Prompt Engine
Run any prompt and get the optimal model to execute it without worrying about GPUs, tokens, or rate limits—it just works effortlessly.
Introduction
JigsawStack Prompt Engine is a powerfult API built from the ground up to execute any prompt or instruction seamlessly. It intelligently selects the best model from a cluster of state-of-the-art models, allowing you to focus on results without worrying about GPUs, tokens, or rate limits.
The Prompt Engine takes in three things: the prompt, dynamic variables, and the output structure you expect every single time you run the prompt. The last two are optional. The Prompt Engine automatically enhances the initial prompt to improve accuracy, reduce token usage, and prevent output structure breakage.
The Prompt Engine is great for a variety of task which include:
- Intelligent AI agents or Chatbots.
- Automations and workflows.
- Data extraction and analysis.
- Complex natural language processing
The Prompt Engine can be utilized in two ways:
- Creating and running a reusable prompt (recommended)
- Executing a prompt directly
Let’s explore these approaches by evaluating job application entries to determine if candidates meet the necessary job requirements.
Initial requirements
- Setup a JigsawStack account (if you don’t have an account already)
- Get your JigsawStack API key from here.
- Install the Node.js SDK
Approach 1 - Creating and executing a reusable prompt (recommended)
- Create the prompt
- Run the prompt
Approach 2 - Executing the prompt directly
That’s it! We’ve used the Prompt Engine API to automatically evaluate job applications.
Recommendations
- For prompts that will be used multiple times, it is recommended to first Create the prompt and then Run it using the prompt ID for better reliability.
- Run Prompt Direct is ideal for one-time use.
Find more information on Prompt Engine API here
Was this page helpful?