Post-Call Analysis Setup and Configuration
Last updated: October 26, 2026
Post-call analysis turns each conversation into a set of fields you defined in advance. You set the analysis questions once, such as whether the visitor is qualified or how soon they plan to buy, and Docket Marketing Agent analyzes and answers them the same way for every conversation that follows.
Because the answers are values rather than prose, you can sort them on the dashboard, trigger alerts from them, and write them straight into your CRM.
Before you set up post-call analysis
You need access to app.docketai.com.
You need at least one Marketing Agent.
Decide which conversation details your team needs after each interaction.
If you plan to sync results to a CRM, confirm the relevant integration and field mapping first.
How to open Post Call Analysis in Docket
Log in to app.docketai.com.
Open Marketing Agent Configuration.
Select the agent you want to configure.
Open the Analysis and Actions tab.
Find Post Call Analysis.
The Post Call Analysis section is where you define what Docket should evaluate or extract from conversations.
Post-call analysis is configured per agent. Use separate analysis prompts when different agents need different qualification criteria, routing signals, or CRM-ready summaries.
Which fields should you create?
Create a field for anything your team currently digs out of a transcript by hand. If someone is reading conversations to find out whether a lead is worth calling, what they asked about, or how soon they need it, that is a field.
Common examples:
Field | What it should capture |
|---|---|
Qualification Status | Whether the visitor appears qualified based on your sales criteria. |
Product Interest | The product, feature, or use case the visitor asked about. |
Pain Points | The challenges or goals the visitor mentioned. |
Timeline | Any urgency, buying window, or implementation timing. |
Follow-Up Notes | A short summary for sales or customer-facing teams. |
Keep field names short and clear because they may appear in dashboards, reviews, or downstream systems. Creating Post-Call Analysis Fields covers the full creation steps.
How to write an effective field instruction
For each analysis field, write instructions that tell Docket exactly what to look for and how to format the answer.
Good instructions are:
Specific about the signal to extract.
Clear about the expected output format.
Focused on one field or decision at a time.
Grounded in the conversation transcript.
For example, instead of asking for "lead quality," ask Docket marketing agent to return one of a small set of statuses and explain which conversation signals should drive the choice.
Where do post-call analysis results appear?
Post-call analysis results appear on the Marketing Agents dashboard as extra columns.
Open the Marketing Agents dashboard.
Choose your agent from the agent menu. The dashboard opens on All Agents, and analysis columns stay hidden until you select a single agent.
Open the Visitors or Accounts tab.
Open the column menu at the right of the table header, then turn on the columns you want under Post Call Analysis Fields.
Once the columns are visible, check whether:
Fields are populated when the conversation contains the needed information.
Empty fields are reasonable when the visitor did not provide that information.
Output formats are consistent.
The extracted values are useful for follow-up and reporting.
If results are inconsistent, revise the field instructions before adding more fields.
How to connect analysis to follow-up
Post-call analysis becomes more useful when it feeds a follow-up workflow.
Use the rest of the Analysis and Actions tab to configure related workflows such as:
Post Call Actions
Post Call Alerts
Sync to Salesforce
Sync to HubSpot
Sync to Marketo
Sync to Dynamics 365
Before enabling CRM sync, confirm your integration is connected and the destination fields are mapped correctly.
How to verify post-call analysis is working
Save the prompt and confirm it appears in Post Call Analysis.
Run a controlled conversation containing the signal the prompt should evaluate.
End the conversation and wait for post-call processing to finish.
Review the extracted value and confirm it matches the configured data type and instruction.
Repeat with missing or ambiguous evidence to verify the fallback behavior.
Disable the prompt when its output is not reliable enough for alerts or CRM sync.
Best practices for post-call analysis
Start with a focused set of high-value fields.
Use controlled outputs when your team needs reporting consistency.
Avoid fields that ask for information the visitor is unlikely to provide.
Review early results before relying on the data operationally.
Update field instructions when your sales process or qualification criteria changes.
Troubleshooting post-call analysis
Issue | What to check |
|---|---|
Analysis field is empty | Confirm the conversation included the information the field asks for. |
Output is inconsistent | Make the instructions more specific and define the expected format. |
Field is not useful for follow-up | Rename, rewrite, or remove the field. |
CRM data is missing | Confirm the CRM integration and field mapping before troubleshooting sync behavior. |
Team receives too much low-value data | Reduce the number of fields and keep only actionable outputs. |
Analysis columns are missing from the dashboard | Select a single agent. The columns do not appear while the dashboard is set to All Agents. |
Older conversations are blank | A field only applies to conversations that happen after you create it. Docket does not fill in earlier conversations. |
Frequently asked questions
Why are the post-call analysis columns missing from my dashboard?
The dashboard opens on All Agents, and analysis columns only appear once you select a single agent. Choose your agent from the menu at the top left and the columns become available.
Will a new field fill in conversations that already happened?
No. A field applies only from the moment you save it, so define the fields you need before an agent goes live.
Why don't my fields appear as mappable options in the CRM settings?
A field has to exist in Post Call Analysis before it can be mapped. Create and save it first, then open the mapping configuration.
How is post-call analysis different from routing?
Post-call analysis runs after the conversation ends. Routing runs during the conversation. They are separate systems, so the same rule text can produce different results in each.
How long after a conversation do results appear?
Results appear once post-call processing finishes, which normally takes under a minute. Connected integrations can add to that.