Rashmi Badadale
RSS FeedPersonal Blog - Not your regular, Hello World! :) I build the infrastructure that makes software reliable — and I'm bringing that rigor to AI.
I love brainstorming and would love to explore what ideas you are working on. Let's connect:
Featured
-
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.
-
How LogIQ Was Born From a Silent VM Bug
How a silent VM bug that only failed after the 20th machine led me to build LogIQ, an AI tool for on-call debugging. It correlates Splunk, Jira, and customer logs into one investigation flow.
-
The AI Didn't Go Rogue. The Architecture Let It.
A SaaS startup lost its production database in 9 seconds to an AI agent, and the real cause was not the AI but the architecture around it. A look at blast radius, over-scoped credentials, and backups that share a failure domain.
Recent Posts
-
What Happens When Women in Tech Actually Get in the Same Room
What two Women in Miami Tech (WIMT) events taught me about showing up in a room full of women in tech. Honest conversations, real connections, and a few better questions to ask next time.
-
DeepStation's Vibe Coding Cohort Experience
An honest, first-hand review of DeepStation's four-week Vibe Coding cohort in Miami, where AI tools turn an idea you cannot yet code into a working product. My takeaways on building with AI.