Get Started

Create your first managed prompt in LangWatch, link it to traces, and use it in your application with built-in prompt versioning and analytics.

Automated setup available. Copy the prompts skill prompt into your coding agent to set up prompt versioning automatically.

A prompt managed in LangWatch holds its text and its dynamic variables on the platform, so your team can update AI interactions without changing code. The steps below create your first prompt and call it from your application.

Get API keys

1. Create a LangWatch account or set up self-hosted LangWatch
2. Create new API credentials in your project settings
3. Note your API key for use in the steps below

Create a prompt

LangWatch UI

Use the LangWatch UI to create a new prompt or update an existing one.

1. Navigate to your project dashboard
2. Go to Prompt Management in the sidebar
3. Click “Create New Prompt”
4. Fill in the prompt details and save

TypeScript SDK

create_prompt.ts

import { LangWatch } from "langwatch";

// Initialize LangWatch client
const langwatch = new LangWatch({
  apiKey: process.env.LANGWATCH_API_KEY
});

// Create a new prompt
const prompt = await langwatch.prompts.create({
  handle: "customer-support-bot",
  scope: "PROJECT",
  prompt: "You are a helpful customer support agent. Help the customer with their inquiry: {{input}}",
  model: "openai/gpt-5-mini"
});

console.log(`Created prompt with handle: ${prompt.handle}`);

Python SDK

create_prompt.py

import langwatch

# Create a new prompt
prompt = langwatch.prompts.create(
    handle="customer-support-bot",
    scope="PROJECT",
    prompt="You are a helpful customer support agent. Help the customer with their inquiry: {{input}}",
    model="openai/gpt-5-mini"
)

print(f"Created prompt with handle: {prompt.handle}")

REST API

Use the REST API to create a new prompt:

create_prompt.sh

# Create a new prompt (this creates the prompt with an initial version)
curl -X POST "https://app.langwatch.ai/api/prompts" \
  -H "Content-Type: application/json" \
  -H "X-Auth-Token: your-api-key" \
  -d '{
    "handle": "customer-support-bot",
    "scope": "PROJECT",
    "prompt": "You are a helpful customer support agent. Help the customer with their inquiry: {{input}}",
    "model": "openai/gpt-5-mini"
  }'

Use prompt

At runtime, you can fetch the latest version of your prompt from LangWatch using the prompt handle.

Python SDK

use_prompt.py

import langwatch
from litellm import completion

# Get the latest prompt by handle
prompt = langwatch.prompts.get("customer-support-bot")

# Compile prompt with variables
compiled_prompt = prompt.compile(
    user_name="John Doe",
    user_email="[e-mail]",
    input="How do I reset my password?"
)

# Use with LiteLLM (unified interface to multiple providers)
response = completion(
    model=prompt.model,  # LiteLLM handles provider prefixes automatically
    messages=compiled_prompt.messages
)

print(response.choices[0].message.content)

TypeScript SDK

use_prompt.ts

import { LangWatch } from "langwatch";
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

// Initialize LangWatch client
const langwatch = new LangWatch({
  apiKey: process.env.LANGWATCH_API_KEY
});

// Get the latest prompt by handle
const prompt = await langwatch.prompts.get("customer-support-bot");

// Compile prompt with variables
const compiledPrompt = prompt.compile({
  user_name: "John Doe",
  user_email: "[e-mail]",
  input: "How do I reset my password?"
});

// Use with AI SDK
const result = await generateText({
  model: openai(prompt.model.replace("openai/", "")),
  messages: compiledPrompt.messages,
  experimental_telemetry: { isEnabled: true },
});

console.log(result.text);

REST API

use_prompt.sh

# Get prompt by handle
curl -X GET "https://app.langwatch.ai/api/prompts/customer-support-bot" \
  -H "X-Auth-Token: your-api-key"

Link with LangWatch Tracing

You can link your prompt to LLM generation traces to track performance and see which prompt versions work best. For detailed information about linking prompts to traces, see the Link to Traces page.

Python SDK

tracing.py

import langwatch
from litellm import completion

# Initialize LangWatch
langwatch.setup()

# Create a trace function
@langwatch.trace()
def customer_support_generation():
    # Get prompt (automatically linked to trace when API key is present)
    prompt = langwatch.prompts.get("customer-support-bot")

    # Compile prompt with variables
    compiled_prompt = prompt.compile(
        user_name="John Doe",
        user_email="[e-mail]",
        input="I need help with my account"
    )

    # Use with LiteLLM (unified interface to multiple providers)
    response = completion(
        model=prompt.model,  # LiteLLM handles provider prefixes automatically
        messages=compiled_prompt.messages
    )

    return response.choices[0].message.content

# Call the function
result = customer_support_generation()

TypeScript SDK

tracing.ts

import { LangWatch, getLangWatchTracer } from "langwatch";
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

// Initialize LangWatch client
const langwatch = new LangWatch({
  apiKey: process.env.LANGWATCH_API_KEY
});

const tracer = getLangWatchTracer("customer-support");

async function customerSupportGeneration() {
  return tracer.withActiveSpan("customer-support-generation", async () => {
    // Get prompt (automatically linked to trace when API key is present)
    const prompt = await langwatch.prompts.get("customer-support-bot");

    // Compile prompt with variables
    const compiledPrompt = prompt.compile({
      user_name: "John Doe",
      user_email: "[e-mail]",
      input: "I need help with my account",
    });

    // Use with AI SDK
    const { text } = await generateText({
      model: openai(prompt.model.replace("openai/", "")),
      messages: compiledPrompt.messages
    });

    return text;
  });
}

// Call the function
const result = await customerSupportGeneration();

---

← Back to Prompt Management Overview