--- title: Create an Agent Observability prompt description: Datadog, the leading service for cloud-scale monitoring. breadcrumbs: Docs > API Reference > Agent Observability --- > For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt). # Create an Agent Observability prompt{% #create-an-agent-observability-prompt %} Copy pageCopied {% tab title="v2" %} **Note**: This endpoint is in preview and is subject to change. If you have any feedback, contact [Datadog support](https://docs.datadoghq.com/help/). | Datadog site | API endpoint | | ----------------- | ------------------------------------------------------------ | | ap1.datadoghq.com | POST https://api.ap1.datadoghq.com/api/v2/llm-obs/v1/prompts | | ap2.datadoghq.com | POST https://api.ap2.datadoghq.com/api/v2/llm-obs/v1/prompts | | app.datadoghq.eu | POST https://api.datadoghq.eu/api/v2/llm-obs/v1/prompts | | app.ddog-gov.com | POST https://api.ddog-gov.com/api/v2/llm-obs/v1/prompts | | us2.ddog-gov.com | POST https://api.us2.ddog-gov.com/api/v2/llm-obs/v1/prompts | | uk1.datadoghq.com | POST https://api.uk1.datadoghq.com/api/v2/llm-obs/v1/prompts | | app.datadoghq.com | POST https://api.datadoghq.com/api/v2/llm-obs/v1/prompts | | us3.datadoghq.com | POST https://api.us3.datadoghq.com/api/v2/llm-obs/v1/prompts | | us5.datadoghq.com | POST https://api.us5.datadoghq.com/api/v2/llm-obs/v1/prompts | ### Overview Create a new prompt (and its first version) in the Agent Observability prompt registry. **Preview**: Prompt composition is available in Preview. To request access, contact [Datadog Support](https://docs.datadoghq.com/help/) or your Customer Success Manager. This endpoint requires all of the following permissions:`llm_observability_read``llm_observability_write``feature_flag_config_read``feature_flag_config_write``feature_flag_environment_config_read` ### Request #### Body Data (required) Create prompt payload. {% tab title="Model" %} | Parent field | Field | Type | Description | | ------------ | ---------------------------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | | data [*required*] | object | Data object for creating an Agent Observability prompt. | | data | attributes [*required*] | object | Attributes for creating an Agent Observability prompt and its first version. `prompt_id` and `template` are required; all other attributes are optional. If `config` is omitted, the first version stores an empty object. Configuration authoring must be enabled for your organization to supply `config`. Otherwise, supplying it, including an empty object, returns HTTP 403. | | attributes | config | object | Versioned prompt configuration is in Preview. To request access, contact [Datadog Support](https://www.datadoghq.com/support/) or your Customer Success Manager. Customer-owned configuration delivered with a prompt version. Datadog stores and returns the object without interpolating it, validating provider-specific keys, or applying it to model calls. Do not include secrets. | | attributes | description | string | Optional description of the prompt. | | attributes | env_ids | [string] | Optional feature-flag environment UUIDs the service attempts to enable and configure to use the first version as their default after creation. | | attributes | labels | [string] | **DEPRECATED**: Optional labels to attach to the first version. Do not use this attribute for new integrations. | | attributes | prompt_id [*required*] | string | Customer-provided identifier for the new prompt. | | attributes | template [*required*] | | A text template, a list of chat messages, or an authored chat object. Text can include an exact prompt version with `{{>prompt-id version=N}}`; other text, including `{{>...}}` sequences without a version, remains literal. Use an authored chat object when including prompts as chat messages. **Preview**: Prompt composition is available in Preview. To request access, contact [Datadog Support](https://docs.datadoghq.com/help/) or your Customer Success Manager. Without access, inline references remain literal text and structured includes are unsupported. Previously compiled prompt versions remain available for execution. | | template | Object 1 | string | A text prompt template. | | template | Object 2 | [object] | A chat prompt template. | | Object 2 | content [*required*] | string | Content of the message. | | Object 2 | role [*required*] | string | Role of the message (for example `system`, `user`, or `assistant`). | | template | Object 3 | object | A chat prompt whose authored items are stored under `messages`. | | Object 3 | messages [*required*] | [ ] | A chat prompt containing messages, references to specific versions of other prompts, or both. | | messages | Object 1 | object | A single chat message in a prompt template. | | Object 1 | content [*required*] | string | Content of the message. | | Object 1 | role [*required*] | string | Role of the message (for example `system`, `user`, or `assistant`). | | messages | Object 2 | object | Includes all or selected messages from a specific version of another prompt. | | Object 2 | include [*required*] | object | Includes messages from a specific version of another prompt. Omitting `items` includes every message from that version in its original order. When `items` is present, messages are included in the specified order, including repetitions. | | include | items | [integer] | Zero-based indexes of messages from the included prompt. For example, `[2, 0, 0]` includes the third message, followed by the first message twice. Omit this field to include all messages in their original order. | | include | prompt_id [*required*] | string | Customer-provided identifier of the included prompt. | | include | version [*required*] | int64 | Positive sequential version number of the included prompt. | | attributes | title | string | Optional title of the prompt. | | attributes | user_version | string | Optional user-supplied version identifier for the first version. | | data | type [*required*] | enum | Resource type of an Agent Observability prompt. Allowed enum values: `prompt-templates` | {% /tab %} {% tab title="Example" %} ```json { "data": { "attributes": { "config": { "model": "provider-model", "response_format": { "type": "json_object" }, "temperature": 0.2 }, "description": "string", "env_ids": [], "labels": [], "prompt_id": "customer-support-assistant", "template": { "description": "You are a helpful assistant for {{audience}}.", "minLength": "You are a helpful assistant for {{audience}}.", "pattern": "You are a helpful assistant for {{audience}}.", "type": "You are a helpful assistant for {{audience}}." }, "title": "string", "user_version": "string" }, "type": "prompt-templates" } } ``` {% /tab %} ### Response {% tab title="200" %} OK {% tab title="Model" %} Response returned after creating an Agent Observability prompt. | Parent field | Field | Type | Description | | ------------ | ------------------------------ | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | | data [*required*] | object | Data object returned after creating an Agent Observability prompt. | | data | attributes [*required*] | object | Attributes returned after creating an Agent Observability prompt and its first version. Empty `config` is omitted when configuration authoring is disabled for the organization. Non-empty saved configuration is always returned. | | attributes | author | string | UUID of the user who authored the prompt. | | attributes | config | object | Versioned prompt configuration is in Preview. To request access, contact [Datadog Support](https://www.datadoghq.com/support/) or your Customer Success Manager. Customer-owned configuration delivered with a prompt version. Datadog stores and returns the object without interpolating it, validating provider-specific keys, or applying it to model calls. Do not include secrets. | | attributes | created_at | date-time | Timestamp when the prompt was created. | | attributes | created_from [*required*] | string | Source that created the prompt, such as `ui-registry`, `sdk-registry`, or `sdk-instrumentation`. | | attributes | datasets | [object] | Datasets observed in runs associated with this prompt. | | datasets | id [*required*] | string | Unique identifier of the dataset. | | datasets | name | string | Name of the dataset. | | attributes | description | string | Description of the prompt. | | attributes | extracted_from | string | Source prompt from which this prompt was extracted, when applicable. | | attributes | in_registry [*required*] | boolean | Whether the prompt is a registry entry (as opposed to a code-discovered prompt). | | attributes | last_seen_at | date-time | Timestamp of the most recent observed run of this prompt. | | attributes | last_version_created_at | date-time | Timestamp when the most recent version of the prompt was created. | | attributes | ml_app | string | The ML application this prompt is associated with. | | attributes | ml_apps | [string] | ML applications observed running this prompt. | | attributes | num_versions [*required*] | int64 | Number of versions of the prompt. | | attributes | prompt_id [*required*] | string | Customer-provided identifier of the prompt. | | attributes | source [*required*] | enum | Whether the prompt was created from the registry or discovered from observed LLM calls. Allowed enum values: `registry,code` | | attributes | tags | [string] | Tags observed on runs of this prompt. | | attributes | title | string | Title of the prompt. | | data | id [*required*] | string | Unique identifier of the prompt. | | data | type [*required*] | enum | Resource type of an Agent Observability prompt. Allowed enum values: `prompt-templates` | {% /tab %} {% tab title="Example" %} ```json { "data": { "attributes": { "author": "string", "config": { "model": "provider-model", "response_format": { "type": "json_object" }, "temperature": 0.2 }, "created_at": "2019-09-19T10:00:00.000Z", "created_from": "sdk-registry", "datasets": [ { "id": "", "name": "string" } ], "description": "string", "extracted_from": "string", "in_registry": true, "last_seen_at": "2019-09-19T10:00:00.000Z", "last_version_created_at": "2019-09-19T10:00:00.000Z", "ml_app": "string", "ml_apps": [], "num_versions": 1, "prompt_id": "customer-support-assistant", "source": "registry", "tags": [], "title": "string" }, "id": "4a1a28ff-8a25-5f0f-946f-f48264d772eb", "type": "prompt-templates" } } ``` {% /tab %} {% /tab %} {% tab title="400" %} Bad Request {% tab title="Model" %} API error response. | Parent field | Field | Type | Description | | ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- | | | errors [*required*] | [object] | A list of errors. | | errors | detail | string | A human-readable explanation specific to this occurrence of the error. | | errors | meta | object | Non-standard meta-information about the error | | errors | source | object | References to the source of the error. | | source | header | string | A string indicating the name of a single request header which caused the error. | | source | parameter | string | A string indicating which URI query parameter caused the error. | | source | pointer | string | A JSON pointer to the value in the request document that caused the error. | | errors | status | string | Status code of the response. | | errors | title | string | Short human-readable summary of the error. | {% /tab %} {% tab title="Example" %} ```json { "errors": [ { "detail": "Missing required attribute in body", "meta": {}, "source": { "header": "Authorization", "parameter": "limit", "pointer": "/data/attributes/title" }, "status": "400", "title": "Bad Request" } ] } ``` {% /tab %} {% /tab %} {% tab title="401" %} Unauthorized {% tab title="Model" %} API error response. | Parent field | Field | Type | Description | | ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- | | | errors [*required*] | [object] | A list of errors. | | errors | detail | string | A human-readable explanation specific to this occurrence of the error. | | errors | meta | object | Non-standard meta-information about the error | | errors | source | object | References to the source of the error. | | source | header | string | A string indicating the name of a single request header which caused the error. | | source | parameter | string | A string indicating which URI query parameter caused the error. | | source | pointer | string | A JSON pointer to the value in the request document that caused the error. | | errors | status | string | Status code of the response. | | errors | title | string | Short human-readable summary of the error. | {% /tab %} {% tab title="Example" %} ```json { "errors": [ { "detail": "Missing required attribute in body", "meta": {}, "source": { "header": "Authorization", "parameter": "limit", "pointer": "/data/attributes/title" }, "status": "400", "title": "Bad Request" } ] } ``` {% /tab %} {% /tab %} {% tab title="403" %} Forbidden {% tab title="Model" %} API error response. | Parent field | Field | Type | Description | | ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- | | | errors [*required*] | [object] | A list of errors. | | errors | detail | string | A human-readable explanation specific to this occurrence of the error. | | errors | meta | object | Non-standard meta-information about the error | | errors | source | object | References to the source of the error. | | source | header | string | A string indicating the name of a single request header which caused the error. | | source | parameter | string | A string indicating which URI query parameter caused the error. | | source | pointer | string | A JSON pointer to the value in the request document that caused the error. | | errors | status | string | Status code of the response. | | errors | title | string | Short human-readable summary of the error. | {% /tab %} {% tab title="Example" %} ```json { "errors": [ { "detail": "Missing required attribute in body", "meta": {}, "source": { "header": "Authorization", "parameter": "limit", "pointer": "/data/attributes/title" }, "status": "400", "title": "Bad Request" } ] } ``` {% /tab %} {% /tab %} {% tab title="409" %} Conflict {% tab title="Model" %} API error response. | Parent field | Field | Type | Description | | ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- | | | errors [*required*] | [object] | A list of errors. | | errors | detail | string | A human-readable explanation specific to this occurrence of the error. | | errors | meta | object | Non-standard meta-information about the error | | errors | source | object | References to the source of the error. | | source | header | string | A string indicating the name of a single request header which caused the error. | | source | parameter | string | A string indicating which URI query parameter caused the error. | | source | pointer | string | A JSON pointer to the value in the request document that caused the error. | | errors | status | string | Status code of the response. | | errors | title | string | Short human-readable summary of the error. | {% /tab %} {% tab title="Example" %} ```json { "errors": [ { "detail": "Missing required attribute in body", "meta": {}, "source": { "header": "Authorization", "parameter": "limit", "pointer": "/data/attributes/title" }, "status": "400", "title": "Bad Request" } ] } ``` {% /tab %} {% /tab %} {% tab title="429" %} Too many requests {% tab title="Model" %} API error response. | Field | Type | Description | | ------------------------ | -------- | ----------------- | | errors [*required*] | [string] | A list of errors. | {% /tab %} {% tab title="Example" %} ```json { "errors": [ "Bad Request" ] } ``` {% /tab %} {% /tab %} ### Code Example ##### \## default # \# Use a Personal Access Token or Service Access Token export DD_BEARER_TOKEN="" \# Curl command curl -X POST "https://api.datadoghq.com/api/v2/llm-obs/v1/prompts" \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${DD_BEARER_TOKEN}" \ -d @- << EOF { "data": { "attributes": { "config": { "model": "provider-model", "response_format": { "type": "json_object" }, "temperature": 0.2 }, "description": "Answers customer questions using the company knowledge base.", "prompt_id": "customer-support-assistant", "template": [ { "content": "You are a helpful customer support assistant for {{company_name}}.", "role": "system" }, { "content": "Help {{customer_name}} with this question: {{question}}", "role": "user" } ], "title": "Customer Support Assistant" }, "type": "prompt-templates" } } EOF ##### ```python """ Create an Agent Observability prompt returns "OK" response """ from os import environ from datadog_api_client import ApiClient, Configuration from datadog_api_client.v2.api.agent_observability_api import AgentObservabilityApi from datadog_api_client.v2.model.llm_obs_create_prompt_data import LLMObsCreatePromptData from datadog_api_client.v2.model.llm_obs_create_prompt_data_attributes import LLMObsCreatePromptDataAttributes from datadog_api_client.v2.model.llm_obs_create_prompt_request import LLMObsCreatePromptRequest from datadog_api_client.v2.model.llm_obs_prompt_config import LLMObsPromptConfig from datadog_api_client.v2.model.llm_obs_prompt_type import LLMObsPromptType from datadog_api_client.v2.model.llm_obs_prompt_version_label import LLMObsPromptVersionLabel body = LLMObsCreatePromptRequest( data=LLMObsCreatePromptData( attributes=LLMObsCreatePromptDataAttributes( config=LLMObsPromptConfig( [("model", "provider-model"), ("response_format", "{'type': 'json_object'}"), ("temperature", "0.2")] ), env_ids=[], labels=[ LLMObsPromptVersionLabel.PRODUCTION, ], prompt_id="customer-support-assistant", template="You are a helpful assistant for .", ), type=LLMObsPromptType.PROMPT_TEMPLATES, ), ) configuration = Configuration() configuration.access_token = environ["DD_BEARER_TOKEN"] configuration.unstable_operations["create_llm_obs_prompt"] = True with ApiClient(configuration) as api_client: api_instance = AgentObservabilityApi(api_client) response = api_instance.create_llm_obs_prompt(body=body) print(response) ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=python) and then save the example to `example.py` and run following commands: DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" python3 "example.py" ##### ```ruby # Create an Agent Observability prompt returns "OK" response require "datadog_api_client" DatadogAPIClient.configure do |config| config.access_token = ENV["DD_BEARER_TOKEN"] config.unstable_operations["v2.create_llm_obs_prompt".to_sym] = true end api_instance = DatadogAPIClient::V2::AgentObservabilityAPI.new body = DatadogAPIClient::V2::LLMObsCreatePromptRequest.new({ data: DatadogAPIClient::V2::LLMObsCreatePromptData.new({ attributes: DatadogAPIClient::V2::LLMObsCreatePromptDataAttributes.new({ config: DatadogAPIClient::V2::LLMObsPromptConfig.new({}), env_ids: [], labels: [ DatadogAPIClient::V2::LLMObsPromptVersionLabel::PRODUCTION, ], prompt_id: "customer-support-assistant", template: "You are a helpful assistant for .", }), type: DatadogAPIClient::V2::LLMObsPromptType::PROMPT_TEMPLATES, }), }) p api_instance.create_llm_obs_prompt(body) ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=ruby) and then save the example to `example.rb` and run following commands: DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" rb "example.rb" ##### ```go // Create an Agent Observability prompt returns "OK" response package main import ( "context" "encoding/json" "fmt" "os" "github.com/DataDog/datadog-api-client-go/v2/api/datadog" "github.com/DataDog/datadog-api-client-go/v2/api/datadogV2" ) func main() { body := datadogV2.LLMObsCreatePromptRequest{ Data: datadogV2.LLMObsCreatePromptData{ Attributes: datadogV2.LLMObsCreatePromptDataAttributes{ Config: map[string]interface{}{ "model": "provider-model", "response_format": "{'type': 'json_object'}", "temperature": 0.2, }, EnvIds: []string{}, Labels: []datadogV2.LLMObsPromptVersionLabel{ datadogV2.LLMOBSPROMPTVERSIONLABEL_PRODUCTION, }, PromptId: "customer-support-assistant", Template: datadogV2.LLMObsPromptTemplate{ LLMObsPromptTextTemplate: datadog.PtrString("You are a helpful assistant for .")}, }, Type: datadogV2.LLMOBSPROMPTTYPE_PROMPT_TEMPLATES, }, } ctx := datadog.NewDefaultContext(context.Background()) ctx = context.WithValue(ctx, datadog.ContextAccessToken, os.Getenv("DD_BEARER_TOKEN")) configuration := datadog.NewConfiguration() configuration.SetUnstableOperationEnabled("v2.CreateLLMObsPrompt", true) apiClient := datadog.NewAPIClient(configuration) api := datadogV2.NewAgentObservabilityApi(apiClient) resp, r, err := api.CreateLLMObsPrompt(ctx, body) if err != nil { fmt.Fprintf(os.Stderr, "Error when calling `AgentObservabilityApi.CreateLLMObsPrompt`: %v\n", err) fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r) } responseContent, _ := json.MarshalIndent(resp, "", " ") fmt.Fprintf(os.Stdout, "Response from `AgentObservabilityApi.CreateLLMObsPrompt`:\n%s\n", responseContent) } ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=go) and then save the example to `main.go` and run following commands: DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" go run "main.go" ##### ```java // Create an Agent Observability prompt returns "OK" response import com.datadog.api.client.ApiClient; import com.datadog.api.client.ApiException; import com.datadog.api.client.v2.api.AgentObservabilityApi; import com.datadog.api.client.v2.model.LLMObsCreatePromptData; import com.datadog.api.client.v2.model.LLMObsCreatePromptDataAttributes; import com.datadog.api.client.v2.model.LLMObsCreatePromptRequest; import com.datadog.api.client.v2.model.LLMObsCreatePromptResponse; import com.datadog.api.client.v2.model.LLMObsPromptTemplate; import com.datadog.api.client.v2.model.LLMObsPromptType; import com.datadog.api.client.v2.model.LLMObsPromptVersionLabel; import java.util.Collections; import java.util.Map; public class Example { public static void main(String[] args) { ApiClient