> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Set up Kore Agent Assist

[Back to messaging or digital channels](https://koreai.mintlify.site/agent-platform/channels.md#messaging-or-digital-channels)

Connect an Artemis project to Kore Agent AI so your deployed agent gives contact center agents real-time guidance. Artemis owns the connection, its generated API key, the environment binding, and the pause state. Kore Agent AI keeps calling the existing Agent Assist API, so the external endpoint contract doesn't change.

The setup requires:

1. [Create the connection in Artemis](#create-the-connection-in-artemis) and copy its four values.
2. [Configure Kore Agent AI](#configure-kore-agent-ai) with those values.
3. [Verify the connection](#verify-the-connection) from the **Testing** tab.

After setup, Kore Agent AI routes each Agent Assist session to the agent version active in the bound environment.

**Important considerations**

* **The API key appears only once**: Artemis reveals the full key at creation. Afterward, only its prefix stays visible. If you lose it, rotate it.
* **Pause and Resume control traffic**: There's no separate enable toggle. A paused or inactive connection returns not found to every external request.
* **Use one connection per environment**: Keep development, staging, and production on separate connections, each with its own key.
* **The key has a narrow scope**: It grants `session:send_message` for the owning project only, not platform administration.

## Prerequisites

Confirm these before you start.

* An agent version deployed to the target environment. Kore Agent Assist requires a published environment.
* Artemis project access with permission to open **Deployments** > **Channels**.
* Administrator access to Kore Agent AI, including **Configuration**.
* A secrets manager to store the API key.

***

## Create the connection in Artemis

Create the connection first. Artemis generates the four values Kore Agent AI needs.

1. Open Artemis and select the project.

2. Go to **Deployments** > **Channels** > **Kore Agent Assist** > **+ New**. The **New Kore Agent Assist Connection** dialog opens, with the setup guide on the left and the fields on the right.

3. Configure the fields:

   | Artemis field | What it controls |
   | - | - |
   | **Display Name** | The label operators see. Name it for the Agent Assist experience and its environment. |
   | **Environment** | The environment whose active deployment supplies the entry agent, welcome message, model, and runtime behavior. Kore Agent Assist requires a non-empty environment. |
   | **Initial Status** | **Active** lets the API resolve the App ID and environment immediately. **Inactive** returns not found to external traffic until you activate it. |

4. Select **Create**.

5. Copy all four values that Artemis reveals, and store the API key in your secrets manager.

| Value | What it is | Watch for |
| - | - | - |
| **Domain URL** | The Artemis host that Kore Agent AI calls | Agent AI appends the API route itself. Don't paste an endpoint path. |
| **Environment** | The environment identifier | It can differ from the environment's display label. Copy the revealed value. |
| **App ID** | The project ID for the connection | Don't substitute the display name, an agent name, or a connection record ID. |
| **API Key** | A generated secret with the `abl_` prefix | Copy the full key now. Artemis can't show it again. |

> [!WARNING]
>
> The API key is reveal-once. If you lose it or suspect exposure, rotate it from the **Configuration** tab and update Kore Agent AI immediately.

***

## Configure Kore Agent AI

Add the connection as an Agentic Copilot app in Kore Agent AI. Use the configuration for the same tenant, project, and environment as the Artemis connection.

**1. Open Agentic Configurations**

1. Sign in to [Kore Agent AI](https://agentassist.kore.ai/koreagentassist/).
2. Go to **Configuration** > **System Setup** > **Linked Services** > **Agentic Configurations**.
3. Select **+ Add Agentic Copilot App**.

**2. Paste the four values**

Under **App Information**, enter an **App Name**, then paste each value exactly, preserving case and punctuation.

| Agent AI field | Artemis value |
| - | - |
| **Domain URL** | **Domain URL** |
| **Environment** | **Environment** |
| **App ID** | **App ID** |
| **API Key** | The full `abl_` key, not the prefix |

Agent AI stores the key in its backend and sends it as `x-api-key`. Never expose it in browser code, transcripts, client logs, or source control.

**3. Test and save**

Select **Test Connection & Save**. Agent AI builds the base path and sends `application/json` with `x-api-key` on every session, execute, terminate, and test request.

