· 5 min read
Introducing Agent Evals: test your agents like you test your code
Evals bring regression testing to AI agents. Write a test once, run it on every deploy, and catch quality drops before your users do.
By Ava Thompson
Blog
Notes from the frontier
Product updates, engineering deep dives and practical guides for building agents.
· 8 min read
How we cut token costs by 32% without touching a prompt
Smart routing, semantic caching and a few boring tricks. Here's how we made every run cheaper across 4,000 teams.
By Kenji Watanabe
· 10 min read
A practical guide to agent observability
Traces, spans and scores: what to measure in production, which alerts matter, and how to debug an agent in minutes.
By Noah Becker
· 3 min read
Nova raises $24M to help every team ship AI agents
We're growing the team, opening two new regions and doubling down on the developer experience.
By Ava Thompson