defaultClient = ApiClient.getDefaultApiClient(); defaultClient.setAccessToken(System.getenv("DD_BEARER_TOKEN")); defaultClient.setUnstableOperationEnabled("v2.createLLMObsPrompt", true); AgentObservabilityApi apiInstance = new AgentObservabilityApi(defaultClient); LLMObsCreatePromptRequest body = new LLMObsCreatePromptRequest() .data( new LLMObsCreatePromptData() .attributes( new LLMObsCreatePromptDataAttributes() .config( Map.ofEntries( Map.entry("model", "provider-model"), Map.entry("response_format", "{'type': 'json_object'}"), Map.entry("temperature", "0.2"))) .labels(Collections.singletonList(LLMObsPromptVersionLabel.PRODUCTION)) .promptId("customer-support-assistant") .template( new LLMObsPromptTemplate("You are a helpful assistant for ."))) .type(LLMObsPromptType.PROMPT_TEMPLATES)); try { LLMObsCreatePromptResponse result = apiInstance.createLLMObsPrompt(body); System.out.println(result); } catch (ApiException e) { System.err.println("Exception when calling AgentObservabilityApi#createLLMObsPrompt"); System.err.println("Status code: " + e.getCode()); System.err.println("Reason: " + e.getResponseBody()); System.err.println("Response headers: " + e.getResponseHeaders()); e.printStackTrace(); } } } ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=java) and then save the example to `Example.java` and run following commands: DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" java "Example.java" ##### ```rust // Create an Agent Observability prompt returns "OK" response use datadog_api_client::datadog; use datadog_api_client::datadogV2::api_agent_observability::AgentObservabilityAPI; use datadog_api_client::datadogV2::model::LLMObsCreatePromptData; use datadog_api_client::datadogV2::model::LLMObsCreatePromptDataAttributes; use datadog_api_client::datadogV2::model::LLMObsCreatePromptRequest; use datadog_api_client::datadogV2::model::LLMObsPromptTemplate; use datadog_api_client::datadogV2::model::LLMObsPromptType; use datadog_api_client::datadogV2::model::LLMObsPromptVersionLabel; use serde_json::Value; use std::collections::BTreeMap; #[tokio::main] async fn main() { let body = LLMObsCreatePromptRequest::new(LLMObsCreatePromptData::new( LLMObsCreatePromptDataAttributes::new( "customer-support-assistant".to_string(), LLMObsPromptTemplate::LLMObsPromptTextTemplate( "You are a helpful assistant for .".to_string(), ), ) .config(BTreeMap::from([ ("model".to_string(), Value::from("provider-model")), ("temperature".to_string(), Value::from(0.2)), ])) .env_ids(vec![]) .labels(vec![LLMObsPromptVersionLabel::PRODUCTION]), LLMObsPromptType::PROMPT_TEMPLATES, )); let mut configuration = datadog::Configuration::new(); configuration.set_unstable_operation_enabled("v2.CreateLLMObsPrompt", true); let api = AgentObservabilityAPI::with_config(configuration); let resp = api.create_llm_obs_prompt(body).await; if let Ok(value) = resp { println!("{:#?}", value); } else { println!("{:#?}", resp.unwrap_err()); } } ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=rust) and then save the example to `src/main.rs` and run following commands: DD_SITE="datadoghq.com" DD_API_KEY="" DD_APP_KEY="" cargo run ##### ```typescript /** * Create an Agent Observability prompt returns "OK" response */ import { client, v2 } from "@datadog/datadog-api-client"; const configuration = client.createConfiguration({ authMethods: { AuthZ: { accessToken: process.env.DD_BEARER_TOKEN as string, }, }, }); configuration.unstableOperations["v2.createLLMObsPrompt"] = true; const apiInstance = new v2.AgentObservabilityApi(configuration); const params: v2.AgentObservabilityApiCreateLLMObsPromptRequest = { body: { data: { attributes: { config: { model: "provider-model", response_format: "{'type': 'json_object'}", temperature: "0.2", }, envIds: [], labels: ["production"], promptId: "customer-support-assistant", template: "You are a helpful assistant for .", }, type: "prompt-templates", }, }, }; apiInstance .createLLMObsPrompt(params) .then((data: v2.LLMObsCreatePromptResponse) => { console.log( "API called successfully. Returned data: " + JSON.stringify(data) ); }) .catch((error: any) => console.error(error)); ``` #### Instructions First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=typescript) and then save the example to `example.ts` and run following commands: DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" tsc "example.ts" {% /tab %}