> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/ai-voice-agents/analyze-your-calls/post-call-analysis.md). # Post-call analysis The Call Analysis tab of a voice agent: what the AI checks after every call, which data it pulls out of the conversation, and where the results go. When a call ends, your voice agent's work isn't over. The **Call Analysis** tab decides what the AI checks about each call, which answers it pulls out of the conversation, and where those results go next. {% embed url="" %} {% file src="/files/7ctSkoqZTnz5MsaJeccJ" %} *** ## Where to find it Open **Voice Agents**, choose an agent and open the **Call Analysis** tab. Everything on this page lives in its **Post-Call Analysis** column. The agent's prompt stays on the right, so you can check your objective against it. | Section | What it does | Details | | ---------------------------------- | ----------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | | **Call Objective** | Describes a successful call. The AI scores every call against it. | Step 1 below | | **Data Retrieval from your Calls** | The answers the AI extracts from each call: text, selector, yes/no or number. | [Post-Call Data Retrieval](/ai-voice-agents/analyze-your-calls/post-call-analysis-post-call-data-retrieval.md) | | **After-call destinations** | Sends each call's results to Google Sheets, HubSpot or a Dapta flow. | [Destinations](/ai-voice-agents/analyze-your-calls/post-call-analysis-destinations.md) | | **Notifications** | Emails someone when a variable meets a condition you set. | [Notifications](/ai-voice-agents/analyze-your-calls/post-call-analysis-notifications.md) | | **Scheduled email report** | A daily email of the agent's call performance. | [Notifications](/ai-voice-agents/analyze-your-calls/post-call-analysis-notifications.md) | *** **Step 1:** Describe a successful call in **Call Objective**. Write it the way you would brief someone reviewing the call: what has to happen for the call to count as a win. For example, *the lead agreed to a 10-minute demo and confirmed a day and time*. The AI evaluates every call against it automatically. **Improve with AI** rewrites your objective so it is specific and consistent with the data you extract and the agent's prompt. Review the suggestion, then click **Use this version** or **Discard**. Click **Save changes** to keep the objective. *** **Step 2:** Choose the data to extract. Under **Data Retrieval from your Calls**, click **Add Variable** and pick a type: | Type | Use it for | Example | | ------------ | --------------------------------- | -------------------------------------------- | | **Text** | Open answers | The reason for the call | | **Selector** | One answer from a list you define | Interest level: high, medium or low | | **Boolean** | Yes or no | `demo_booked`: did the lead agree to a demo? | | **Number** | A quantity | How many seats the lead asked about | Give the variable a **Name**, such as `demo_booked`, and an **Instruction**: the question the AI answers from the conversation. Text variables also take an optional format example, and selectors take their list of choices. **Confirm** saves the variable to the agent right away. Every variable you add becomes call data you can send to a destination or use as a notification condition. More on each type in [Post-Call Data Retrieval](/ai-voice-agents/analyze-your-calls/post-call-analysis-post-call-data-retrieval.md). *** **Step 3:** Send the results where your team works. **After-call destinations** send every call's results to Google Sheets, HubSpot or a Dapta flow as soon as the call ends: the contact's details, the variables you extracted, the summary and the transcript. Set them up in [Destinations](/ai-voice-agents/analyze-your-calls/post-call-analysis-destinations.md). *** **Step 4:** Get an alert, or a daily report. **Notifications** email a recipient when a variable matches a value, for example when `demo_booked` equals *Yes*. The **Scheduled email report** sends a daily summary of the agent's calls. Both are explained in [Notifications](/ai-voice-agents/analyze-your-calls/post-call-analysis-notifications.md). {% hint style="info" %} **What saves when:** variables and destinations are saved the moment you confirm them. The call objective is saved with **Save changes** at the top right. {% endhint %} *** ## Next steps {% content-ref url="/pages/nIdByf9nkUCuT4zoF0eh" %} [Post Call Analysis – Destinations](/ai-voice-agents/analyze-your-calls/post-call-analysis-destinations.md) {% endcontent-ref %} {% content-ref url="/pages/gxhpP1yhijCQc9bCFjp5" %} [Post Call Analysis – Post-Call Data Retrieval](/ai-voice-agents/analyze-your-calls/post-call-analysis-post-call-data-retrieval.md) {% endcontent-ref %} {% content-ref url="/pages/kw78x5OsUQnH6W4FSCDY" %} [Post Call Analysis – Notifications](/ai-voice-agents/analyze-your-calls/post-call-analysis-notifications.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.dapta.ai/ai-voice-agents/analyze-your-calls/post-call-analysis.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.