
transcript
show notes
Mike & Tommy tackle the emerging role of the semantic model as an AI contract layer in Microsoft Fabric, weighing in on whether Data Agents should reason over governed semantic models or hit OneLake directly. They explore the tension between years of invested business logic in semantic models and the flexibility of Lakehouse-first agent access, breaking down how OneLake Security, RLS, and semantic model permissions can coexist for both traditional BI and AI-powered data workloads.
This is a Mailbag episode.
Get in touch:
Send in your questions or topics you want us to discuss by tweeting to @PowerBITips with the hashtag #empMailbag or submit on the PowerBI.tips Podcast Page.
Visit PowerBI.tips: https://powerbi.tips/
Watch the episodes live every Tuesday and Thursday morning at 730am CST on YouTube: https://www.youtube.com/powerbitips
Subscribe on Spotify: https://open.spotify.com/show/230fp78XmHHRXTiYICRLVv
Subscribe on Apple: https://podcasts.apple.com/us/podcast/explicit-measures-podcast/id1568944083
Check Out Community Jam: https://jam.powerbi.tips
Follow Mike: https://www.linkedin.com/in/michaelcarlo/
Follow Tommy: https://www.linkedin.com/in/tommypuglia/