A column is not a definition, and a table is not a process. Ask an AI what a column means and the best it can do is read the schema. The schema only records how one application happened to store something. What you actually need to know is how reality became that data: which business event happened, what your team agreed to call it, and which process turned it into a row.

No prompt carries that understanding.

That’s why DeltaVault doesn’t run its AI on one-off prompts. Every AI action in the product follows the same five steps, whether it’s proposing a business domain, matching a source table, or shaping a view. This post maps the loop, and the rest of the series already walks each step.

Why is a one-off prompt not enough for a data platform?

A prompt is one person’s memory of the context, typed into a box on a deadline. The answer comes back as text. Someone re-keys it into the catalog. Whatever shaped that answer evaporates when the tab closes.

Nobody audits that workflow, and nobody budgets for it.

The deeper problem is what the AI is reading: columns and tables instead of your approved business meaning. That’s how you end up with plausible answers about somebody else’s business. And because the recommendations are hard to inspect, approving one means rebuilding the reasoning yourself.

Human in the loop AI, as most products practice it, fixes none of this. It puts you at the end of a process holding an approve button. So where should you be? DeltaVault’s answer is that the human starts the loop. Your context enters at the first step and rides through every step after it. AI governance for data platforms begins there, not at the signature.

How DeltaVault runs every AI action through one loop

Five steps make up the loop, and the first two happen before you ask for anything. Context means your business categories, each marked as an event or a concept, plus your naming convention and your classification schemes. All of it lives under Settings and Conventions.

  1. Set the context. Business context for AI is authored once instead of pasted in each time, and every conventions-aware skill reads it.
  2. Bring in the content. Glossaries, requirements, source documentation, and domain notes go into the knowledge base.
  3. Describe the outcome. With those inputs grounded, you say what you want in plain language, and the Ask AI panel routes the request to the right published skill.
  4. Review the proposal. The AI proposes rather than acts. A model, a mapping, a relationship, a view, or a metadata change arrives as a plan you review item by item.
  5. Refine and approve. Edit a proposal, reject one, or say the change you want and read the result. Only what you approve is applied.

Whichever skill ran, the result returns as actions the product knows how to apply, not a paragraph you re-key. That write path is what makes DeltaVault an AI-native data platform rather than a catalog with a chat button.

The same five steps, whatever the AI is doing

The loop isn’t a modeling feature. It’s the shape of every AI action in the product. You learn it once and it holds everywhere.

  • Domain recommendations come back as selectable cards in the chat thread, and the run parks while you pick, spending nothing until you do.
  • The modeling workshop proposes concepts onto your model’s own canvas, each one carrying its reasoning. So you can accept, rename, move between lanes, or dismiss them one at a time.
  • Map & Match scores every suggested table or column match, attaches a written rationale, and writes the mapping only once you accept it.
  • Ask for a view in plain language and the proposal opens the view designer pre-populated, with nothing created until you save.
  • Ask the AI to tighten a knowledge document and the rewrite arrives as an inline diff you accept or reject change by change.

Because context and content come first, those proposals speak your language. A workshop run sorts what it finds into your own category lanes and titles each unit of work by its verb (“Customer places Sales Order”). It records why each concept earned its place. That’s what an AI data catalog looks like when it’s built to explain how reality became data instead of summarizing a schema. It’s the difference between metadata management you can audit and a chat panel you can only quote.

Refine feeds the next run

What changes on the second run? The last step feeds the first one. When you accept AI context alongside a proposal, every later run against that row inherits it, and so does every descendant. A column inherits from its table, an entity from its model and its domain. Re-run the domain skill and it updates what already exists instead of duplicating it. So the same request draws on more of your own decisions each time you make it.

The standards world frames trustworthy AI the same way. In the AI Risk Management Framework from the National Institute of Standards and Technology, governance runs through the whole lifecycle rather than arriving as a check at the end.

So start where the quality of everything downstream is decided. Open Settings, choose Conventions, and define your categories, because business context is a setting, not a prompt. The rest of the how we use AI series picks up the thread from there. It starts by giving the AI content rather than more prompts and then running the workshop through the last three steps on a model of your own.