[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)

# Reply to waiting Trengo customers with AI

> Find Trengo conversations where the customer wrote last and reply from your quick replies, with your OK on each. Email and WhatsApp.

Source: https://cotlet.dev/integrations/trengo-api-mcp-server/reply-to-waiting-customers

The customer wrote last, the conversation sits in Assigned to me, and each morning someone opens every one to type an answer that mostly repeats a quick reply.

Cotlet does it in your own Trengo account with list\_conversations, get\_conversation, list\_quick\_replies, reply\_to\_conversation and add\_internal\_note, 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 has quick replies, rules with the action Send message, and its own AI Agent, HelpMate (checked 20 Oct 2026). A person inserts a quick reply, a rule fires on fixed conditions such as Message body contains, and the AI Agent follows the Skills and instructions you set in Trengo and sees only the current ticket. Nothing lets your own agent read a thread with the internal notes and answer it by your rules.

## How you do it in Trengo today

1. In Inbox > Assigned to me, the agent opens each conversation and reads who wrote last.
2. For a repeated question the agent inserts a quick reply from Settings > Quick replies, where tags fill in details such as names automatically.
3. Messaging quick replies serve channels such as Facebook, WhatsApp and Website chat, and Email quick replies also take attachments.
4. The agent sends the message, or opens the dropdown next to it and picks Send and close.
5. On WhatsApp the agent keeps the 24-hour limitation in mind, because only a template can start a conversation with a customer.

## How to reply to waiting Trengo customers with AI

Prompt

```
Find my Trengo conversations where the customer wrote last. Reply from my quick replies in my tone, skip anything about refunds or chargebacks and leave an internal note saying why. Send nothing without my OK.
```

1. 01  
### Find who waits  
list\_conversations with folder assigned\_to\_me and last\_message\_from customer returns the conversations where the customer wrote last. A conversation where your team wrote last is never returned, so nobody gets two replies in a row.
2. 02  
### Read the whole thread  
get\_conversation brings customer messages, team replies and internal notes. A note from a colleague saying to wait, or a reply another agent sent a minute ago, takes the conversation off the list.
3. 03  
### Start from your wording  
list\_quick\_replies runs with type email for email conversations and messaging for WhatsApp, Facebook and live chat. The agent picks the quick reply that matches the question and fills in the details itself, because tags come back as written.
4. 04  
### Decide what needs you  
Refunds, chargebacks, legal questions and anything your prompt marks as sensitive get no reply. The agent writes the reason with add\_internal\_note and lists the conversation for you. A WhatsApp conversation whose last customer message is older than 24 hours is listed too.
5. 05  
### Send after your OK  
reply\_to\_conversation sends in the conversation's own channel, and each call waits for your OK by default. Before sending, the agent reads the conversation again and skips it if a colleague answered meanwhile.

### What you get back

Example data

```
Waiting for an answer: 9
Replies ready for your OK 6:
- Lena Vos, Email: refund timeline, from "Refund timeline"
- Noor Haddad, WhatsApp: parcel status
Left for you 3:
- Chargeback threat (billing)
- WhatsApp: customer wrote 31 hours ago, past the 24-hour limit
- Note from Sam says to wait for finance
```

### Other ways to ask

- Reply only to WhatsApp conversations about delivery and leave the email ones to me.
- Draft replies for everything waiting as a list in this chat and send nothing.
- Every afternoon, answer conversations waiting more than 2 hours and close them when the reply solves the question.

## What Trengo allows, and what to know first

- A Trengo conversation is an outbound message that starts in Trengo or replies to an inbound one, inside a 7-day window, so each reply your agent sends counts against your subscription's conversations.
- Trengo quick replies are set up per channel type, Messaging or Email, and only Email quick replies take attachments.
- Send and close sits in the dropdown next to Send, so a reply and a close can be one step.
- Trengo sends a WhatsApp template only to start a conversation, and once the customer answers you reply freely, within WhatsApp's 24-hour limitation.

reply\_to\_conversation and add\_internal\_note ask for your OK by default. To run it daily without you, switch confirmation off for those tools in your dashboard.

Sources: [Trengo Help: Conversations in Trengo](https://help.trengo.com/article/conversations-in-trengo) · [Trengo Help: Adding quick replies to your inbox](https://help.trengo.com/article/adding-quick-replies-to-your-trengo-inbox) · [Trengo Help: Starting a WhatsApp conversation](https://help.trengo.com/article/starting-a-whatsapp-conversation) · [Trengo Help: Closing a conversation](https://help.trengo.com/article/closing-a-conversation) · [Trengo Help: How the AI Agent makes decisions](https://help.trengo.com/article/how-the-ai-agent-makes-decisions----what-you-should-know)

## Call reply\_to\_conversation from a script

curl

```
curl -X POST https://cotlet.dev/api/v1/trengo/conversations/5120391/replies \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message":"Hi Lena, your refund was issued today and shows on your statement within a few days. Reply here if it has not arrived by Friday."}'
```

Example response

```
{
"conversation_id": 5120391,
"message_id": 93410022,
"channel": "Email",
"sent_at": "2026-10-20T08:14:00Z",
"closed": false
}
```

MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is trengo\_write → reply\_to\_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 reply to waiting Trengo customers with AI__
| Tool | Parameters |
| ----------------------- | --------------------------------------------- |
| list\_conversations | folder, label, last\_message\_from, cursor |
| get\_conversation | conversation\_id |
| list\_quick\_replies | type |
| reply\_to\_conversation | conversation\_id, message, close\_after\_send |
| add\_internal\_note | conversation\_id, note |

[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)
- [Close resolved Trengo conversations with AI](https://cotlet.dev/integrations/trengo-api-mcp-server/close-resolved-conversations.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.