News
Introducing AI Evaluation: Close the Loop Across the Full AI Lifecycle
New Relic adds AI Evaluation to its AI Observability platform, using an LLM to score prompts for safety and accuracy, flagging injection, leakage, and hallucinations.
More News
- Flux9s GA: Flux Cluster State, From the Terminal
- DigitalOcean MicroVMs: Fast, Isolated Compute for Your AI Agent Infrastructure
- Zero‑Downtime PostgreSQL Migrations: A Production Playbook for Safe Schema Changes
- Anthropic Introduces Agentic Evaluations to Benchmark AI Agent Quality, Performance, & Safety
- Solana Rally Shows Signs of Exhaustion