crtd labs inc
An email marketing simulation for an e-commerce brand to increase sales
Core trick
An LLM writes email variants, a persona simulator predicts opens and clicks, and a 5-email schedule search picks the best send times.
Description
An email marketing simulation for an e-commerce brand to increase sales
README excerpt
--- title: Email Campaign Simulation emoji: 🔉 colorFrom: blue colorTo: pink sdk: docker pinned: false app_port: 8000 tags: - openenv - email-marketing - simulation --- # Email Campaign Simulation Environment Simulation environment for testing and optimizing a clothing-brand email campaign. The workflow combines: - Email copy generation (DeepSeek + template fallback) - 10x marketer judging (rule-based + DeepSeek scoring) - Persona-based simulation for opens, CTR, and purchases - 5-email day/time schedule optimization ## Quick Start Run the 5-email optimizer: ```bash python simulate_5_email_campaign.py \ --persona-source hf \ --send-days mon,tue,wed,thu,fri,sat,sun \ --send-hours 8,10,12,15,18,21 ``` Run variant-level campaign simulation: ```bash python simulate_brand_campaign.py --persona-source hf ``` Outputs are written to `outputs/evals/`. ## Building the Docker Image Before using the environment, you need to build the Docker image: ```bash # From project root docker build -t clothing_brand_ctr_env-env:latest -f server/Dockerfile . ``` ## Deploying to Hugging Face Spaces You can easily deploy your OpenEnv environment to Hugging Face Spaces using the `openenv push` command: ```bash # From the environment directory (where openenv.yaml is located) openenv push # Or specify options openenv push --namespace my-org --private ``` The `openenv push` command will: 1. Validate that the directory is an OpenEnv environment (checks for `openenv.yaml`) 2. Pre