Platform V2: Faster Deployments & New AI Models

We've shipped major performance improvements and expanded AI model support. Here's what's new.

3× Faster Container Startup

Agent deployments now start in under 10 seconds, down from 30+ seconds. We optimized our container orchestration layer and implemented aggressive caching for base images.

New AI Models

You can now deploy agents with:

• GPT-4o - OpenAI's latest multimodal model
• Claude 3.5 Sonnet - Anthropic's most capable model
• Gemini 1.5 Pro - Google's 1M token context window
• Groq Llama 3 - Ultra-fast inference

Improved Dashboard

The dashboard now shows real-time CPU & memory usage, message counts, and uptime metrics. You can restart, stop, or update your agent with one click.

What's Next

We're working on custom domains, WhatsApp integration, and a visual agent builder. Stay tuned.