https://carney.wiki/tags/ai-agents/Recent content in AI agents on carney.wikiHugo -- gohugo.ioenMon, 01 Jun 2026 00:00:00 +0000https://carney.wiki/blog/ai-agents-need-more-than-semantic-layer/Mon, 01 Jun 2026 00:00:00 +0000https://carney.wiki/blog/ai-agents-need-more-than-semantic-layer/A semantic layer is not an AI strategy. It is one important part of one. That distinction matters because a lot of companies are still treating AI like a smarter search box. They connect a model to documents, databases, dashboards, SaaS tools, or internal knowledge bases and expect useful work to fall out the other side. Sometimes it does. More often, the model gives a plausible answer, misses the business logic, forgets the prior context, or takes an action without understanding how the work is actually supposed to get done.https://carney.wiki/blog/did-governance-just-die/Tue, 17 Feb 2026 00:00:00 +0000https://carney.wiki/blog/did-governance-just-die/Data governance is not dead. Governance theater is. If you have ever sat through a data governance council where everyone agreed definitions matter and then immediately went back to shipping whatever, you know the problem. The meeting was not governance. It was a performance about governance. That used to be annoying. In the AI era, it becomes dangerous. Humans can often patch ambiguity with tribal knowledge. They know which dashboard is “really” used by finance, which field is stale, which Salesforce status is fiction, and which metric definition nobody says out loud.https://carney.wiki/blog/data-modernization/Mon, 16 Feb 2026 00:00:00 +0000https://carney.wiki/blog/data-modernization/Modern data stacks were supposed to make things easier. Faster insights. More self-service. Better dashboards. Cleaner pipelines. Fewer heroic spreadsheet rescues. Instead, a lot of organizations ended up with complexity by default: more tools, more integration work, more handoffs, more cloud spend, and a growing gap between data work and real business outcomes. Now AI agents are being layered on top of that mess. That is not automatically bad. But it is risky if leaders treat AI like a shortcut around the fundamentals.https://carney.wiki/blog/your-ai-agent-is-a-toddler-with-root-access/Tue, 10 Feb 2026 00:00:00 +0000https://carney.wiki/blog/your-ai-agent-is-a-toddler-with-root-access/Agentic AI is no longer a demo. It calls APIs. It writes to databases. It triggers workflows that affect customers, revenue, and operations. That is powerful. It is also a fundamental shift in risk. Once an AI system moves from advisory to execution, it becomes part of the control plane. Whether the organization admits that or not is mostly irrelevant. The risk already changed. Agents expand the attack surface overnight The moment an AI system can execute actions, it becomes a privileged actor.https://carney.wiki/blog/prompt-injection-has-left-the-chatbot/Thu, 05 Feb 2026 00:00:00 +0000https://carney.wiki/blog/prompt-injection-has-left-the-chatbot/Prompt injection did not suddenly become dangerous. We connected it to systems that matter. For years, prompt injection was treated as a curiosity: a way to make a chatbot ignore rules, leak instructions, or say something awkward. Interesting for demos. Annoying in production. Easy to dismiss as a model behavior problem. That framing is obsolete. The recent reporting around ServiceNow AI agent vulnerabilities should make the shift clear. This is not just about a model getting confused.