Then link the app to your Agent AI experience. See [Agentic Copilot](https://docs.kore.ai/agentassist/uncategorized/agentic-copilot/).

### Validation checklist

Review these items before you route live conversations to the connection.

| Validation item | Expected result |
| :- | :- |
| Artemis connection | Status shows **Active**, and the **Deployment** tab shows an **Active Deployment**. |
| Agent AI values | Domain URL, Environment, App ID, and the full current key match Artemis exactly. |
| Agent AI save | **Test Connection & Save** succeeds. |
| Artemis **Testing** tab | Every test action returns a successful result. |

***

## Verify the connection

The **Testing** tab calls the live Agent Assist API with the connection's saved values. Run it before you configure Agent AI, and again after any key rotation.

1. Open the connection and select the **Testing** tab.
2. Under **Connection**, confirm the **Domain URL**, **Environment**, and **App ID**.
3. In **API Key**, paste the full key you stored. The test actions stay unavailable until you do.
4. Run the actions in order. They all share the generated **sessionReference**.
5. Review **Results**, which lists each request, status, duration, and response. Select **New session** to start over with a new reference.

| Action | Endpoint | What it confirms |
| - | - | - |
| **Test connection** | `/test` | The key authenticates, the App ID and environment resolve, and the deployment, entry agent, and model are ready. No conversation, no model call. |
| **Connect (welcome)** | `/sessions` | The session opens and returns the authored welcome message. |
| **Send message** | `/runs/execute` | The agent answers a turn. Turn on **Stream response (SSE)** to check streaming delivery. |
| **Terminate** | `/sessions/terminate` | The session ends and returns a termination response. |

### Verify pause and resume

Confirm that the connection status controls all external traffic.

1. Select **Pause** in the connection header.
2. Run **Test connection**, and confirm it returns not found.
3. Select **Resume**, and run **Test connection** again.

***

## Manage the channel connection

Open a connection from **Deployments** > **Channels** > **Kore Agent Assist** to manage it. The page has a header, three tabs, and a summary panel on the right.

**Header.** Shows the connection name, its environment badge, its status, and when it last changed. **Pause** and **Resume** control external traffic, and the **...** overflow menu holds the other connection-level actions. Before you delete a connection, remove or update the matching app in Agent AI.

**Summary panel.** Stays visible on every tab.

| Field | Description |
| - | - |
| **Channel** and **Connection Type** | Read **Kore Agent Assist** and **Channel Connection**. |
| **Identifier** | The App ID and environment this connection resolves, joined by a colon. |
| **Created** and **Updated** | Date and time of creation and of the last change. |

> [tab] Configuration
>
> Under **Kore Agent AI configuration**, copy the values Agent AI needs and rotate the key.
>
> | Setting | Description |
> | - | - |
> | **Display Name** | The label operators see. |
> | **Domain URL**, **Environment**, **App ID** | Read-only, each with a copy control. |
> | **API Key** | Masked. Select **Rotate** to replace it. |
>
> To rotate the key:
>
> 1. Select **Rotate** beside **API Key**.
> 2. Copy the new key. Artemis reveals it once and revokes the previous key as soon as it saves the replacement.
> 3. In Agent AI, replace the **API Key** and select **Test Connection & Save**.
>
> Select **Save Changes** after you edit the **Display Name**.

> [tab] Deployment
>
> Choose which deployed version answers Agent Assist sessions.
>
> | Setting | Description |
> | - | - |
> | **Environment** | Under **Environment Binding**. Selects which deployed version handles incoming messages. |
> | **Active Deployment** | Shows the bound version and when someone deployed it. |
>
> Select **Save Changes** after you switch the environment. Then check the **Environment** value on the **Configuration** tab, and update Agent AI if it changed.

> [tab] Testing
>
> Run the test actions through the live API. See [Verify the connection](#verify-the-connection).

***

## API reference

Kore Agent AI calls these endpoints for you. Use this section to build a custom integration or diagnose failed requests.

### Base path and authentication

Every endpoint shares one base path built from the connection values.

```text theme={null}
{Domain URL}/api/v2/apps/{App ID}/environments/{Environment}
```

Send `Content-Type: application/json` and the full key in `x-api-key`. Don't send `Authorization: Bearer`, an Artemis user token, an SDK public key, or the key prefix. The API checks that the key's tenant and project match the resolved App ID and environment, and returns not found on any mismatch.

