> For the complete documentation index, see [llms.txt](https://docs.nerovasystems.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nerovasystems.com/guides/operate-the-digital-employee/conversations.md).

# Read and steer conversations

List the customer chats your tenant's employee handles on WhatsApp, read a PII-redacted transcript while it is retained, and send a message into an open conversation when an operator needs to step in.

> **Experimental.** The `/api/v1/**` operations on this page are callable with your Live key (`nrv_live_`), which runs on the free testing allowance until a commercial agreement is signed or a card is saved. See [Lifecycle and availability](https://docs.nerovasystems.com/documentation/api/lifecycle).

## What you'll build

An operator view over live conversations: a list of recent chats, a transcript panel, and a reply path that stays safe under retries.

## Prerequisites

* An activated tenant: follow [Provision and activate tenants](/guides/provision/partner-playbook.md) first.
* An API key with `conversation:read` and `conversation:write`; see [Authentication](https://docs.nerovasystems.com/documentation/getting-started/authentication).

## 1. List recent conversations

Page through conversations, newest activity first:

```bash
curl --request GET \
  --url "https://api.nerovasystems.com/api/v1/tenants/{tenantId}/conversations?Limit=25" \
  --header "Accept: application/json" \
  --header "Authorization: ******"
```

`Limit` accepts 1–100 (default 50). Follow `nextCursor` until it is `null`, and optionally narrow with `From`/`To`, a half-open UTC window of at most 31 days. Each item carries a `status` (`open`, `completed`, or `expired`), a stable pseudonymous `participantReference` for the customer, and a `transcriptAvailability` flag.

## 2. Read a transcript

```bash
curl --request GET \
  --url "https://api.nerovasystems.com/api/v1/tenants/{tenantId}/conversations/{conversationId}" \
  --header "Accept: application/json" \
  --header "Authorization: ******"
```

The response includes up to the most recent 100 messages while the transcript is retained. Transcripts are kept for 7 days (`transcriptRetentionDays`); after that the conversation stays listable with `"transcriptAvailability": "expired"` but its messages are gone, so copy anything you need into your own records in time. Message content is redacted before it leaves Nerova: emails, phone numbers, and long digit runs become `[redacted-email]`, `[redacted-phone]`, and `[redacted-number]`.

## 3. Send a message

Send operator text into an open conversation. The send is idempotent, so a retried request cannot double-message the customer:

```bash
curl --request POST \
  --url "https://api.nerovasystems.com/api/v1/tenants/{tenantId}/conversations/{conversationId}/messages" \
  --header "Accept: application/json" \
  --header "Authorization: ******" \
  --header "Content-Type: application/json" \
  --header "Idempotency-Key: reply-wacon-8412-0031" \
  --data '{
    "text": "We can move you to 14:00 tomorrow if that helps.",
    "actor": {
      "actorReference": "operator:jane.d",
      "delegationReference": null
    }
  }'
```

Set `replyToMessageId` to thread the reply under a specific customer message. The tenant's WhatsApp channel must be ready and the conversation's customer-service window open, otherwise the send is rejected with `409`. If delivery cannot be verified you get `409` with code `partner.action_outcome_unknown`: read the conversation back and check the transcript before sending again.

## Next steps

* Handle persisted requests for human attention in your platform: [Work the attention queue](https://github.com/Nerova-Systems/Project-Songbird/tree/main/docs/guides/attention.md).
* Reach customers outside an open window: [Send customer notifications](/guides/operate-the-digital-employee/notifications.md).
* Full request and response shapes: [Conversations reference](https://docs.nerovasystems.com/api-reference/conversations).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.nerovasystems.com/guides/operate-the-digital-employee/conversations.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.