Blogs

Self-Improving Agents, Powered by Your Evals

Fireworks

Eval Protocol is a unified eval interface that powers both prompt optimization and RL on the same evaluation function.

Visit Site

Blogs Fireworks

BlogsFrontier AI at a fraction of the cost: open-source worker agents with a closed-source advisor.Fireworks BlogsOpen, frontier, and yours: LangChain Deep Agents on NVIDIA Nemotron 3 Ultra, running on FireworksFireworks BlogsTrain past the frontier: Training API now generally availableFireworks BlogsBest Practices for Multi-Turn RLFireworks BlogsDeepSeek V3 just got vision capabilities!Fireworks BlogsVision Model Platform Updates: Enhanced Capabilities and New FeaturesFireworks BlogsIntroducing ClickStack Cloud: Serverless observability powered by ClickHouseClickhouse BlogsClickStack and Hud bring runtime intelligence to AI-powered developmentClickhouse Products & ServicesZero Standing Privileges (ZSP) Solution1password EventsPyData Amsterdam Meetup: Agents in the Data-verseMotherduck BlogsWhat’s New: Streamlined User Management, Metadata, and UI EnhancementsMotherduck BlogsStructured memory management for AI Applications and AI Agents with DuckDBMotherduck BlogsStreamline the Development of Real-Time AI Applications with MindsDB Docker ExtensionDocker BlogsLima v2.1: macOS guests and enhanced AI agent safetyCncf BlogsHow Jaeger is evolving to trace AI agents with OpenTelemetryCncf BlogsIntroducing Prempti: Policy and visibility for AI coding agentsCncf BlogsBest AI Video Tools for Real Estate Listings, Virtual Staging, and Property Videos in 2026Heygen LearnSlack Agents on Vercel with the AI SDKVercel JobsFull-stack Engineer - Creative AgentsElevenlabs Products & ServicesNatural AI Voice Agents that Take Action by ElevenLabsElevenlabs