Agentic AI Capability

Juno indexes your tables, your values and your words.

Before Juno can map a column or understand a question, it needs to know what your estate holds.

WHAT IS REGISTEREDTHE KNOWLEDGE INDEXWHAT READS ITRegistered tables23 tables, five systemsColumns and keys412 columns describedColumn valuespatterns and countsYour wordsvocabulary and aliasesAutomatic mappinga proposal with a reasonChatLimathe objects in a questionLinkingone thing in two systemsTrainingyour words join the index01The table and columnindexevery registered table andcolumn, with its type andits keys02The value indexthe patterns, the rangesand the distinct values ineach column03Thebusiness-languageindexthe same tables and columnsin your words, withsynonymsrefreshed by each sync scan and each training run
The index sits between what is registered and everything that reads it: mapping, questions, linking and training. Showcase estate.
412
columns indexed from 23 tables in the showcase estate
showcase estate
3
indexes: the tables and columns, the values, the business language
product
9,340
distinct supplier numbers profiled in one column
showcase estate
Nightly
the index refreshes with each sync scan and each training run
product
Where this sits

Stage 2 of six: map

Step by step

How the index is built from a registered table

Two steps read the data description, two add language, and the last keeps it current.

FROM A REGISTERED TABLE TO AN INDEX JUNO CAN SEARCH01Read thedescriptionnames, types, keys and asample02Profile the valuesthe pattern, the range andthe distinct count03Expand the namesMENGE becomes “quantity”,LGORT “storage location”04Index your wordsyour vocabulary, acronymsand aliases05Publish andrefresheach scan and eachtraining run updates iteach confirmed mapping and each correction strengthens the next proposal
The first two steps read what the source already says about itself. The third and fourth add language, and the last keeps the index current as your estate changes.

Registration recorded the description of each table: the names, the data types, the keys, the row count and a sample of values. The index starts there, with one entry per table and one per column.

Juno then profiles each column from the sample: the pattern the values follow, the range they cover and how many distinct values there are. A column of ten-digit numbers that joins to the supplier table looks very different from a column of dates.

Names come next. Technical names are expanded into business words from a dictionary of common systems and abbreviations, so MENGE becomes “quantity” and LGORT becomes “storage location”. Your own aliases and synonyms join the same entry when you teach them.

The result is published as one searchable record. It refreshes when a sync scan adopts a change, when a training run adds vocabulary, and when your team confirms or corrects a mapping.

The three indexes

What each one holds and what reads it

Three records of the same estate: its structure, its values and its language.

Every table and column

The structure: table names, column names, data types, lengths, keys and the joins between tables. This is what the mapping stage compares with the ontology.

The values in each column

The pattern, the range and the distinct values in each column, read from the sample. This is what recognises a supplier number, a plant code or a location.

Names in business language

The same tables and columns in the words your people use, with synonyms, acronyms and the aliases your team teaches. This is what a question is matched against.

The index holds the description and a sample. The rows stay in the source system. Product.

On screen

How “L04542” is recognised as a location

A value a person types is searched across every indexed column, with the shape of the values as the evidence.

Knowledge index · value lookup · “L04542” · showcase estate
Column that carries this valueDistinct valuesPatternRows that matchOntology attribute
Warehouse system · STOCK.LOCATION_ID1,284L + five digits3,912Location · location code
SAP · LIPS.LGORT_EXT1,284L + five digits1,204Location · location code
Supplier portal · SHIP_TO_LOC860L + five digits112Location · location code
SAP · MARD.LGORT46four characters0Storage location · code

One value, looked up across every indexed column. Showcase estate.

A person typing “how much stock sits at L04542” uses a value, so Juno searches the value index for it. Three columns in three systems carry values of that shape, and all three map to the location code of the ontology. The storage location column has a different shape and a different meaning, so it stays out of the answer.

The same lookup works for a supplier name, a material number, a plant or a customer. It is the step that turns a value a person knows into the business object Juno holds, and it runs before a query is written.

Refresh

Four moments update the index

The index is a living record, so a mapping proposed today rests on what your estate holds today.

A data set is registeredEach newly registered table is described and profiled the same day, and its entry joins the index.
A sync scan is adoptedAn adopted column is profiled and indexed; a column that left the source is marked on its entry.
A training run finishesYour vocabulary, your acronyms and your table and column aliases join the business-language index.
A mapping is confirmed or correctedEach decision your team makes is kept on the entry and becomes evidence for the next proposal.
The running example

Monday 11:20: 412 columns become one searchable record

Showcase estate.

The running example

A. Novak registered 23 tables by 10:07 on Monday. The index run that followed read every column, profiled the values in each one and expanded the technical names. It found 9,340 distinct supplier numbers in one SAP column and the same ten-digit shape in the Oracle supplier column of the acquired division.

That record is what made the rest of the week quick. Mapping proposals arrived at 08:30 on Tuesday with the value evidence behind them. When L. Tan asked her question on Wednesday, “NCNR” and the plant code in it were matched against the same index, and the query went to the right tables at the first attempt.

Next capability

Linking the same thing across systems

How Juno recognises that a supplier in SAP, in Oracle and on the portal is one supplier, and how much of the data agrees.

Terms on this page
Knowledge indexJuno’s record of your registered estate: its tables and columns, its values and its business language.
Value profileWhat Juno learned about one column from a sample: the pattern, the range and the distinct count.
PatternThe shape the values in a column follow, such as ten digits, or the letter L and five digits.
Business languageThe words your people use for a table or a column, with their synonyms and acronyms.
AliasA name your team gives a table or a column so questions can use it.
Index refreshThe run that brings the index up to date after registration, a sync scan or a training run.
Questions
Does the index hold our data?

It holds the description of each table and what a sample of values looks like: the pattern, the range and the distinct count. The rows stay in the source system and are read when a question or a rule needs them.

How large is the sample?

Enough to recognise the shape of a column, and it follows the access rights of the connection. Your team sets the size per data set, and a column your policy keeps out of the sample is described by its name and type alone.

What happens with a column of free text?

It is indexed by name and type, and the value profile records that the values vary. Columns like that are usually mapped by a person, and your aliases carry most of the meaning.

Can we search the index ourselves?

Yes. The catalogue screen searches it by table, by column, by value and by business word, which is how a data lead answers where a field lives and who owns it.

In the platform

Where Juno sits among the four capabilities

Each one builds on the one before it.

One shared foundationCatalogLineageAccess policyWrite path

See Juno answer and act on your own data

Bring two systems and one decision your planners make every week. In the first week we register the data, confirm the mapping with your team, answer your questions in ChatLima and run the first agent at the level you choose.