Integration · Azure OpenAI
Azure OpenAI Prompt Management
Enterprise teams on Azure OpenAI need prompt governance too. PromptForge adds version control, audit trails, and live API delivery to every GPT-5.3 Instant deployment prompt.
PromptForge + Azure OpenAI in one file
Version, template, and serve Azure OpenAI prompts via REST API. Manage system prompts for Azure GPT-4o deployments in PromptForge, add the governance layer your enterprise deployments require without touching application code.
- 1
- Fetch your versioned, interpolated prompt from the PromptForge REST API with a single
fetch()call. - 2
- Pass the returned
contentstring directly to the Azure OpenAI SDK as the system prompt, no transformation needed. - 3
- Update the prompt in the PromptForge dashboard anytime, running applications pick up the change on the next request. No redeployment required.
import { AzureOpenAI } from "openai";
const client = new AzureOpenAI({
endpoint: process.env.AZURE_OPENAI_ENDPOINT,
apiKey: process.env.AZURE_OPENAI_API_KEY,
apiVersion: "2025-01-01-preview",
deployment: "gpt-4o",
});
async function fetchPrompt(region: string, compliance: string) {
const res = await fetch(
"https://www.promptforge-app.com/api/v1/prompts/your-prompt-id",
{
method: "POST",
headers: {
Authorization: "Bearer pfk_your_api_key",
"Content-Type": "application/json",
},
body: JSON.stringify({
version: "latest",
variables: { region, compliance },
}),
}
);
const { content } = await res.json();
return content as string;
}
// Prompt template in PromptForge (e.g.):
// You are an enterprise assistant for {{region}}. Follow {{compliance}} guidelines.
// 1. Fetch the system prompt with dynamic variables (region, compliance)
const content = await fetchPrompt("EU", "GDPR");
// 2. Call your Azure OpenAI deployment with the versioned prompt
const completion = await client.chat.completions.create({
model: "gpt-5.3-chat-latest",
messages: [
{ role: "system", content },
{ role: "user", content: "Draft a GDPR-compliant data retention policy." },
],
});
console.log(completion.choices[0].message.content);Azure OpenAI + PromptForge in Three Steps
Add a prompt management layer to your Azure OpenAI integration without refactoring your application.
Store Azure deployment prompts as versioned templates
Azure OpenAI deployments are fixed model snapshots, but your system prompts must evolve. Store them in PromptForge with {{region}}, {{compliance}}, or {{business_unit}} variables and manage them independently of your deployment configuration.
Maintain an audit trail for every prompt change
Enterprise deployments often require proof of what prompt was active at a given time. PromptForge's version history gives you a timestamped, immutable record of every change, satisfying internal audit and compliance requirements without manual documentation.
Fetch and inject into your Azure SDK calls
The `AzureOpenAI` SDK from the `openai` npm package is API-compatible with PromptForge. Fetch the system prompt once, pass it to `client.chat.completions.create`, and update it from the PromptForge dashboard, your Azure deployment configuration never needs to change.
Powerful Prompt Management Features for AI Developers
From simple prompt storage to production-ready APIs with version control, dynamic variables, rollback, and a public gallery.
Dynamic Variables
Use {{variable}} syntax to create reusable prompt templates. Pass different values via API for endless customization across any LLM.
Instant Prompt API
RESTful API endpoint ready in seconds. Fetch any prompt with version pinning and variable interpolation. No redeployment needed.
Rollback with Diff Checker
View a line-by-line diff of every change and roll back to any previous version in one click. Never lose a working prompt again.
Publish to Gallery
Share your best prompts with the community in the public gallery. Get discovered by other developers and grow your personal library.
Start for free, upgrade anytime
No credit card required to get started. Paid plans include a 14-day free trial.
- 1k API requests/month
- 1 prompt
- Unlimited versions
- Dynamic variables
- Version pinning
- API key management
No charge until your trial ends
- 10k API requests/month
- 5 prompt
- Unlimited versions
- Dynamic variables
- Version pinning
- API key management
No charge until your trial ends
- 100k API requests/month
- 25 prompt
- Unlimited versions
- Dynamic variables
- Version pinning
- API key management
No charge until your trial ends
- 500k API requests/month
- 100 prompt
- Unlimited versions
- Dynamic variables
- Version pinning
- API key management
Questions? Contact us
Azure OpenAI + PromptForge: Common Questions
Specific answers for developers integrating PromptForge with Azure OpenAI.
How do I use PromptForge with Azure OpenAI's deployment names?
Azure OpenAI uses deployment names (e.g. `gpt-4o`, `gpt-4o-mini`) to route requests, these are set in your `AzureOpenAI` client config and are separate from prompt management. PromptForge manages the prompt text. Store a separate PromptForge prompt per deployment if the deployments serve different use cases, or share one prompt across deployments if the system message is the same. The deployment name and prompt ID are independent configuration values.
Can PromptForge work with Azure OpenAI's content filtering settings?
Azure OpenAI's content filters are configured at the deployment level in Azure AI Studio, they are not part of the prompt. PromptForge manages the system prompt text that guides model behaviour above the content filter layer. If your content filtering configuration requires specific instructional framing in the system prompt (for example, explicit refusal instructions), store and version that framing in PromptForge so you can update it centrally across all deployments.
Does PromptForge support Azure OpenAI private endpoints?
PromptForge's API (`api.promptforge-app.com`) is a separate HTTPS endpoint from your Azure OpenAI private endpoint. Your application makes two calls: one to PromptForge to retrieve the prompt (requiring outbound internet access to `api.promptforge-app.com`), and one to your Azure private endpoint for inference. If your environment prohibits outbound internet access entirely, you can pre-fetch and cache the PromptForge prompt at deployment startup time, refreshing it on a schedule rather than per-request.
How do I version prompts when migrating between Azure OpenAI model versions?
When Microsoft releases a new model version (e.g. `2024-11-20` → `2025-01-01`), prompt behaviour sometimes shifts. Keep your current prompt pinned to a specific PromptForge version number in production while you test a new prompt version against the updated model in staging. Once you validate the new prompt version's output quality, update your production API call to fetch the new version. This staged rollout pattern minimises regression risk during Azure model version transitions.