Field meaning
What an agent calls a field, and what it understands the value to mean. You set all of it in the field picker’s Meaning column, one field at a time or many at once.
Meaning: label, instruction, synonyms
The Meaning column opens one editor per field. A filled glyph means the field already carries something.
To write meanings for many fields at once, click Show Meaning. The level, filter, write and create columns give way to an editable Meaning box per row, beside the field’s help text from Salesforce Setup.
Click the arrow to copy that help text across as the field’s meaning, or the cross to clear what’s there. Show Config brings the checkboxes back.
You choose what to copy, field by field. Help text is often written for someone looking at a form — “click the lookup to pick an account” — the least useful sentence an agent can read. ContextWorks versions what you keep, like any other edit.
| Slot | Use it for |
|---|---|
| Label | What the agent should call this field |
| Instruction | What the value means here → Instructions |
| Synonyms | What people call it, comma-separated |
Synonyms let an agent match the word a user actually typed: put commit, upside, and at risk on a forecast field and a question using any of them resolves. They reach the agent through Get Catalog, so they cost nothing in a payload.
Rename a field for the agent
Set a Label to have the agent read a field by your org’s name for it — Amount as Contract Value, say.
The API name never changes. Get Catalog shows it in its own column beside the label, because filters and writes still speak API names. The picker shows the Salesforce label in grey next to any override, so you can still find the field in setup.
Rename only where the Salesforce label genuinely misleads. A relabel ships with the next Activate, and every agent reading that entity sees the new word.
What’s next
- Instructions — what to write in the Instruction slot, with examples
- Fields — choosing which fields appear, and at which level