Peter Avenant (@PeterAvenant) profile picture

Peter Avenant

@PeterAvenant

Head of Data & AI Engineering at https://nitter.gq/t.co/jnFGXAsKGe

deltavault.ai
Joined September 2013
  • Tweets2K
  • Following152
  • Followers330
Your silver layer can keep its sources' shape and still be readable by an AI agent. A business model and the mappings tied to it carry the meaning. We lay out seven steps for one business area, each ending in a check you can run. deltavault.ai/blog/seven-ste…
Illustration for the article Seven steps to a meaning layer

ALT Illustration for the article Seven steps to a meaning layer

4
A few pages of business definitions lifted text-to-SQL accuracy 17 to 23 points on three frontier models, and no table moved. The bottleneck for AI is meaning, not structure. A faster diagram tool automates the step that needed you. deltavault.ai/blog/who-is-th…
Illustration for the article Who is the data model for?

ALT Illustration for the article Who is the data model for?

1
7
Audit history, parallel loading and new sources all have cheaper homes than a Data Vault. What is your vault still for?
7
Adding meaning to data used to cost a table. Now it costs a sentence. How many tables did your last concept need?
17
Databricks Genie, Fabric data agents and Snowflake Cortex Agents each read their own semantic layer, so the business meaning you curate for one gets written again for the next. Write it once, on no platform, and render it into each.
Illustration for the article What the agent reads

ALT Illustration for the article What the agent reads

1
63
Data Vault puts meaning into hubs and links because a table was once the only thing a machine could read. An AI agent reads a business model, so in AIMS a hub becomes an entity class and a link a relationship. Which table would you defend?
Illustration for the article What a hub becomes when an agent reads the model

ALT Illustration for the article What a hub becomes when an agent reads the model

1
8
Mapping every column to a business attribute before a table can ship rebuilds a canonical model's cost, one column at a time. AIMS makes mapping mandatory only for critical columns and tracks the rest as coverage that warns, not blocks. deltavault.ai/blog/every-met…
Illustration for the article Every method stops at the concept

ALT Illustration for the article Every method stops at the concept

16
A Data Vault hub or link no longer has to be a table. It can be a statement an agent reads. Which stays a table for you?
14
Databricks, Snowflake and Microsoft Fabric each build their agent a semantic layer, so you write the same business meaning on every platform. AIMS writes it once, on no platform, and every agent reads the same data contract. deltavault.ai/blog/what-the-…
Illustration for the article What the agent reads

ALT Illustration for the article What the agent reads

1
29
Bronze shipped a year ago and gold still isn't trusted. That gap isn't a missing platform feature. It's six pieces of integration work nobody scheduled, and the first is one meeting to agree what a customer is. deltavault.ai/blog/six-steps…
Illustration for the article Six steps to your integration layer: from bronze to trusted gold

ALT Illustration for the article Six steps to your integration layer: from bronze to trusted gold

5
Data Vault wrote business meaning into tables because a table was all a machine could read. Your model's new reader reads sentences. Audit history and parallel loading now live in persistent staging, and the meaning lives in your catalog. deltavault.ai/blog/modeling-…
Illustration for the article Modeling for Machines That Can Read

ALT Illustration for the article Modeling for Machines That Can Read

8
Agents rarely miss the join. They miss what the column means. Would an agent understand your column names today?
7
An AI-drafted description reads like one a steward wrote, so the next AI run treats it as fact. In DeltaVault's Map & Match, every suggestion arrives with a confidence score and a written reason, and a person decides where the bar sits. deltavault.ai/blog/context-f…
Illustration for the article Context for AI, context by AI: metadata needs a confidence score

ALT Illustration for the article Context for AI, context by AI: metadata needs a confidence score

5
Your silver layer can keep its sources' shape and integrate last. What are you integrating that nobody asked for?
9
Never let a governance rule block someone from saving metadata to a branch. Block a half-governed draft and people stop writing drafts, and the work moves to a spreadsheet. Gate generation, approval, and promotion to main instead. deltavault.ai/blog/metadata-…
Illustration for the article A Model You Can Diff: Metadata Version Control for Data Teams

ALT Illustration for the article A Model You Can Diff: Metadata Version Control for Data Teams

2
Gold can read silver before anything is integrated. Keep each source table in its own shape, and add a key mapping and golden record beside it only when a named consumer needs one record. Which of your integrations had that consumer?
Illustration for the article Integration by exception

ALT Illustration for the article Integration by exception

11
Data Vault wrote business meaning into hubs and links because tables were all a machine could read. A language model now reads the meaning directly: 16 percent correct on a raw schema, 54 percent over an ontology of the same tables. deltavault.ai/blog/you-dont-…
Illustration for the article You don't need Data Vault anymore

ALT Illustration for the article You don't need Data Vault anymore

15
Data Vault builds a hierarchical link table for a customer's parent account. AIMS adds one parent key column and writes the rest down as a hierarchy relationship your AI agent reads. We translated every construct the same way. deltavault.ai/blog/what-a-hu…
Illustration for the article What a hub becomes when an agent reads the model

ALT Illustration for the article What a hub becomes when an agent reads the model

14
Nothing about the data moved, yet a language model went from 16% to 54% accuracy on business questions once an ontology described the tables. Your meaning no longer needs a table per concept. It needs a sentence in your catalog. deltavault.ai/blog/the-econo…
Illustration for the article The economics of meaning flipped

ALT Illustration for the article The economics of meaning flipped

8
Portability has to live somewhere. Put it in the generated SQL and you get code that runs everywhere and uses nothing well. Put it in the model and Databricks gets a real Lakeflow bundle. Change the target, not the meaning. deltavault.com/blog/portabil…
Illustration for the article The model is portable. The code is native.

ALT Illustration for the article The model is portable. The code is native.

1
25
Load more