### Session lifecycle

Each conversation reuses the same session identity across every call.

| Step | Endpoint | Details |
| - | - | - |
| Start | `POST /sessions` | Send `sessionIdentity` before the first turn. Set `metadata.isSendWelcomeMessage` to `true` to receive the welcome message. |
| Send turns | `POST /runs/execute` | Send `sessionIdentity` and `input[]`. Reuse the same `sessionReference` for later turns. |
| End | `POST /sessions/terminate` | Send the same identity when the conversation ends. The API returns a termination response even if the session is already gone. |
| Check readiness | `POST /test` | Reports agents, entry agent, deployment, and model readiness without a conversation or model call. |

### Response modes

The request fields on `/runs/execute` decide the response mode.

| Mode | How to request it | Behavior |
| - | - | - |
| Synchronous (default) | Leave streaming off and omit `callbackUrl`. | Returns one completed response on the same HTTP connection. |
| Streaming (SSE) | Set `stream.enable` to `true` and accept `text/event-stream`. | Streams the response with heartbeats, then sends the final session and run details. Takes precedence over `isAsync`. |
| Async push | Set `isAsync` to `true` and include `callbackUrl`. | Validates the callback, returns `202` with a processing state, and later delivers the completed or error response. |

If `isAsync` is `true` but `callbackUrl` is missing, the API falls back to the synchronous response. For async push, use an approved HTTPS destination outside private and link-local ranges. When callback signing is on, verify `X-ABL-Signature`, which signs `timestamp.rawBody`.

### Payload rules

The API normalizes and restricts request content before the agent runs.

| Element | Rule |
| - | - |
| `sessionIdentity` | Accepts `sessionReference`, `sessionId`, `sessionIdentity`, and `userReference` entries. Include at least one stable `sessionReference`, `sessionId`, or `userReference`, and keep it unchanged. |
| `input[]` | Needs at least one item of type `text`, `object`, or `tool_input`. Agent execution needs a `text` item. Each content value allows up to 16,000 characters. |
| `metadata.aa_uamsgs` | Carries Agent Assist history. The API keeps up to 50 messages. |
| Other `metadata` | Accepts custom keys. The API strips reserved transport, credential, tenant, project, session, and authorization keys. |
| Output | Text and markdown, plus optional normalized renderables, actions, and activity events. No attachments or channel-native rich media. |

***

## Troubleshoot connection issues

Match the symptom to its likely cause, and apply the recommended action.

| Symptom | Likely cause | Recommended action |
| - | - | - |
| `401 Unauthorized` | Missing, partial, or revoked key | Paste the full current `abl_` key, and confirm every request sends `x-api-key`. |
| `404` app not found | Wrong App ID or Environment, a key from another project, or a paused or inactive connection | Recopy the values from the **Configuration** tab, and confirm the connection shows **Active**. |
| **Test Connection & Save** fails in Agent AI | A pasted value differs from Artemis | Recopy every value with the copy controls on the **Configuration** tab. |
| `/test` reports a deployment resolution failure | No active deployment, or an invalid entry agent or model | Publish or activate the environment, and check its entry agent and model configuration. |
| Streaming returns JSON or stalls | Streaming isn't requested, or a proxy buffers the response | Set `stream.enable` to `true`, accept `text/event-stream`, turn off proxy buffering, and let heartbeats pass for the full timeout. |
| Async returns an invalid callback error or never delivers | Unapproved callback URL or failed signature check | Use an approved HTTPS URL outside private and link-local ranges, and verify `X-ABL-Signature` when signing is on. |
| Welcome and follow-up turns land in different sessions | The session identity changes between calls | Reuse the same `sessionReference`, and keep identity values and their order unchanged between `/sessions` and `/runs/execute`. |
| Test actions stay unavailable | The **Testing** tab has no key | Paste the full key, or rotate it from the **Configuration** tab and paste the new one. |

***

**Related articles:**

* [Channels](https://koreai.mintlify.site/agent-platform/channels.md)
* [Deployment](https://koreai.mintlify.site/agent-platform/deployment.md)
* [Linked Services in Kore Agent AI](https://docs.kore.ai/agentassist/settings/linked-services/)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.