A lot of enterprise AI pilots stall below the model, in the systems they have to read from and write to. I call that layer the substrate: the data, permissions and system contracts a workflow runs on.
Senior Data Scientist & AI Engineer at IBM · AI agents in production
I write about AI agents in production: retries and idempotency, tool permissions, evaluation, cost and the data foundations underneath. 13+ years from mainframes to cloud data engineering to enterprise AI. Full deep dives on Medium (abivarma.medium.com), Sunday digest on Substack (abivarma.substack.com). Views my own.
Markdown supported · ⌘↵ to post
No responses yet.