> ## 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.

# Catalog settings

Catalog settings cover the reusable material a project draws on: response templates, modules imported from elsewhere, modules this project publishes, trace metadata, telemetry export, and the voice credentials its channels use.

## Templates

The **Template Catalog** holds the response formats agents can send. It's a reference you copy from rather than a place you author. Open a template to see how it renders, adjust its payload, and copy the snippet your agent needs.

Navigation: **Project** > **Settings** > **Templates**

### Find a template

Search by name, or filter by category. The categories group templates by the job the response does rather than by the channel it targets.

| Category | Description |
| - | - |
| **Content** | Templates carrying formatted text and structured message payloads, including formats specific to a single messaging platform. |
| **Media** | Templates whose payload is a file the client plays, displays, or offers for download. |
| **Data** | Templates presenting numeric or tabular information, where the point is the figures rather than the prose around them. |
| **Input** | Templates collecting a response, where the agent expects the user to act on the message rather than only read it. |
| **Feedback** | Templates gathering a rating or reporting progress back to the user. |

### Reading a template card

Each card carries the template name, a short description, its category, and three badges. The badges are the part to read before you commit to a template, because they tell you whether it will work where your agent actually runs.

| Badge | Description |
| - | - |
| **Web** | Reports how the web chat surface renders the template. A native value means the surface renders the template's own form. Anything else means it renders a substitute, so the agent still responds but the user doesn't see the layout the template describes. Weigh this alongside the channels your agent serves, since a template built for one messaging platform necessarily degrades elsewhere. |
| **Preview** | Reports how the catalog's own preview pane renders the template, which isn't always how the live surface renders it. A limited preview is a limitation of this page rather than of the template, so don't rule a template out on the preview alone. |
| **ABL** | Reports whether you can emit the template from ABL. An insertable template is one you can send directly. A preview-only template can be inspected here but has to reach the user by another route, and a partial value means only some of the template is available. Check this badge first when you're choosing a template to build on. |

### Inspect and use a template

Selecting a card opens a detail panel that takes you from looking at a template to sending one. Its three parts let you see the rendering, change the content, and take away the code.

| Section | Description |
| - | - |
| **Preview** | Renders the template from the payload currently in the editor, so you can see the result before you write any agent code. |
| **JSON Editor** | Holds the template payload, which you can edit to try your own content in place of the sample. A character count below the editor shows how much of the allowed payload size you've used. |
| **ABL Snippet** | Gives the ABL that produces this template. Select **Copy** and paste it into your agent, then replace the sample values. This is the fastest route from choosing a template to sending one, and it saves you deriving the syntax from the payload by hand. |

***

## Imported modules

The **Imported Modules** page lists the reusable components this project has taken from the catalog or from other projects, including agents, tools, and workflows.

Navigation: **Project** > **Settings** > **Imported Modules**

The page title is **Module Dependencies**. Select **Import Module** to import a module.

Each entry records the module name, its version, the project it came from, and when this project imported it. The version and source together are what matter during an upgrade, since they tell you whose change you're taking on and who to ask before you take it.

***

## Module publishing

The **Module Publishing** page turns this project's agents, tools, and workflows into modules other projects can import.

Navigation: **Project** > **Settings** > **Module Publishing**

Publishing places a module in the workspace catalog, where you choose the resources to include, set the version, and control who can import it. Treat a published module as an interface rather than a copy, because projects that import it inherit your future versions along with the current one.

To make the project reusable, select **Enable as Reusable Module**. Then select **Publish Release** to publish a release. The **Published Releases** list shows every release the project has published, with a count.

> [!NOTE]
>
> If module features aren't enabled for your tenant, the page shows **Module features are not enabled for this tenant**.

A release exports the agents, tools, and workflows you selected. Workflows come across in two forms: those you published directly, and those a published workflow tool depends on. The second kind travels whether or not you selected it, so review a release for dependencies you didn't intend to share.

***

## Trace dimensions

The **Trace Dimensions** page defines the custom metadata the platform records with every trace event.

Navigation: **Project** > **Settings** > **Trace Dimensions**

A counter at the top shows how many dimension keys you've configured out of the 100 allowed.

Each dimension carries a name, a source, and a data type. Dimensions become filters in the session browser and in Insights, so define them around the questions you expect to ask, such as the customer segment or the campaign behind a conversation. A dimension you add today applies to traces recorded from that point on, which makes this a setting worth getting ahead of rather than reaching for once you need the analysis.

***

## Telemetry export

The **Telemetry Export** page sends this project's live model, agent, and tool telemetry to an external observability provider or to your own endpoint, so agent behavior appears alongside the rest of your infrastructure monitoring.

Navigation: **Project** > **Settings** > **Telemetry Export**

### Destination

This section holds the destination connection and decides how much telemetry leaves the platform. Complete it before you enable export, since the status switch has nowhere to send to until you do.

