Data modeling, code generation, the context store and the agents that work on it, written by the people who build VaultSpeed and the practitioners who run it.
This series covers how Snowflake® and VaultSpeed work together, one industry per post: the business problem, the architecture, and what changes once it is in place. Financial services goes first, because few industries are as strict about getting a number…
Kevin Monk
6 min read
An AI agent on your data platform answers with the same confidence whether the record it read is current, abandoned or duplicated. Nothing in a stale …
Mieke Beelen
4 min read
Ask an LLM to design a Data Vault for 13 tables from a bank's core banking, card and risk systems, with names like LOAN, COLLATERAL and COUNTERPARTY, …
Jonas De Keuster
14 min read
How purpose-built AI agents extend data vault automation beyond code generation, covering source analysis, semantic layers, and governed data products…
Patrick Van Deven
12 min read
What if your team of ten could run a data vault like the best in the industry? The architecture review meeting is one of the most predictable scenes i…
Patrick Van Deven
11 min read
"We're going to use AI agents to build and maintain our data platform." A lot of data teams are now seriously considering exactly that: automating mod…
Jonas De Keuster
8 min read
Every enterprise with an AI programme has heard the same advice: get your data foundations for AI in order. Clean it up. Govern it.
Jonas De Keuster
11 min read
Source systems change constantly. Columns get added, tables get split, keys get redefined, feeds get restructured. In a conventional ETL pipeline, you…
Patrick Van Deven
5 min read
Bring a source system and a question. We connect the context store to it and show you what the agents propose.
Talk to us