Tag: ai-agents
All the articles with the tag "ai-agents".
-
Credential Sentinel: An Agent That Reads Widely and Acts Narrowly
Updated:How I built Credential Sentinel, a LangGraph AI agent that finds the credentials nobody is rotating and walks them to a safe, human-approved rotation. A look under the hood at the resumable state machine, the real TLS handshake, delayed-revoke cutovers, automatic rollback, and a cross-run memory.
-
Deploying an AI Agent: How I Shipped Credential Sentinel to Production
How I deployed Credential Sentinel, my LangGraph AI agent, from local development to a live production URL. The infrastructure story: multi-stage Docker builds, Kubernetes with GPU nodes, a one-line vLLM swap, Prometheus, and Fly.io.
-
Building the Agent Was the Easy Half. The Evaluation Wasn't.
How I evaluated my own AI agent: a 50-case golden dataset scored with code and an LLM-as-judge in LangSmith, plus the security regression I caught. The story of taking Credential Sentinel from a 0.976 composite score to a clean 1.0.
-
The Model War Is a Distraction. The Real Fight Is the Agent Runtime Layer.
Why the AI model race is a distraction and the real fight is the agent runtime layer. It is the infrastructure that decides which companies build durable AI systems and which spend the next two years rearchitecting.