> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect a Voiceflow agent to Slack DMs

> Connect Slack to a Voiceflow text agent. Configure the platform, host the relay, test replies and prepare release.

## Overview

Answer direct messages to a Slack app with a Voiceflow agent. The supplied relay verifies Slack’s HTTP requests, isolates users and DM threads, and posts plain-text replies as the app’s bot.

<a id="before-you-begin"></a>

## Before you begin

Collect the agent, account and host access.

| Requirement | Obtain before installation |
| --- | --- |
| Voiceflow owner | An existing agent with a known support answer, a private project API key, project ID and reviewed Environment alias. [Build the agent](/docs/documentation/build/overview) first, then [publish the intended release](/docs/documentation/deploy/environments/publishing). |
| Workspace | A Slack workspace where you may create and install an app, with administrator approval if the workspace requires it. |
| Bot scopes | `im:history` for direct-message events and `chat:write` for replies; this example does not read public/private channels. |
| Relay operator | A Node.js host, public HTTPS hostname, private secrets and persistent disk; an operator who can investigate paused conversations. |

The example provides public-policy text support. Keep private Voiceflow and platform credentials on the host; a customer’s messaging identity does not authorize access to orders or account records. Have the agent return text only and provide a support route in its instructions. Buttons, audio and Handoff traces need additional adapters; see [Adapt agent replies](/docs/guides/channels/messaging/adapt-agent-replies).

<a id="create-platform-app"></a>

## Prepare the platform account

Create the exact app or account this relay will use.

### 1. Create the Slack app

At [Slack’s app dashboard](https://api.slack.com/apps), create an app for your development workspace. Copy its **App ID** and **Signing Secret** from **Basic Information**. In **OAuth & Permissions**, add the bot scopes `im:history` and `chat:write`.

### 2. Install and enable direct messaging

Choose **Install to Workspace**, review the permission request and authorize it. Copy the **Bot User OAuth Token** into `SLACK_BOT_TOKEN`. In **App Home**, enable the Messages tab and allow people to send messages to the app. After changing scopes, reinstall the app so its granted permissions match.

Use `auth.test` with the bot token to confirm the workspace:

```js
// identity.mjs — node --env-file=.env identity.mjs
import { request } from './core.mjs';
console.log(await request('https://slack.com/api/auth.test', {
  headers: { Authorization: `Bearer ${process.env.SLACK_BOT_TOKEN}` }, body: {}
}));
```

Save the returned `team_id` as `SLACK_TEAM_ID`. A single-workspace installation does not need Marketplace publication; distribution to other workspaces needs its own OAuth installation and review decisions.

<a id="run-relay"></a>

## Run the relay

Configure and host the supplied executable example.

Use the [configuration file](/docs/examples/messaging/slack.env.example) for this platform. Every name below is read by the supplied artifact; IDs identify the resources prepared above. `VF_ENVIRONMENT` is the Environment alias, not a version label pasted from another project.

```dotenv
VF_API_KEY=YOUR_PRIVATE_VOICEFLOW_PROJECT_KEY
VF_PROJECT_ID=YOUR_VOICEFLOW_PROJECT_ID
VF_ENVIRONMENT=YOUR_ENVIRONMENT_ALIAS
DATA_DIR=/var/lib/voiceflow-messaging
PORT=8080
PLATFORM=slack
SLACK_BOT_TOKEN=YOUR_XOXB_TOKEN
SLACK_SIGNING_SECRET=YOUR_SIGNING_SECRET
SLACK_TEAM_ID=YOUR_WORKSPACE_ID
SLACK_APP_ID=YOUR_SLACK_APP_ID
```

### 1. Download and configure the relay

On a Linux host you administer, create `/opt/voiceflow-messaging` and extract the [relay archive](/docs/examples/messaging/messaging-relay.zip) there. Use Node.js 22.12 or later. Run `node --test fixtures.test.mjs` first: it generates signed synthetic events and mocks all remote calls, without credentials or live messages. Save the configuration above as `.env`, replacing every `YOUR_` value; restrict it to the service account with `chmod 600 .env`. Set `DATA_DIR` to a private persistent directory that this account can write.

The archive includes `core.mjs`, platform adapters, HTTP/Teams entry points, local fixture tests and a package manifest. Run `node --env-file=.env relay.mjs serve`. The HTTP relay uses only Node built-ins; it does not need `npm install`.

### 2. Expose the HTTPS endpoint

Point your own DNS hostname to the host. Terminate HTTPS with a valid public certificate and proxy to `127.0.0.1:8080`. For example, with [Caddy](https://caddyserver.com/docs/quick-starts/reverse-proxy) installed:

```sh
caddy reverse-proxy --from support.example.com --to 127.0.0.1:8080
```

Replace the example hostname, allow inbound 80/443 for certificate provisioning and keep the relay port private. Use a separate hostname and credentials for testing. Confirm `https://YOUR_HOST/health` returns `ok` before registering `/webhook`.

### 3. Keep one process running

After the foreground check, stop it and create a service using the unit below. Keep one process and one writable data directory per installation. Do not run this file store on ephemeral serverless storage or start multiple replicas.

```ini
# /etc/systemd/system/voiceflow-messaging.service
[Unit]
Description=Voiceflow messaging relay
After=network-online.target

[Service]
User=relay
WorkingDirectory=/opt/voiceflow-messaging
ExecStart=/usr/bin/node --env-file=.env relay.mjs serve
Restart=on-failure
UMask=0077

[Install]
WantedBy=multi-user.target
```

Create the non-login `relay` service user, give it read access to the application and `.env`, and ownership of `/var/lib/voiceflow-messaging`. Confirm `/usr/bin/node --version` is 22.12 or later, or substitute your actual Node path. Then run `sudo systemctl daemon-reload` and `sudo systemctl enable --now voiceflow-messaging`. Expect the service to stay active; keep the HTTPS proxy running through its own service.

