Introducing Proactive Agents.
Learn more
Product Update
Company news
Technology & research
Industry

Company

Blog
/

Written by

Table of contents
Example h2

Subscribe to our newsletter

Get monthly updates with our latest articles, podcasts, videos, and more.

Recent posts

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.

Why off-policy training isn't enough: SFT, RL, and the limits of imitation

The choice between off-policy and on-policy training shapes not just how well a model performs, but how it fails.

Deliver the concierge experiences your customers deserve

Get a demo