Soumendra Kumar Sahoo

The reliable way to deal with AI-assisted cheating in an interview is not to prove that somebody used AI. It is to collect enough evidence that they can do the job: probe a specific decision, watch them work through a real problem, change a constraint, and ask them to test their own answer. Eye contact, pause length and pasted code are weak signals that even trained interviewers get wrong most of the time. Interview design is the actual defense.[1] I have been on the candidate side of the table…

Langfuse observability for Hermes Agent is the way to see, per query, what your self-hosted agent actually does: which model it called, how many tokens it burned and what it cost. Hermes Agent is not built on LangChain, so it reports traces through Langfuse’s native OpenTelemetry support instead of a framework plugin. In this post I wire self-hosted Langfuse into a self-hosted Hermes Agent on a single Hetzner VPS, and share the gotchas that only show up when you actually run it. My Hermes agent…

One night my AI agent Hermes, which I run 24/7 on my own hardware, spent 47 turns trying to “fix” a script. Every turn it ran the same broken command, got the same error, apologized and tried again. I sat there watching the token counter climb like a Tatkal queue at 10 AM, and I genuinely could not tell what had gone wrong. Was the prompt bad? Was it missing context? Was a tool broken? Was the loop just never going to stop? I am an AI Observability Architect, and I was staring at my own agent…

This post is not technical. It’s an outlier to my regular posts: nothing to do with technology directly. Lately I’ve been exploring Indian philosophy, especially Buddhism. Most of the time I end up absent-minded and confused. I thought writing this down would clarify things. Spoiler: it didn’t. But I found something else along the way. The River There’s a fragment from Heraclitus, a Greek philosopher who lived around 500 BCE. He said: “No man ever steps in the same river twice.” By the time you…