The file store is a small single-process starting point. Back it up privately and monitor disk space, queue age and failures. Higher traffic needs a transactional inbox/outbox and per-conversation workers before adding replicas. Session keys and customer text are stored in the data directory; apply your retention and access policy there as well as in Voiceflow.

<a id="register-events"></a>

## Register incoming events

Connect the platform to your hosted endpoint.

### 1. Enable the subscribed events

In **Event Subscriptions**, turn **Enable Events** on and enter `https://YOUR_HOST/webhook` as the **Request URL**. The relay verifies the signing secret and returns the URL-verification challenge. Expect **Verified**. Add the bot event **message.im**, then choose **Save Changes** and reinstall if prompted.

### 2. Check delivery authentication

Keep Socket Mode disabled for this HTTP recipe. Slack’s [request verification](https://docs.slack.dev/authentication/verifying-requests-from-slack/) uses `v0:timestamp:raw-body`, HMAC-SHA256 and a five-minute freshness check. Its [Events API](https://docs.slack.dev/apis/events-api/) requires acknowledgment within three seconds and retries failed delivery. The relay persists each event before responding and runs the agent after that acknowledgment.

<a id="conversation-routing"></a>

## Route conversations and replies

Keep the customer, agent session and reply destination aligned.

| Stage | Mapping in the example |
| --- | --- |
| Customer identity | Workspace + DM channel + sender; a DM thread uses its root `thread_ts`, while ordinary unthreaded messages share the DM root session. |
| Incoming text | Bot subscription `message.im`, requiring `channel_type: im`; bot messages and subtypes are ignored. |
| Visible reply | `chat.postMessage` to `channel`, retaining incoming `thread_ts` when present; disable Markdown interpretation and unfurls. |
| Duplicate | Deduplicate the outer `event_id`; retry headers are diagnostic information, not a new event identity. |

The relay hashes platform, destination account, customer/thread, project and Environment into a bounded Voiceflow `userID`. It creates a session with the private project key, stores the returned `sessionKey`, launches once, then sends `{ action: { type: "text", payload: text } }` to `/v4/interact`. Text traces become platform replies. Follow-ups reuse the key; starting a session every message would reset the conversation.

This walkthrough covers text in personal DMs to the app. Channel mentions, group DMs, message edits, file analysis and Slack AI app surfaces require additional subscriptions and implementation. No privileged channel-history scopes are implied.

Check Slack’s response body as well as HTTP status: Web API errors may return `ok: false`. A `429` response, removed app or changed workspace authorization pauses the affected conversation. Review any applicable Slack AI app requirements before broader distribution; a basic DM installation is not a Marketplace approval.

<a id="test-conversation"></a>

## Test a customer conversation

Verify the reply in the destination you installed.

### 1. Send a real platform message

Open the app’s Messages tab in Slack and send your prepared question. Expect the bot’s text reply in the same DM.

### 2. Check continuity and isolation

Ask a related follow-up, then test with a second authorized customer. Confirm the intended Voiceflow project and exchange in [Transcripts](/docs/documentation/measure/transcripts). Run `node --env-file=.env relay.mjs inspect` while the service is stopped to compare event IDs, conversation keys and completion states without printing session tokens.

### 3. Check this platform’s delivery behavior

Start a reply thread in that DM and ask a follow-up. Verify the response stays in that thread. Use a second workspace member to check memory isolation, and replay an event to check deduplication.

A saved callback, accepted API request or successful Voiceflow Run does not prove this platform conversation. Keep local signed-fixture tests separate from this authenticated customer test.

<a id="troubleshooting" />

### The callback saves but no reply arrives

Check platform access as well as endpoint connectivity.

Check App Home messaging, `message.im`, installed scopes and workspace ID. A verified Request URL does not grant `im:history` or `chat:write`. If the bot loops, check that bot messages and subtypes remain filtered.

### A conversation is paused or a reply is duplicated

Reconcile remote effects before resuming the saved job.

Inspect the event’s `phase`, `failedDuring`, saved traces and accepted chunks in the private data file. A runtime timeout can occur after a tool action; a send timeout can occur after the platform accepted the message. The sample pauses that conversation and does not retry either effect automatically. Follow [Recover failed messages](/docs/guides/channels/messaging/recover-failed-messages), then repeat the platform test.

<a id="go-live"></a>

## Release and maintain the connection

Promote the tested route and keep recovery available.

### 1. Approve the production destination

Use an approved workspace installation with production bot credentials. For another workspace, perform OAuth and store credentials per installation; do not reuse this single-workspace configuration for multiple teams.

### 2. Release the reviewed agent

Have the Voiceflow owner publish the tested agent to the intended Environment. Deploy that alias and production credentials to the relay, restart its service and repeat the [customer test](#test-conversation) with a fresh customer/session. Existing session keys are not an automatic migration to a new release. Keep the previous deployment and state backup available for rollback.

### Rotate, update or disconnect

Maintain both the provider registration and the relay state.

Stop the service before changing `.env` or running maintenance commands. Rotate the platform credentials using its administrator controls, update the secret file and restart. If a webhook secret changes, update both sides and check a real event. For a release change, drain or reconcile pending jobs first; do not erase the state file to resolve a delivery problem.

To disconnect, disable/remove this callback or uninstall this app in the provider, stop the relay and revoke its unused credentials. Confirm no new events arrive and retain/delete customer state according to your policy. Keep the registration details needed to reconnect. See [Pause automated replies](/docs/guides/channels/messaging/pause-automated-replies) for a temporary conversation-specific pause.
