[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)

# Close resolved Trengo conversations with AI

> Close Trengo conversations the customer has settled and set reminders on the ones still waiting, every Friday, by your own rule.

Source: https://cotlet.dev/integrations/trengo-api-mcp-server/close-resolved-conversations

Conversations sit in Assigned to me long after your team wrote last, and nobody closes them until someone sorts the folder by hand.

Cotlet does it in your own Trengo account with list\_conversations, get\_conversation, set\_reminder and close\_conversation, called by your AI agent, an n8n workflow or a script.

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

Hosted · nothing to install or maintain

## Can Trengo do this on its own?

Trengo closes a conversation when an agent clicks it, in bulk for up to 50 at a time, or through a rule with the action Close ticket (checked 20 Oct 2026). A rule can combine Last message direction equals outbound with Elapsed time is 5 hours, so it closes on silence, not on what the customer wrote. Nothing in Trengo reads the thread to see whether the matter is settled.

## How you do it in Trengo today

1. An agent opens Inbox > Assigned to me and opens each conversation to see who wrote last.
2. If the customer has what they need, the agent clicks the checkmark above the ticket, or sends a last message with Send and close.
3. To close many at once, the agent clicks the coloured circles in front of the tickets, or the circle left of With selected to take 50, and picks an action from the arrow.
4. For a conversation that waits for the customer, the agent clicks the Bell icon and picks a date and time; the ticket moves to the Reminders folder and comes back then.
5. Deciding which conversations are really finished is still a read of each thread, so the folder grows between sorting sessions.

## How to close resolved Trengo conversations with AI

Prompt

```
Every Friday, go through my Trengo conversations where our team wrote last more than 3 days ago. Close the ones where the customer confirmed it worked, set a reminder for Monday 9:00 on the ones still waiting for the customer, and skip any with a note to wait.
```

1. 01  
### Find the quiet ones  
list\_conversations with folder assigned\_to\_me and last\_message\_from team returns conversations where your team wrote last. The agent keeps those whose last message is older than your window, using last\_message.at, and follows next\_cursor to the end.
2. 02  
### Read how it ended  
get\_conversation shows the customer's last message and your last reply. A thank you, "that worked" or an answer with no open question counts as settled. A question you asked that nobody answered does not.
3. 03  
### Respect the notes  
The same call returns internal notes. A note such as "waiting for finance" keeps the conversation open, and the agent lists it for you instead of closing it.
4. 04  
### Remind instead of closing  
set\_reminder puts a reminder at the time in your prompt on conversations still waiting for the customer. It reaches nobody and one more call clears it, so it does not wait for your OK.
5. 05  
### Close the settled ones  
close\_conversation runs once per conversation and asks for your OK by default. Journeys, rules or a CSAT survey you built may react to a closed conversation, and the agent cannot see them, so the close is the call you approve.

### What you get back

Example data

```
Our team wrote last, more than 3 days ago: 13
Closed 9:
- Customer said thanks or confirmed the fix
Reminder set for Monday 9:00 on 4:
- Our question about an order number is still unanswered
Left for you 0
```

### Other ways to ask

- Close every conversation labelled Delivery where the customer confirmed the parcel arrived.
- Show me the conversations you would close with the customer's last line, and close nothing.
- Every Monday, set a reminder for Thursday on conversations where I asked for an order number and got no reply.

## What Trengo allows, and what to know first

- Trengo bulk actions close, assign, mark as spam or delete up to 50 conversations at a time, and a deleted ticket cannot be retrieved.
- A Trengo reminder reopens the ticket at the date and time you choose and keeps it in the Reminders folder until then.
- AI Journeys has a Conversation closed trigger, and AI Labeling uses it to tag closed conversations, so a close can start a journey of yours.
- Closed conversations stay searchable by ticket number, name, phone number, email address or keyword; only deleted tickets do not appear in results.

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

Sources: [Trengo Help: Closing a conversation](https://help.trengo.com/article/closing-a-conversation) · [Trengo Help: Bulk actions in your inbox](https://help.trengo.com/article/bulk-actions-in-your-inbox) · [Trengo Help: Setting a ticket reminder](https://help.trengo.com/article/setting-a-ticket-reminder) · [Trengo Help: Rules explained](https://help.trengo.com/article/rules-explained) · [Trengo Help: AI labeling in Journeys](https://help.trengo.com/article/ai-labeling-in-journeys-automate-and-analyze-conversations) · [Trengo Help: Searching a conversation](https://help.trengo.com/article/searching-a-conversation)

## Call close\_conversation from a script

curl

```
curl -X POST https://cotlet.dev/api/v1/trengo/conversations/5120302/close \
  -H "Authorization: Bearer $COTLET_API_KEY"
```

Example response

```
{
"conversation_id": 5120302,
"status": "closed",
"closed_at": "2026-10-20T09:10:00Z"
}
```

MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is trengo\_write → close\_conversation. Example data.

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

## Trengo tools this automation uses

__Cotlet Trengo tools used to close resolved Trengo conversations with AI__
| Tool | Parameters |
| ------------------- | ------------------------------------------ |
| list\_conversations | folder, label, last\_message\_from, cursor |
| get\_conversation | conversation\_id |
| set\_reminder | conversation\_id, remind\_at, clear |
| close\_conversation | conversation\_id |

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

## Frequently asked questions

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

Yes. You sign in to Trengo yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Trengo 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 Trengo automations

- [Triage new Trengo conversations with AI](https://cotlet.dev/integrations/trengo-api-mcp-server/triage-new-conversations.md)
- [Reply to waiting Trengo customers with AI](https://cotlet.dev/integrations/trengo-api-mcp-server/reply-to-waiting-customers.md)
- [Trengo API and MCP server: every tool](https://cotlet.dev/integrations/trengo-api-mcp-server.md)
- [All use cases](https://cotlet.dev/use-cases.md)

## Give your agent access to Trengo.

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

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

---

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.