> ## Documentation Index
> Fetch the complete documentation index at: https://docs.custral.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Post-conversation agents

> An AI agent that runs on its own after a call, email thread or chat completes, to create records, file bugs, update tasks or draft follow-ups.

## Overview

A **post-conversation agent** runs after a conversation completes and acts on what was said. Give it instructions like "If the caller mentions a bug, create a record in the Bugs object with a short title and the quote" and it does that on every matching call, email thread or chat, with no one in the loop.

It's a different thing from a [chat agent](https://docs.custral.com/ai/chat-agents/overview.md), which is a persona you talk to in the Stella chat.

![Settings → AI and automations → Agents → Post-conversation Agents → New agent.](https://docs.custral.com/images/screens/ai/post-conversation-agent-light.png)

Settings → AI and automations → Agents → Post-conversation Agents → New agent.

## How it works

* **It runs when a conversation completes**: someone marks it done, or Custral finishes analysing it and nothing is left to act on (no suggested actions waiting, no required scorecard review).
* **Once per conversation.** Each agent runs at most once on a conversation, however many times it completes.
* **Only on real content.** A conversation with nothing said in it (a silent call, a chat holding only a system notice) is skipped.
* **It reads the whole conversation.** The transcript or thread is its context, along with your instructions.
* **It acts without asking, within a fixed set of tools.** Nobody is there to approve a step, so its changes go through without the approval card Stella shows in chat. It can look things up in the workspace, create and update records, create, update and complete tasks, and update notes. It can't send email or texts, enroll anyone in a sequence, delete or archive anything, change settings or the schema, or browse the web. Write instructions that say exactly what it may create or change, and when to do nothing.

## Create one

**1. Open the tab**

Go to **Settings → AI and automations → Agents → Post-conversation Agents** and click **New agent**. Creating and changing agents needs the Admin role.

**2. Name it and write the instructions**

Fill in **Name**, and optionally **Description** and **Avatar emoji**. In **Instructions**, say what to do and when. **Generate with AI** drafts them from a sentence, or from the name and description if you leave it blank.

**3. Choose when it runs**

Leave **Run after conversation completes** on. **Restrict to channel types** limits it to **Calls**, **Email threads**, **SMS**, **Web chat** or **Slack**; leave it empty to run on every conversation type.

**4. Pick a model and save**

**Model** defaults to **Auto (follow workspace default)**. Leave **Enabled** on and click **Create agent**.

| Field | What it does |
| - | - |
| **Name** | Shown in the agents list. Required. |
| **Description**, **Avatar emoji** | Shown under and beside the name in the list. |
| **Instructions** | What the agent does after a conversation. Required. |
| **Model** | The model it runs on. Only enabled models are offered. |
| **Run after conversation completes** | Runs the agent every time a matching conversation completes. |
| **Manual only** | Keeps the agent from running on its own. Run it from a conversation's menu instead. |
| **Restrict to channel types** | Calls, Email threads, SMS, Web chat, Slack. Empty means all. |
| **Enabled** | Off pauses the agent without deleting it. |

The list shows each agent's **Triggers** (On completed, Manual), **Channels** and **Status**. Click a row to edit it. **Delete agent** is in the row's menu.

## Run one by hand

Open a conversation, click its `⋯` menu, and pick the agent under **Run agent**. Every enabled agent is listed; a Manual only agent carries a **Manual only** tag. Running one needs edit access to the workspace.

A toast says when it's done: what it did, that it found nothing to do, or why it couldn't finish. A run can take up to a minute. If it takes longer, the toast says it's still running, and its result appears on the agent's **Runs** tab.

## See what it did

An agent's **Runs** tab lists its runs, newest first: when it ran, whether by hand or after the conversation ended, the conversation's name, a one-line outcome, and a status.

| Status | Means |
| - | - |
| **Done** | It acted: created or changed something. |
| **Nothing** | It read the conversation and found nothing to do. |
| **Failed** | It couldn't finish. The outcome says why. |

Click a run to open its conversation. A conversation you can't open, or one that was deleted, reads "Conversation unavailable".

## Troubleshooting

| Symptom | Likely cause | What to check |
| - | - | - |
| The agent didn't run on a conversation | The conversation hasn't completed yet: it still has suggested actions waiting or a required scorecard review | Finish those, or mark the conversation done. |
| It ran on some conversations and not others | **Restrict to channel types** leaves those types out | Clear the list, or add the channel. |
| It never runs | **Enabled** is off, or **Run after conversation completes** is off (Manual only) | Turn both on, or run it from the conversation's menu (**Run agent**). |
| **Run agent** isn't in a conversation's menu | No agent is enabled | Turn on **Enabled** for the agent. |
| It skipped a call | Nothing was said on it | Expected. An agent only runs on a conversation with content. |
| It ran once and not again after the conversation reopened and completed | Each agent runs once per conversation | Expected. |
| It created something you didn't want | It acts without asking | Tighten **Instructions**: name the object, and say when to do nothing. |
| It said it would send an email or delete something, and didn't | Those tools aren't available to a post-conversation agent | Expected. Have it create a task for a person instead. |
| **New agent** is greyed out, or the modal opens as **View agent** | "Only workspace admins can create, change or delete AI agents." | Ask an admin. |
| Saving says "Name and instructions are required." | Name or Instructions is blank | Fill in both. |

> [!NOTE]
>
> When reporting an issue, include the request id shown in the error toast. It links the in-app error to the server logs.

## Related

* [Chat agents](https://docs.custral.com/ai/chat-agents/overview.md): personas you talk to in the Stella chat.
* [Routines](https://docs.custral.com/ai/routines/overview.md): Stella on a schedule, sending you the answer.
* [Instructions](https://docs.custral.com/ai/chat-agents/instructions.md): how to write agent instructions.
* [Models & Providers](https://docs.custral.com/ai/models/overview.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.