AI Briefing#rag
The latest AI and developer news about #rag, with the original source and a short summary.
The latest AI and developer news about #rag, with the original source and a short summary.
AI adoption is spreading across financial services, but trust and governance remain the key to moving into production.
Enterprises need execution-capable knowledge agents, not simple RAG chatbots.
This piece summarizes the AI technology trends and service application cases that LY Corporation presented at Tech-Verse 2025.
Kakaopay has developed 'Pageny,' a financial AI concierge that uses a multi-agent architecture based on AWS Bedrock.
AI21 presented grounding as the key challenge for enterprise AI.
A planning-based AI pipeline was presented as a way to manage both product description quality and regulation together.
For AI agents to succeed, they must go beyond simple information retrieval and perform knowledge work that handles complex reasoning and context.
Upstage and Chosun Ilbo are pushing forward Korea's first commercialization of media-specialized AI.
Upstage has released the 10.7B-parameter Solar Mini on AWS.
The Kakao Pay team used AWS AI services to develop the 'Geum.Yong.Sa.' service, which explains difficult financial terms and recommends related products.
RAG agents should be evaluated on accuracy, observability, adaptability, time-to-value, and enterprise readiness.
Parallel subagents and prompt/eval design pushed Research's performance higher.
Mistral AI has launched Codestral Embed, a specialized embedding model optimized for code retrieval and understanding.
Mistral has announced the Agents API for building AI agents equipped with code execution, web search, and image generation capabilities.
It explains the concept and causes of hallucination, a phenomenon where AI models plausibly generate information that differs from the facts.
Kakao Pay implemented a voice consultation chatbot that recommends personalized loan products using AWS AI services.
KakaoPay held its in-house hackathon '2025 CafeTon' offline, leveraging AWS Generative AI.
Cohere's major LLM and multimodal models are now available for serverless inference on the Hugging Face Hub.
This introduces how to use an LLM as a judge to evaluate the performance of RAG systems and presents the RAG Triad framework.
RAG evaluation should look at real-world document relationships rather than just scores.
Zendesk is introducing proactive AI agents that plan and execute on their own, powered by OpenAI models.
The Sentence Transformers v4.0 update reveals an efficient way to train and fine-tune Reranker models.
Hebbia has unveiled Matrix, a multi-agent platform that automates 90% of financial and legal work by leveraging OpenAI models.
Presents how to build a high-performance, low-power RAG application using FuriosaAI's RNGD accelerator.