Language Guide · Ruby
Manage AI Prompts in Ruby
No SDK required. One HTTP call.
Fetch versioned, variable-interpolated AI prompts from Ruby using the standard library. Works with Rails, Sinatra, and any Ruby application — no new gems required.
Code Example
One function. Any AI provider.
Fetch a versioned, interpolated prompt from PromptForge with a single HTTP call. The returned content string passes directly to your AI SDK — no transformation, no adapter, no extra library.
- 1Fetch a versioned prompt by ID with your variable values.
- 2Receive the fully rendered content string in the response.
- 3Pass it directly to your AI provider SDK as the system prompt.
require 'net/http'
require 'json'
def fetch_prompt(api_key:, prompt_id:, vars: {})
uri = URI("https://www.promptforge-app.com/api/v1/prompts/#{prompt_id}")
uri.query = URI.encode_www_form({ _version: 'latest' }.merge(vars))
request = Net::HTTP::Get.new(uri)
request['Authorization'] = "Bearer #{api_key}"
response = Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(request)
end
JSON.parse(response.body)['content']
end
content = fetch_prompt(
api_key: ENV['PROMPTFORGE_API_KEY'],
prompt_id: 'YOUR_PROMPT_ID',
vars: { role: 'developer', task: 'review code' },
)
# Pass content to any AI SDKWhy Ruby teams choose PromptForge
Designed for developers who want control without complexity.
Zero new gems
Net::HTTP and JSON are in the Ruby standard library. No Gemfile entry, no bundle install, no gem conflicts to worry about.
Rails-friendly by default
Wrap in a service object, call from an initializer, or memoize with Rails.cache.fetch. Fits every Rails architecture pattern without friction.
Cache per version for performance
Pin to a specific version number and cache the response indefinitely. When you publish a new prompt version, bump the pin to invalidate automatically.
Integrate in 4 steps
From zero to fetching your first versioned prompt in under 10 minutes. No framework setup, no SDK installation — just HTTP.
- 1
Create a prompt with variables
Open the dashboard, click New Prompt, and write your system prompt using {{variable}} placeholders for any dynamic values.
- 2
Copy your prompt ID
Your prompt ID appears in the URL bar when editing: /dashboard/prompts/YOUR_PROMPT_ID. The API Usage panel also shows it with pre-filled examples.
- 3
Generate an API key
Go to the API settings page and click Generate Key. Store it with dotenv or the Rails credentials system and read from ENV.
- 4
Fetch with Net::HTTP
Build a GET request with the Authorization header, start a TLS connection, and parse the response JSON. Pass the content string to your AI provider gem.
Teams building AI features in Ruby
Rails product teams use PromptForge to let non-engineers refine AI prompts without submitting PRs or waiting for deploy windows. The prompt change is live in production on the next request — no Capistrano, no Heroku slug compile, no waiting.
Start Free TrialStart for free, upgrade anytime
No credit card required to get started. Paid plans include a 14-day free trial.
- 1 Production Prompt
- 1,000 API Requests/mo
- Stable/Latest Channel Routing
- No Credit Card Required
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