[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Triage new Gladly conversations

> Tag each new Gladly conversation with the right Topic and route it to the right Inbox by your own rules. Runs daily, hosted, nothing to maintain.

Source: https://cotlet.dev/integrations/gladly-api-mcp-server/triage-new-conversations

Overnight emails land in the New tab of an Inbox, and a team manager opens each one just to pick a Topic and decide which Inbox should answer it.

Cotlet does it in your own Gladly account with list\_conversations, get\_conversation, list\_topics, list\_assignees, apply\_topics and assign\_conversation, called by your AI agent, an n8n workflow or a script.

[Sign up free](https://cotlet.dev/app/signup?app=gladly) [All Gladly tools](https://cotlet.dev/integrations/gladly-api-mcp-server.md)

Hosted · nothing to install or maintain

## Can Gladly do this on its own?

Gladly routes by Channel, Entry Point and Inbox, and its AI can classify Conversations (checked 20 Oct 2026). The REST API can set topics and assignee on a Conversation, but it has no list of New Conversations per Inbox and no MCP server. Nothing in Gladly applies your own Topic rules to a New queue from an AI agent in your own session.

## How you do it in Gladly today

1. Administrators and Team Managers click the New status tab on the home page to see the Conversations no Agent has picked up yet.
2. Open the Conversation and read the first message in the Conversation Timeline.
3. Click Topics at the bottom of the screen and pick the Topic that matches the reason for contact, searching by name when the list is long.
4. In the Customer Profile, click the Agent or Inbox name under Assigned To, type the target Inbox and click Assign.
5. Repeat for every New Conversation, because routing rules cannot read what the customer wrote in the message.

## How to triage new Gladly conversations

Prompt

```
Go through the New conversations in the Email Inbox. Apply the topic that fits each one and assign order questions to the Orders inbox. Leave anything unclear for me.
```

1. 01  
### Read the New queue  
The agent calls list\_conversations with status new for one Inbox. Only Administrators and Team Managers see the status tabs, so any other role stops the run before anything is tagged.
2. 02  
### Load the allowed Topics and Inboxes  
list\_topics returns the Topics with their parents, and list\_assignees the Inboxes and Agents. The agent only uses names from these two lists, so it never invents a Topic.
3. 03  
### Read each Conversation  
get\_conversation returns the timeline. The agent reads the customer's own words and quotes the sentence it based the Topic on, so you can check each choice.
4. 04  
### Tag and route the clear ones  
apply\_topics adds the most specific nested Topic, for example Exchange > Size, so reports roll it up to Exchange. assign\_conversation moves only the Conversations that match your routing rule. Assignment asks for your OK per call.
5. 05  
### Leave the rest alone  
A message that fits two Topics, or a Conversation another person assigned in the meantime, stays untouched and appears in the report with a one-line reason.

### What you get back

Example data

```
New in Email Inbox: 17
Tagged 14, assigned to Orders 6
Example: Marco Silva, "Where is my parcel?" -> Order Status, Orders inbox
Left for you 3:
- Dana Reyes: refund and wrong size in one message
- Ola Berg: only an attachment, no text
```

### Other ways to ask

- Every morning at 7, tag the New conversations in the Chat Inbox and list how many per Topic.
- Only read New conversations and suggest a Topic for each, but change nothing.
- Assign conversations that mention a damaged item to the Returns inbox and tag them Damaged Merchandise.
- Count the New conversations per Topic this week and tell me which Topic grew the most.

## What Gladly allows, and what to know first

- Gladly lists Conversations that no Agent has been assigned as New, and routes them when an Agent becomes available.
- Gladly Topics can be nested with a > separator, and a Conversation tagged with the child Topic rolls up to the parent in reporting.
- Gladly recommends applying a Topic to every Conversation even where it is not required, so reports show what customers contact you about.
- Reassigning a Conversation replaces the previous Agent or Inbox, and the change appears in the Conversation Timeline.
- Only Administrators and Team Managers see the status tabs of an Inbox.

assign\_conversation asks for your OK by default. To run it daily without you, switch confirmation off for that tool in your dashboard.

Sources: [Gladly Help: Conversation Status (New, Open, Waiting, Closed)](https://help.gladly.com/docs/conversation-status-new-open-waiting-closed) · [Gladly Help: Apply Topics to a Conversation](https://help.gladly.com/docs/apply-topics-to-a-conversation) · [Gladly Help: Assign Conversation to a Different Inbox or Agent](https://help.gladly.com/docs/assign-conversation-to-a-different-inbox-or-agent) · [Gladly developer docs: REST API](https://developer.gladly.com/rest/)

## Call apply\_topics from a script

curl

```
curl -X POST https://cotlet.dev/api/v1/gladly/conversations/HXRqKC5GSV-jAlq0-sxYTA/topics/apply \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"add":["Z_Oto7j-Sy2DlQdnZBDdDw"]}'
```

Example response

```
{
"conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
"topics": [
"Order Status"
]
}
```

MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is gladly\_write → apply\_topics. Example data.

[Schedule it in n8n, Make, Zapier or cron](https://cotlet.dev/integrations/gladly-api-mcp-server.md#automations)

## Gladly tools this automation uses

__Cotlet Gladly tools used to triage new Gladly conversations__
| Tool | Parameters |
| -------------------- | -------------------------------------- |
| list\_conversations | status, inbox\_id, cursor |
| get\_conversation | conversation\_id |
| list\_topics | none |
| list\_assignees | none |
| apply\_topics | conversation\_id, add, remove |
| assign\_conversation | conversation\_id, inbox\_id, agent\_id |

[All 13 Gladly tools with descriptions](https://cotlet.dev/integrations/gladly-api-mcp-server.md#tools)

## Frequently asked questions

### Can the agent create a new Topic?

No. Topics are set up by your administrators in Gladly, and the agent only uses Topics that list\_topics returns. A missing Topic goes in the report for you to add.

### Is it safe to connect Gladly to Cotlet?

Yes. You sign in to Gladly yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Gladly once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

## More Gladly automations

- [Close resolved Gladly conversations](https://cotlet.dev/integrations/gladly-api-mcp-server/close-resolved-conversations.md)
- [Create follow-up tasks in Gladly](https://cotlet.dev/integrations/gladly-api-mcp-server/create-follow-up-tasks.md)
- [Gladly API and MCP server: every tool](https://cotlet.dev/integrations/gladly-api-mcp-server.md)
- [All use cases](https://cotlet.dev/use-cases.md)

## Give your agent access to Gladly.

Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with Gladly.

[Sign up free](https://cotlet.dev/app/signup?app=gladly)

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.