Agentic AI Capability

Teach Juno your company’s words once; everyone benefits.

Every company has its own words: acronyms on a purchase order screen, a short form a planner types every day, a table name that means one thing in purchasing and another in logistics.

WHAT YOU SUPPLYWHAT TRAINING DOESWHAT THE WORDS SERVERegistered tablesnames, types, samplesVocabulary fileyour company termsAcronym listNCNR · OTIF · DOSAbbreviationsshort forms, expandedCustom aliasesyour name for a columnChatLimaplain-language questionsTask agentspolicies in your wordsSmartAppsapproval queues and clocksPower BIthe same terms in reportsYour correctionsreturn as training input01Read thedescriptionstables, columns, keys02Profile the valueswhat lives in each column03Expand short namesMENGE reads as quantity04Attach your wordsaliases and synonyms05Match the ontologyattribute by attribute06Publish a versiondated and reversibletraining runs again when a term or an alias changes
The words you supply become part of the knowledge index, and the index serves every surface that asks a question. Showcase estate.
4
plain stages take a company vocabulary into production
product
10
training steps sit behind those four stages
product
96
terms, acronyms and aliases in the showcase estate’s first vocabulary file
showcase estate
18 min
for one training run across 23 registered tables
showcase estate
Where this sits

Stage 4 of six: teach

Step by step

Four stages take your vocabulary into production

Stages one, two and four belong to your team; stage three belongs to Juno and runs in the background.

FROM A COMPANY GLOSSARY TO ANSWERS IN YOUR WORDS01Choose the scopethe registered tables and thecolumns in daily use02Give the wordsvocabulary, acronyms,abbreviations, aliases03Run the training taskthe knowledge index is rebuilt inthe background04Correct and repeatdownload the result, adjust it,upload it, run againa new term, a new alias or a new table starts the four stages again
The loop at the bottom is the normal state of affairs: vocabularies grow, and each addition takes minutes.

Stage one sets the scope. Your data lead picks the registered tables that people ask about and marks the columns in daily use. Juno reads the description of each table and profiles the values in the marked columns, so it learns which column holds supplier numbers and which holds plant codes.

Stage two is the words themselves. Four kinds of input go in: a vocabulary file of company terms, a list of acronyms with their expansions, a list of abbreviations, and custom aliases that give a table or a column the business name your people use. Each entry keeps the name of the person who added it.

Stage three runs the training task. Juno rebuilds the knowledge index: every table and column, the values in each column, and the names in business language with your synonyms attached. People carry on asking questions while the task runs, and the new version takes over when it finishes.

Stage four closes the loop. The result downloads as a working file, your team corrects what reads oddly, and the corrected file goes back in. Each published version is dated, carries an author and can be restored, so a vocabulary change is as reviewable as a rule change.

The inputs

Four kinds of input, each one a plain file or a screen entry

The four inputs arrive as spreadsheets or through the vocabulary screen; both routes end in the same list.

Vocabulary file

Company terms with a short meaning for each: “push-out”, “allocation-bound”, “firm zone”.

Known acronyms

The short forms your people type, each with the words it stands for: NCNR, OTIF, DOS, ASN.

Abbreviations

Shortened words that appear in field names and in typed questions, with their expansions.

Custom aliases

A business name for a table or a column, so a question can use the word your team uses.

TermWhat it means in this companyKindAdded byWhen
NCNRNon-cancellable, non-returnable: a line the supplier holds to the agreed dateAcronymD. OkaforThu 09:00
LT fenceLead-time fence: the date inside which the plan stays firmAbbreviationL. TanThu 09:20
“strat supplier”The strategic class on the supplier recordAliasP. SharmaThu 09:40
DOSDays of supply: stock divided by average daily demandAcronymL. TanThu 09:48
“cxl window”The days in which a purchase order line may still be cancelledAliasD. OkaforThu 10:04
“push-out”A customer moving an agreed delivery date laterVocabularyJ. RidleyFri 08:30

Six of the 96 entries in the showcase estate’s first vocabulary file, which P. Sharma owns and reviews. Showcase estate.

The training task

Ten steps, and your team owns six of them

The task runs in the background, so people keep asking questions while a new version is prepared.