| Field | Description |
| - | - |
| **Adapter** | Selects where the platform sends telemetry. Default: **Azure Monitor**. Choose **OTLP/HTTP** to send to any OpenTelemetry-compatible backend, such as Datadog, Grafana, or New Relic, or **Webhook** to send signed payloads to your own HTTPS endpoint. The connection fields change with the adapter you select. See [Connection fields by adapter](#connection-fields-by-adapter). |
| **Signals** | Selects the telemetry the platform exports: **LLM calls** (model, tokens, latency, and finish reason), **Tool calls** (tool name, outcome, and latency), **Agent lifecycle** (handoffs, delegations, escalations, and decisions), **Messages** (user and agent message events), **Flow steps** (flow step exits and transitions), **Voice** (speech-to-text and text-to-speech completions), **Errors** (system errors), and **Session lifecycle** (session start and end, and turn start and end). |
| **Data export level** | Decides how much leaves the platform. Default: **Metadata only**. Metadata covers models, token usage, latency, and tool names. Full content adds prompts, responses, and tool inputs and outputs, which makes your observability provider a second store of conversation content and brings it into scope for the same privacy review as the platform itself. |
| **Trace grouping** | Decides what one trace represents. Grouping per session gives you the whole conversation in a single trace with each turn nested inside it, which suits reading conversations end to end. Grouping per turn gives accurate duration and status on each trace, which suits alerting and latency work. Default: **Per session**. |
| **Status** | Turns export to the configured destination on or off without discarding the configuration. Default: **Disabled**. Until you enter connection details, the page shows **Connection details required**. |

> [!NOTE]
>
> Provide the connection details for the selected adapter before you save a new telemetry exporter.

### Connection fields by adapter

Each adapter asks only for the details it needs to reach its destination. The platform records every change to a field that carries a credential, such as a connection string, header, or signing secret, in the audit log.

| Adapter | Field | Description |
| - | - | - |
| **Azure Monitor** | **Connection string** | Holds the Azure Monitor connection string, which needs to carry both an instrumentation key and an ingestion endpoint. The field masks the value once saved. |
| **OTLP/HTTP** | **Endpoint URL** | The HTTPS address of your OpenTelemetry collector or vendor intake. The platform sends traces over OTLP/HTTP. |
| **OTLP/HTTP** | **Headers** | Request headers the destination needs, such as an API key or tenant header. Headers are write-only: once saved, you can replace them but can't read them back. |
| **Webhook** | **Endpoint URL** | The HTTPS address of the service that receives the telemetry payloads. |
| **Webhook** | **Headers** | Extra request headers your endpoint expects. Headers are write-only, as with OTLP/HTTP. |
| **Webhook** | **Signing secret** | The secret the platform uses to sign each payload. Reveal it to copy the value into your receiving service, which uses it to confirm that the payload came from the platform and wasn't changed in transit. |

#### Verify webhook payloads

Webhook payloads follow the [Standard Webhooks](https://www.standardwebhooks.com/) specification, so you can verify them with any Standard Webhooks library instead of writing your own check.

1. Copy the **Signing secret** from the **Telemetry Export** page into your receiving service's configuration.
2. In your endpoint, pass the raw request body and the `webhook-id`, `webhook-timestamp`, and `webhook-signature` headers to a Standard Webhooks library.
3. Accept the payload only when the library confirms the signature, and reject requests with an old timestamp to block replayed payloads.

Each destination exports independently. If one destination slows down or stops responding, the platform holds back delivery to that destination only, and the others keep receiving telemetry.

### Page actions

Three controls at the top of the page manage the configuration you've entered.

| Action | Description |
| - | - |
| **Validate** | Checks the destination details you entered. Run it before saving, since an unreachable destination silently drops telemetry rather than reporting an error later. |
| **Save** | Writes the exporter configuration to the project. |
| **Reset to defaults** | Returns the form to its default values. |

***

## Voice credentials

Voice credentials let your project’s voice channels authenticate with the speech-to-text (STT) and text-to-speech (TTS) providers they use. Platform administrators now provision and manage these credentials centrally in the Admin console and assign them to tenants, so you no longer need to configure voice credentials for each project.

By default, a project uses the platform credential assigned to its tenant. If you prefer, you can bring your own credentials for a provider.

Navigation: **Project** > **Settings** > **Voice Credentials**

### How credentials are resolved

When a voice channel needs a speech credential, the platform works down a fixed order and uses the first match.

| Order | Source | Description |
| :- | :- | :- |
| 1 | **Channel selection** | The credential selected explicitly on the channel. It always wins over the project default. |
| 2 | **Project default** | The credential you set on this page. |
| 3 | **Workspace default** | The default credential for the workspace. |
| 4 | **Platform-provided** | A credential supplied by the platform, used only when nothing above it's set. |

Setting a project default is the right choice when a project needs a different provider from the rest of the workspace. Leave it on the workspace default when you want the project to follow whatever the workspace uses, since a change at workspace level then reaches this project without further work.

### Project defaults

The page has one section for each service. The two work independently, so you can set an STT default and leave TTS on the workspace default, or the reverse.

| Section | Field | Description |
| :- | :- | :- |
| **Speech recognition (STT)** | **Project default STT credential** | Decides which credential converts caller speech to text for this project. |
| **Speech synthesis (TTS)** | **Project default TTS credential** | Decides which credential converts agent responses to speech for this project. |

Each field is a dropdown with the same two kinds of choice.

| Option | Description |
| :- | :- |
| **Use workspace default** | The project sets no default of its own. Channels fall back to the workspace default credential. A note beneath the field confirms this by reading "No project default." |
| **Your credentials** | The credentials available to you, listed by name, such as *Deepgram Speech Credentials* for STT or *ElevenLabs (TTS) Credentials* for TTS. A credential that's also the workspace default is labeled **(workspace default)**. Selecting one makes it the project default. |

The list for each field shows the credentials that apply to that service, so a provider that offers both recognition and synthesis can appear in both lists.

### Save a project default

Each section has its own **Save** button, and it stays unavailable until you change that section's selection.

To go back to following the workspace, set the field to **Use workspace default** and select **Save**.

> [!NOTE]
>
> A channel's own credential selection overrides the project default. If a channel doesn't use the credential you set here, check whether that channel has an explicit selection.


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