Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions agent/slack.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@

## Connect additional integrations from Slack

Once your Slack workspace is connected, you can ask the agent in Slack to set up any third-party integration that it should use as context. The agent uses [Composio](https://docs.composio.dev/toolkits) to support a broad catalog of third-party services, including issue trackers, knowledge bases, CRMs, and developer tools.

Check warning on line 37 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L37

In general, use active voice instead of passive voice ('is connected').

Check warning on line 37 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L37

Did you really mean 'CRMs'?

To add a new integration from Slack:

Expand All @@ -46,7 +46,7 @@
3. Click the link, sign in to the third-party service, and approve the requested permissions.
4. Return to Slack. The agent confirms the connection and can immediately use the integration as context for future requests.

Integrations that you connect from Slack are scoped to individual Slack users, so each teammate sets up their own connections and the agent uses the connections of whoever sent the message. If a Slack user has not connected a service, the agent falls back to the organization-level integrations installed from the [Agent](https://dashboard.mintlify.com/products/agent) page in the dashboard.

Check warning on line 49 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L49

In general, use active voice instead of passive voice ('are scoped').

To remove or reauthorize an organization-level integration, use the **Agent settings** section of the [Agent](https://dashboard.mintlify.com/products/agent) page.

Expand All @@ -71,7 +71,7 @@

Example questions:
- "Which pages mention the API rate limit?"
- "How do I set up authentication?"

Check warning on line 74 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L74

Avoid first-person pronouns such as ' I '.
- "How is our navigation structured?"

## Update documentation
Expand All @@ -96,7 +96,7 @@
- "Document the new endpoints added in `acme/backend#1234`."
- "What repositories do you have access to?"

Cloned repositories are read-only. The agent uses them for context, but always opens pull requests against your documentation repository.

Check warning on line 99 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L99

In general, use active voice instead of passive voice ('are read').

## Track progress in real time

Expand All @@ -105,6 +105,7 @@
- **Status updates**: A live-updating message shows what the agent is doing, such as how many files it has searched, read, and edited.
- **Task progress**: When the agent breaks your request into multiple tasks, it displays a checklist so you can track progress on each one.
- **Questions**: If the agent needs more information, it presents options for you to select from or reply in the thread with a custom answer.
- **Permission requests**: Before the agent runs a third-party action that writes data, such as sending an email or creating a ticket, it asks you to approve or deny the action. The approval card is sent as an ephemeral message visible only to you, the person who triggered the request, so other thread participants are not interrupted. Click **Approve** to let the agent proceed or **Deny** to cancel the action.

Check warning on line 108 in agent/slack.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

agent/slack.mdx#L108

In general, use active voice instead of passive voice ('is sent').
- **Interruptions**: If you send a follow-up message while the agent is still working, it stops the current task and starts on the new one.
- **Completion**: When the agent finishes, it posts a summary with a link to the pull request and a link to open the changes in the web editor.

Expand Down
1 change: 1 addition & 0 deletions es/agent/slack.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@ Mientras el agente trabaja en tu solicitud, proporciona retroalimentación en vi
- **Actualizaciones de estado**: Un mensaje que se actualiza en vivo muestra lo que el agente está haciendo, como cuántos archivos ha buscado, leído y editado.
- **Progreso de las tareas**: Cuando el agente divide tu solicitud en varias tareas, muestra una lista de verificación para que puedas seguir el progreso de cada una.
- **Preguntas**: Si el agente necesita más información, presenta opciones para que selecciones o respondas en el hilo con una respuesta personalizada.
- **Solicitudes de permiso**: Antes de que el agente ejecute una acción de terceros que escribe datos, como enviar un correo o crear un ticket, te pide que apruebes o rechaces la acción. La tarjeta de aprobación se envía como un mensaje efímero visible solo para ti, la persona que activó la solicitud, para no interrumpir a otros participantes del hilo. Haz clic en **Approve** para que el agente continúe o en **Deny** para cancelar la acción.
- **Interrupciones**: Si envías un mensaje de seguimiento mientras el agente aún está trabajando, detiene la tarea actual y comienza con la nueva.
- **Finalización**: Cuando el agente termina, publica un resumen con un enlace a la solicitud de extracción y un enlace para abrir los cambios en el editor web.

Expand Down
1 change: 1 addition & 0 deletions fr/agent/slack.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,7 @@ Pendant que l'agent travaille sur votre demande, il fournit un retour en direct
- **Mises à jour de statut** : Un message mis à jour en direct indique ce que l'agent est en train de faire, comme le nombre de fichiers qu'il a recherchés, lus et modifiés.
- **Progression des tâches** : Lorsque l'agent décompose votre demande en plusieurs tâches, il affiche une liste de contrôle pour que vous puissiez suivre la progression de chacune.
- **Questions** : Si l'agent a besoin de plus d'informations, il présente des options parmi lesquelles vous pouvez choisir ou vous pouvez répondre dans le fil avec une réponse personnalisée.
- **Demandes d'autorisation** : Avant que l'agent n'exécute une action tierce qui écrit des données, comme envoyer un e-mail ou créer un ticket, il vous demande d'approuver ou de refuser l'action. La carte d'approbation est envoyée sous forme de message éphémère visible uniquement par vous, la personne qui a déclenché la demande, afin de ne pas interrompre les autres participants du fil. Cliquez sur **Approve** pour laisser l'agent continuer ou sur **Deny** pour annuler l'action.
- **Interruptions** : Si vous envoyez un message de suivi pendant que l'agent travaille encore, il arrête la tâche en cours et commence la nouvelle.
- **Achèvement** : Lorsque l'agent a terminé, il publie un résumé avec un lien vers la pull request (demande de fusion) et un lien pour ouvrir les modifications dans l'éditeur web.

Expand Down
1 change: 1 addition & 0 deletions zh/agent/slack.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,7 @@ keywords: ["Slack 集成", "Slack 机器人", "团队协作", "agent 集成", "
- **状态更新**:一条实时更新的消息会显示智能体正在执行的操作,例如已搜索、读取和编辑了多少文件。
- **任务进度**:当智能体将你的请求拆分为多个任务时,它会显示一个清单,以便你跟踪每个任务的进度。
- **提问**:如果智能体需要更多信息,它会列出选项供你选择,或者你可以在线程中回复自定义答案。
- **权限请求**:在智能体执行需要写入数据的第三方操作之前(例如发送邮件或创建工单),它会请求你批准或拒绝该操作。审批卡片以临时消息的形式发送,仅对你(即发起请求的人)可见,因此不会打扰线程中的其他参与者。点击 **Approve** 让智能体继续执行,或点击 **Deny** 取消该操作。
- **中断**:如果你在智能体仍在工作时发送后续消息,它会停止当前任务并开始处理新任务。
- **完成**:当智能体完成后,它会发布一份摘要,其中包含指向拉取请求(PR)的链接和在 Web 编辑器中打开更改的链接。

Expand Down
Loading