Author
Laying out a Microsoft Fabric lakehouse for analytics
Fabric puts the lake, the warehouse and Power BI on one storage layer. That only simplifies things if medallion layers, workspace ownership and Direct Lake models are settled before the first load.
NinetyX Data & AI Practice · · 3 min read
Governed data comes before useful AI
AI work stalls in the data layer far more often than in the model. A catalogue, access granted at the source and lineage you can query are the groundwork most plans leave out.
NinetyX Data & AI Practice · · 2 min read
Dashboards people trust start with the semantic model
Dashboards built straight on raw tables soon disagree, and trust goes the first time someone notices. A semantic model with one grain per fact table and agreed measures keeps every report on the same numbers.
NinetyX Data & AI Practice · · 2 min read
Treat LLM features as engineering, not experiments
Useful LLM features depend less on model size than on retrieval over your own content, an evaluation set that gates each release, and guardrails tested like any other code.
NinetyX Data & AI Practice · · 2 min read
Start from the platform you have today
Tell us what you run, what is holding back the next release or workload, and who owns it. An engineer replies with questions and a proposed first step.