> 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/correcting-a-call-result.md).

# Correcting a call result

Correct the AI's result on a voice call when it got it wrong, explain why, and see who changed it and when.

After every call, the AI decides whether the call met its goal by checking it against your agent's [Call Objective](/ai-voice-agents/analyze-your-calls/post-call-analysis.md). When it gets one wrong, you can correct the result yourself, and your team sees who changed it, when and why.

***

## Before you start

* You can correct calls that have **ended**. Calls that didn't connect or have no analysis yet show **No verdict** and can't be corrected.
* To change a result you need permission to **edit voice agents**. Without it you still see the call's result and who corrected it, but you can't change it.

***

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-563950dcabab577868747722f7c0ec113b92d5aa%2Fvoice-agents-correct-call-result.mp4?alt=media>" %}

{% file src="/files/u7MBYcJMmIny5qLNiT4K" %}

**Step 1:** Open the call.

In the side menu, open **Voice Agents** → **Call History** (or open the agent and go to its call log). Click the call you want to correct; it opens in a new tab.

***

**Step 2:** Find the call result.

Under the call recording you'll see the result: **Goal met** or **Goal not met**. Next to it, a line tells you where the result comes from. While nobody has corrected it, it reads **According to the AI, judged against the agent's call objective.**

<figure><img src="https://3835013762-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-d49aab3b9075f5454023ad8694f8a70385476439%2Fvoice-agents-call-result-01-badge.png?alt=media" alt="The Goal not met result under the call recording, with the line According to the AI, judged against the agent&#x27;s call objective"><figcaption></figcaption></figure>

***

**Step 3:** Pick the right result.

Click the result to open its menu, then pick the other option. The current one has a check mark.

<figure><img src="https://3835013762-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-5799e6728e6195a33260e3c473588876ddbfff1b%2Fvoice-agents-call-result-02-menu.png?alt=media" alt="The result menu open with the options Goal met and Goal not met"><figcaption></figcaption></figure>

***

**Step 4:** Explain why you're changing it.

The **Call result** window opens. In **Why are you marking it as Met?** (or **Not met**), write what really happened in the call, in at least 10 characters. For example: *the lead confirmed the demo at the end of the call*. Your team sees this reason in the history.

<figure><img src="https://3835013762-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-dcad98d5d44a28473f27272aab0db10edc7ceffe%2Fvoice-agents-call-result-03-window.png?alt=media" alt="The Call result window with the reason field, the change history and the Mark as met button"><figcaption></figcaption></figure>

***

**Step 5:** Save the new result.

Click **Mark as met** (or **Mark as not met**). The result under the recording now shows your value with a pencil icon, and the line next to it reads **Corrected by** your name and the date. Hover over the result to see what the AI said originally.

In **Call History**, the call's result shows your value followed by **· corrected**.

***

## What your correction changes

* **The result Dapta shows and counts.** The call detail, **Call History**, its **Successful** filter and the success numbers on the **Voice Agents** page all use the corrected result.
* **Nothing is sent again.** Your webhooks, after-call destinations (Google Sheets, HubSpot, Dapta flows) and email notifications keep the result they received when the call ended.

{% hint style="warning" %}
**Re-analyzing a call puts back the AI's result.** The **Re-analyze** button next to **Summary** runs the AI analysis again, and the call then shows the AI's new result instead of your correction. Avoid re-analyzing a call you corrected. Your earlier correction stays in the history.
{% endhint %}

***

## Change history

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-7b7a687f740321f7eb667ba4ace80333f71ad3dc%2Fvoice-agents-call-result-history.mp4?alt=media>" %}

{% file src="/files/iEwi2w1W4vsRo7KyHAgj" %}

Every correction is kept in **History**, at the bottom of the **Call result** window: who changed it, the result before and after, when, and the reason. The author's name stays in the history even if that person later leaves the workspace.

To undo a correction, pick the other result again from the menu, or click **Back to** in the window, and give a reason. That adds a new entry; nothing is deleted.

{% hint style="info" %}
A correction doesn't analyze the call again. The summary and the data the AI extracted stay as they were; only the call's result changes.
{% endhint %}

***

## Next steps

{% content-ref url="/pages/XBht0aB2BJwGPG1Pt4oC" %}
[Post-call analysis](/ai-voice-agents/analyze-your-calls/post-call-analysis.md)
{% endcontent-ref %}

{% content-ref url="/pages/oNC9HlyGUVFeZ1aALA60" %}
[Giving Feedback on Calls](/ai-voice-agents/analyze-your-calls/giving-feedback-on-calls.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/correcting-a-call-result.md?ask=<question>&goal=<user_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.