Skip to main content
DialNexa post-call analysis extracts structured fields from a completed call. Define the extraction fields here; review the extracted values per call in Post-Call Analysis Results. Users can add, edit, delete, and reorder text, selector, boolean, number, and DateTime fields so Call History and exports show outcomes such as summary, call result, customer interest, age, qualification, callback time, or next step. DialNexa Post-Call Analysis settings panel showing a custom Demo Date and Time field with edit, delete, and add controls.
If operations needs a column later, define the field before the campaign. Future-you has enough to do.

​
Supported Field Types

Choose the type that matches the value you need.
TypeBest forExample
TextFree-form summaries or notes.call_summary
SelectorOne value from a known set.call_outcome: Resolved, Escalated, Follow-up Required
BooleanTrue or false outcomes.customer_interested
NumberNumeric values.customer_age or payment amount
DateTimeCallback, appointment, renewal, or follow-up timing.callback_datetime returned as UTC ISO 8601, such as 2024-06-17T10:30:00Z
Use DateTime when another system or a workflow needs a schedulable time. In the field description, ask for the value in UTC ISO 8601 format so the extracted result can be parsed consistently. DialNexa Post Call Analysis add menu showing Text, Selector, Boolean, Number, and Date and Time field types.

​
Where Results Appear

Post-call fields become operational data after the call.

Call detail custom section

Custom extracted values appear on the call detail page.

CSV exports

Exports can include extracted fields for reporting.

Workflow decisions

Workflow paths can reason about call attributes when configured.

QA review

Annotations and transcript review can explain why a field was wrong.

​
Post-Call Extraction LLM

The Post Call Analysis panel includes a model settings control for the LLM used by post-call extraction. This is separate from the live conversation model so teams can tune completed-call extraction without changing how the agent speaks during the call. DialNexa Post Call Analysis LLM settings popover showing GPT model choices for post-call extraction.
SettingBehavior
DefaultDialNexa selects GPT-4.1 when it is available.
Allowed dashboard choicesGPT-5.4 Mini, GPT-5.4 Nano, GPT-4.1, GPT-4.1 Nano, and GPT-4o Mini.
Published versionsPublished versions can disable edits. Update a draft version before changing extraction fields or extraction model.
API fieldIntegrations can set post_call_analysis_llm_id when creating or updating agents.
Use a stronger extraction model when the transcript is long, the fields depend on reasoning across multiple turns, or selector values need careful evidence. Keep the live model and post-call extraction model aligned only when you want both tasks to share the same cost and behavior profile.

​
Write Strong Extraction Fields

1

Name the field like a column

Use names that will make sense in exports.
2

Describe the evidence

Tell the extractor exactly what part of the conversation proves the value.
3

Use selector options for finite outcomes

Do not ask for free text when operations needs a clean report.
4

Use DateTime for schedulable callbacks

Ask for UTC ISO 8601 output when the caller gives a callback time, appointment time, or other follow-up date.
5

Test on real calls

Check whether the transcript contains the evidence needed to extract the field.

​
Extraction Problems

The transcript may not contain the fact, or the description may be too vague.
Use clearer allowed options and descriptions.
Define what counts as true and false.
Use the DateTime field type and describe the expected UTC ISO 8601 output. Workflow Time nodes should point at a DateTime PCA field.
Published versions protect live settings. Edit a draft version.

Post-Call Analysis Results

Review extracted fields.

Exporting Call Data

Export analysis columns.

Call Detail Page

Inspect one call.