Post-Call Analysis Data Types and Allowed Values
Last updated: August 10, 2026
Choose Text, Number, or Boolean when you create a Post-Call Analysis prompt. The data type controls the expected output and cannot be changed after the prompt is created.
Supported Data Types
Data type | Use for | Example instruction | Example output |
|---|---|---|---|
Text | Categories, summaries, names, or extracted details | Return one qualification category. |
|
Number | Scores, counts, quantities, or amounts | Score buying intent from 1 to 10. |
|
Boolean | A strict true-or-false decision | Return true if the visitor asked for pricing. |
|
Dates and timeframes are not separate data types. Capture them as Text unless your downstream workflow explicitly expects a numeric value.
Use Permitted Values with Text
Text prompts can include permitted values. Use them when the result must come from a fixed list for filtering, routing, or CRM mapping.
Example values for Qualification Status:
QualifiedNot QualifiedUnknown
Permitted values are not available for Number or Boolean prompts. For those types, define the expected numeric range or true/false condition in the instruction.
Write Type-Specific Instructions
Every instruction should identify the context to evaluate, the required output, and the missing-data behavior.
Text: Return one permitted value based on
@Conversation Data. ReturnUnknownwhen evidence is insufficient.Number: Return an integer from 1 to 10 based on buying-intent signals in
@Conversation Data. Return0when no signal is present.Boolean: Return
trueonly when the visitor explicitly asks to schedule a meeting; otherwise returnfalse.
Use Add Context or type @ to reference the available Conversation or Visitor data scopes.
Creation Rules
A prompt name is required and can contain up to 40 characters.
The instruction is required.
Prompt names must be unique for the agent.
The prompt's data type is fixed after creation.
The workspace response controls the maximum active prompts; the current client default is 10.
Verify the Output
Save the prompt and confirm it appears in Post Call Analysis.
Run a controlled conversation that should produce a known result.
End the conversation and review the extracted value.
Confirm the output matches the selected data type and any permitted values.
Repeat with missing or ambiguous input to verify the fallback behavior.