Data integration, DataOps, real-time architecture and AI-ready data without the platform theatre. We write about the engineering problems that appear when enterprise data has to move, stay current, remain governed and support real operational outcomes.
The Data Was Right. The Decision Was Right. The Action Was Still Wrong. I’ve been thinking about one slightly awkward part of Agentic AI. Not hallucinations. Not prompts. Not whether the model is clever enough. Timing. We’ve spent a lot
Why least privilege may need a companion: least context Here’s a funny thing about enterprise AI. We spend a lot of time talking about what an agent should be allowed to do, but much less time talking about what it
The difficult part starts when an agent stops describing the business and starts changing it Enterprise AI has become very good at telling us what it thinks should happen next. It can investigate an incident, review a supplier, classify a
Microsoft Copilot is becoming more than a productivity assistant. That is the part many businesses are watching closely. The first wave was about helping users write, summarise, search and move a bit faster. Useful, yes. But not transformational on its
Why enterprise AI agents can behave perfectly and still reach the wrong conclusion The agent gives a perfectly reasonable answer. The model behaved as expected. The prompt was fine. The tool call worked. And the result is still wrong. I
Enterprise AI is crossing an important boundary. Until recently, most enterprise AI systems were primarily asked to read information and produce an answer. They could summarise a contract, explain a report, find customer information or draft a response. Agentic AI
When Enterprise Data Platforms Become Too Complex Enterprise data platforms usually start with a sensible goal: Connect the data Make it trustworthy Make it useful The problem is that, over time, the platform itself can become part of the complexity.
