Welcome to Prompt Forge
Your powerful toolkit for AI prompt engineering, evaluation, and optimization.
Get Started
Simple LLM as a Judge Evaluation
Evaluate prompts using an LLM as a judge based on specified metrics. Upload JSON and adjust parameters.
Simple Ground Truth LLM Evaluation
Evaluate prompts by comparing LLM outputs against a provided ground truth dataset.
Automated Prompt Engineering (APE)
Let AI iterate and optimize your prompt to maximize its performance based on your goals.
Overview
Activity Feed
View your recent tasks and project statuses.
- 2h ago
Marketing Campaign Prompts
Optimization Complete
- 5h ago
Evaluated "New User Welcome Email" (LLM Judge)
Score: 88.5
- 1 day ago
Customer Support Chatbot
Evolution In Progress (Gen 3/10)
- 2 days ago
APE for "Slogan Generation"
Error during evaluation
- 3 days ago
Evaluated "FAQ Accuracy" (Ground Truth)
Score: 92.0