StageStepWhat happensWho
Choose the scope01 Pick the tablesThe registered tables people ask about join the training setData lead
02 Mark the columnsColumns in daily use are marked; the rest stay in the catalogueData lead
03 Profile the valuesJuno reads a sample and records the pattern of each columnJuno
Give the words04 Load the vocabularyCompany terms with their meanings enter the listDomain owner
05 Load the acronymsEach short form is stored with the words it stands forDomain owner
06 Load the abbreviationsShortened words used in fields and questions are expandedDomain owner
07 Add aliasesTables and columns receive the business names your team usesDomain owner
Run the task08 TrainThe knowledge index is rebuilt and matched to the ontologyJuno
Correct and repeat09 Download the resultThe proposed meanings arrive as one working fileData lead
10 Correct and uploadThe corrected file goes back in and training runs againData lead

Steps three and eight belong to Juno. The other eight are your team’s, and they are the reason the result sounds like your company. A first pass over a purchasing estate takes an afternoon; later passes take minutes, because only the changed tables need a fresh run.

Where the words land

One vocabulary serves questions, agents and screens

A term taught once is live for every person and every agent on the next question.

ChatLima · after trainingshowcase estate
LT
Show me the NCNR lines in this week’s excess list for plant 1210.
L
Eleven purchase order lines carry the non-cancellable, non-returnable flag. Their value is $96,400, and the supplier holds them to the agreed date.
SupplierLinesValue
Delta Fasteners Ltd6$54,200
Corvid Plastics3$28,900
Two others2$13,300
NCNR → non-cancellable, non-returnablePurchase order linePlant 1210
3.8 sSAP S/4HANA · planning suitevocabulary v2
QuestionsA typed acronym is understood on the first try, and the answer shows which term it used.
Agent policiesA policy sentence may say “keep NCNR lines”, and the rules engine reads the same definition.
Approval screensQueues in SmartApps label lines with the words buyers already use.
ReportsThe Power BI connector carries the same names, so one term means one thing everywhere.
The audit trailEach answer records the vocabulary version it used, so an old answer stays explainable.
The running example

Thursday morning: three words that changed the answers

Showcase estate.

The running example

On Wednesday L. Tan asked which open purchase order lines were still inside their cancellation window that week: 31 lines worth $348,000. Two follow-up answers came back wider than expected, because the questions used words Juno had yet to learn: the NCNR flag D. Okafor writes on a supplier note, and the “LT fence” L. Tan works to every week.

On Thursday D. Okafor added NCNR to the acronym list at 09:00, L. Tan added the lead-time fence at 09:20, and P. Sharma added the alias for the strategic supplier class at 09:40. P. Sharma owns the vocabulary file and reviewed all three entries. The training task ran in the background at 10:30, over four purchasing tables, in six minutes. By 10:40 the same question returned the 31 lines with the 11 NCNR lines marked, and the cancellation policy written on Friday read the supplier class through the same vocabulary.

Next capability

Feedback that improves the next answer

What a thumbs-up records, what a correction changes, and how a verified pair becomes the answer everyone sees.

How this is usually done

A glossary project that starts from an empty page

The work moves from writing a model to teaching the words your company already uses.

Most tools that answer questions over data ask for a semantic model and a business glossary written by hand before the first question. Practitioners describe the preparation for a large estate in quarters, and every new source starts the exercise again. The glossary then drifts, because the people who own the words work far from the people who maintain the model.

Juno starts with the supply chain ontology already in place, so training adds your words to a map that exists. The people who own a term add it themselves, in a file or on a screen, and see the effect on the next question.

Terms on this page
Vocabulary fileA list of your company’s terms, each with a short meaning, loaded into training.
Acronym listThe short forms your people type, each stored with the words it stands for.
Custom aliasA business name given to a table or a column, so questions can use your own word.
SynonymA second word that carries the same meaning as an ontology term in your company.
Knowledge indexJuno’s record of your tables, the values in each column, and the names in business language.
Training taskThe background run that rebuilds the knowledge index from your tables and your words.
Questions
Who supplies the vocabulary?

The people who use the words: a planner, a buyer, a master-data steward. Your data lead collects the files, and each entry keeps the name of the person who added it.

How long does a training run take?

Minutes for a few dozen tables. In the showcase estate 23 tables took 18 minutes as a background task, and people carried on asking questions throughout.

What happens when we add a term later?

You add the entry and run training again for the tables it touches. The word is live from the next question, and the earlier version stays available for restore.

Does our vocabulary leave our estate?

Table names, column names and your vocabulary may reach the external model at design time. Row data stays inside your estate. The trust page states the boundary rule in full.

Can two teams keep different words for one thing?

Yes. A term can carry a scope, so purchasing and logistics each keep their own word for the same ontology attribute, and both questions are answered correctly.

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.