Get monthly updates with our latest articles, podcasts, videos, and more.
Recent posts
Why we built Decagon Duet on Agent Operating Procedures
When we started building Duet, we first considered connecting a frontier reasoning model directly to our platform. Here's why we took a different path.
Optimizing GEPA for production: A test-driven approach to prompt engineering
GEPA is a gradient-free optimizer that uses natural language reflection rather than policy gradients to adapt prompts.
Designing low-latency AI agents through reranker optimization
We traced a meaningful chunk of our response latency back to a single stage in our RAG pipeline: reranking.
Deliver the concierge experiences your customers deserve