail with the same error. A restart was never going to supp

Evidence

I recorded my Kubernetes AI agent failing, on purpose

Source