33 essays
All analysis.
Written by Himanshu Saxena, an engineering leader and TEDx speaker, and published on Substack and LinkedIn. Recurring themes: AI Governance, AI in the wild, Security, AI, Agents, Cost.
01AI GovernanceJev for AI Governance: Preventing Destructive Cloud Agent ActionsDiary of a CTO02AI GovernanceDynamic Cloud Risk Assessment with Jev: Same Command, Different ContextDiary of a CTO03AI GovernanceHow to Build an AI Agent Execution Gateway with JevDiary of a CTO04AI GovernanceJev for SIEM Log Analysis: A Splunk Integration ArchitectureDiary of a CTO05AI GovernanceDetecting Authorized Access Misuse with Jev and Audit LogsDiary of a CTO06AI GovernanceDetecting Possible Data Exposure with Jev Event CorrelationDiary of a CTO07AI GovernanceJev vs. LLM Guardrails: How to Benchmark Risk, Latency, and CostDiary of a CTO08AI GovernanceAI Governance Audit Evidence and Production Rollout with JevDiary of a CTO09AI in the wildOpenAI Agent Breached Australia's Health Website for 3 MonthsDiary of a CTO10AI in the wildKing Charles Told AI's Top CEOs the Risk Is "Existential." Here's What Was Actually Said at Dumfries House.Diary of a CTO11AI in the wildA UK Council Spent £11,688 on AI-Generated Public Art. Here's What the Bill Actually Covered.Diary of a CTO12SecurityComp AI Raises $34M to Expand AI-Powered Security and Compliance PlatformDiary of a CTO13AI GovernanceAnthropic and OpenAI Say They'll Embed Independent AI Safety Evaluators — Can They Actually Stay Independent?Diary of a CTO14AIWhen Software Starts Exercising Engineering JudgmentLinkedIn15AgentsMy agents don't know the other agents exist. That's the part that should scare you.Substack16SecurityClaude Breached Three Real Companies. Days Later, It Wiped a Database Too.Substack17SecurityOpenAI Just Proved Why AI Agents Need a Kill SwitchSubstack18CostWhy AI Agent Token Costs Are So Hard to ControlLinkedIn19CostYour token bill is not an AI problem. It is the same infrastructure trap from 2019.LinkedIn20AgentsThe web was built to exploit you. Agents don't care.LinkedIn21AgentsI studied how humans make decisions. Agents have none of those weaknesses.Substack22SecurityThe Composio Breach Exposed the Hole SOC 2 Was Never Built to SeeLinkedIn23SecurityYour SOC 2 certification says nothing about your agentsSubstack24LeadershipThe CTO who'd rather hire a junior than build the AI.Substack25ToolingClaude Code forgets everything when you close it. Someone built a fix and open sourced it.Substack26LeadershipWhat if I never felt like an imposterSubstack27LeadershipFail fast is terrible advice. Here's what actually works.LinkedIn28CultureThe three things that actually drive engineering culture (and it's not ping pong tables)LinkedIn29CultureThe Best Engineering Teams Do Not Document. They Build Systems That Remember.LinkedIn30DevOpsDevOps Was Built for Humans. Agentic DevOps Won't Look the Same.LinkedIn31DevOpsDevelopers Are Getting Replaced. DevOps Is Not Ready for That.LinkedIn32DevOpsYour DevOps Stack Was Built for Google, Not for YouLinkedIn33CareerI talked to a CTO who built a profitable startup, shut it down, and went back to being an ICLinkedIn