FetchPrompt is a prompt lifecycle management platform. Store, version, and fetch your AI prompts at runtime via a simple REST API.

Introduction

FetchPrompt is a prompt lifecycle management platform built for teams that work with AI. It gives you a central place to store, version, and serve prompt templates — and a REST API to fetch them at runtime so you can iterate on prompts without redeploying your application.

Why FetchPrompt?

When you hardcode prompts inside your application code, every change requires a code review, a merge, and a deployment. This slows down iteration, makes collaboration between engineers and non-engineers difficult, and increases the risk of shipping broken prompts.

FetchPrompt solves this by decoupling prompts from your application code:

Store prompts centrally — Write and manage prompts in a web dashboard instead of scattered across source files.
Fetch at runtime — Your application calls the FetchPrompt API to get the latest prompt content on every request.
Version everything — Every save creates an immutable snapshot. Roll back to any previous version instantly.
Separate environments — Maintain independent Stage and Production versions of every prompt. Test changes safely before going live.
Collaborate across roles — Product managers, prompt engineers, and developers can all edit prompts without touching application code.

How it works

The core workflow has three steps:

Create a prompt in the FetchPrompt dashboard. Give it a name, write the content, and use {{variables}} for dynamic values.
Generate an API key for your target environment (Stage or Production).
Fetch the prompt at runtime from your application using a simple HTTP request.

curl -H "Authorization: Bearer fp_prod_your_key" \
  "https://www.fetchprompt.com/api/v1/prompts/customer-support-bot?user_name=Sarah"

The API returns the prompt content with variables interpolated:

{
  "slug": "customer-support-bot",
  "name": "Customer Support Bot",
  "content": "You are a helpful customer support agent. The customer's name is Sarah.",
  "version": 3,
  "environment": "prod"
}

Key concepts

Concept	Description
Prompt	A named template with content that can include `{{variable}}` placeholders. Identified by a unique slug.
Environment	Each prompt has independent Stage and Production versions. API keys are scoped to one environment.
Version	Every save creates a new numbered version with an immutable snapshot. Versions are never overwritten.
Variable	A `{{placeholder}}` in prompt content that gets replaced at fetch time with values you provide.
API Key	A Bearer token (prefixed `fp_stage_` or `fp_prod_`) used to authenticate API requests and determine which environment to serve.
Slug	A URL-friendly identifier auto-generated from the prompt name (e.g., `customer-support-bot`). Used in API calls.

Free tier

FetchPrompt is free to start with generous limits:

Unlimited prompts — no limit on the number of prompts you create
30,000 API calls per month — per organization, across all prompts and environments
2 environments — Stage and Production
Unlimited team members — invite your whole team

Next steps

Getting Started — Create your first prompt and make your first API call in under 5 minutes.
API Reference — Full documentation of every endpoint, request format, and response shape.
Environments — Learn how Stage and Production environments work together.