AI Briefing#prompt-optimization
The latest AI and developer news about #prompt-optimization, with the original source and a short summary.
The latest AI and developer news about #prompt-optimization, with the original source and a short summary.
Microsoft has released AutoSaddler, a system that analyzes agent execution traces to automatically update prompts and tools.
Apple released PROOF-Gen, which recovers failed tool-calling scenarios to significantly improve model distillation performance.
DSPy's Flex leverages GEPA to automatically optimize not just prompts but also program code.
Factory adopted LangSmith to gain observability into its LLM pipelines and automate feedback loops, doubling its product iteration speed.
CANTANTE improves multi-agent prompt optimization through credit assignment.
Amazon Bedrock has released a tool that helps optimize prompts and switch models by comparing up to 5 models.
LangChain has launched LangChain Labs, an applied research organization focused on continual learning for agents.
Promptimus automatically improves already-good LLM prompts without manual work.
Netflix used LLM judges and agents to automatically evaluate synopsis quality in line with human standards.
DSPy made Dropbox Dash's relevance judge cheaper and more accurate.
The LangChain team has released the Promptim library, which automatically improves prompts based on datasets and evaluation metrics.
Cohere has released Prompt Tuner in beta, a feature that automatically improves prompts.