22 posts
line 들어가며 지난 엔터프라이즈 LLM 서비스 구축기 1: 컨텍스트 엔지니어링에서는 260개의 도구와 수백 페이지의 문서를 다루는 환경에서 LLM에게 필요한 정보만 골라서 제공하는 '점진적 공개' 전략을 공유해 드렸습니다. 1편이 AI에게 '무엇을 전달할 것인가?'에 대한 답이었다면, 이번 2편은 그 다음 질문으로 넘어갑니다. 정제된 맥락을 전달받는 에이전트를 '어떻게 만들 것인가?'입니다. 본격적인 이야기에 앞서, 먼저 현재 Flava AI 어시스턴트(이하 FAA)의 실전 성적표를 공개합니다. 저희…
aws AWS Weekly Roundup: OpenAI partnership, AWS Elemental Inference, Strands Labs, and more (March 2, 2026) This past week, I’ve been deep in the trenches helping customers transform their businesses through AI-DLC (AI-Driven Lifecycle) workshops. Throughout 2026, I’ve had the privi…
dropbox Using LLMs to amplify human labeling and improve Dash search relevance When someone uses Dropbox Dash to search or ask a question, it follows a retrieval-augmented generation (RAG) pattern. This means our AI first retrieves relevant company information and then uses that informa…
toss 당신의 팀은 같은 LLM을 쓰고 있나요? 현재 많은 개발팀이 LLM을 도입하고 있지만, 냉정하게 들여다보면 그것은 '각자도생'에 가깝습니다. 같은 모델, 같은 IDE를 쓰는데도 결과물의 차이는 극심합니다. 어떤 엔지니어는 '컨텍스트 엔지니어링(Context Engineering)'에 대한 높은 이해도로 LLM에게 정확한 역할을 부여해 10분 만에 복잡한 리팩토링을 끝냅니다. 반면, 어떤 엔지니어는 단순한 질문과 답변을 반복하며 할루시네이션과 씨름하느라 1시간을 허비하죠. 예를 들어, 같은 레포지…
microsoft When we launched the Microsoft Learn Model Context Protocol (MCP) Server in June 2025, our goal was simple: make it effortless for AI agents to use trusted, up-to-date Microsoft Learn documentation. GitHub Copilot and other agents are increasingly common, and they need to be abl…
google How AI tools can redefine universal design to increase accessibility February 5, 2026 Marian Croak, VP Engineering, and Sam Sepah, Lead AI Accessibility PgM, Google Research Google Research's Natively Adaptive Interfaces (NAI) redefine universal design by embedding multimodal AI…
dropbox Engineering VP Josh Clemm on how we use knowledge graphs, MCP, and DSPy in Dash I was recently a guest speaker in Jason Liu’s online course on RAG offered by the education platform Maven. I did some mini deep-dives into what we’ve been doing at Dropbox with knowledge graphs; how…
netflix Featured The AI Evolution of Graph Search at Netflix: From Structured Queries to Natural Language -- 8 Listen Share By Alex Hutter and Bartosz Balukiewicz Our previous blog posts (part 1, part 2, part 3) detailed how Netflix’s Graph Search platform addresses the challenges of se…
toss The current AI hype cycle is a significant economic bubble where massive infrastructure investments of $560 billion far outweigh the modest $35 billion in generated revenue. However, drawing parallels to the 1995 dot-com era, the author argues that while short-term expectations are overblown, the long-term transformation of the developer role is inevitable. The conclusion is that developers won't be replaced but will instead evolve into "Code Creative Directors" who manage AI through the lens of technical abstraction and delegation. ### The Economic Bubble and Amara’s Law * The industry is experiencing a 16:1 imbalance between AI investment and revenue, with 95% of generative AI implementations reportedly failing to deliver clear efficiency improvements. * Amara’s Law suggests that we are overestimating AI's short-term impact while potentially underestimating its long-term necessity. * Much of the current "AI-driven" job market contraction is actually a result of companies cutting personnel costs to fund expensive GPU infrastructure and AI research. ### Jevons Paradox and the Evolution of Roles * Jevons Paradox indicates that as the "cost" of producing code drops due to AI efficiency, the total demand for software and the complexity of systems will paradoxically increase. * The developer’s identity is shifting from "code producer" to "system architect," focusing on agent orchestration, result verification, and high-level design. * AI functions as a "power tool" similar to game engines, allowing small teams to achieve professional-grade output while amplifying the capabilities of senior engineers. ### Delegation as a Form of Abstraction * Delegating a task to AI is an act of "work abstraction," which involves choosing which low-level details a developer can afford to ignore. * The technical boundary of what is "hard to delegate" is constantly shifting; for example, a complex RAG (Retrieval-Augmented Generation) pipeline built for GPT-4 might become obsolete with the release of a more capable model like GPT-5. * The focus for developers must shift from "what is easy to delegate" to "what *should* be delegated," distinguishing between routine boilerplate and critical human judgment. ### The Risks of Premature Abstraction * Abstraction does not eliminate complexity; it simply moves it into the future. If the underlying assumptions of an AI-generated system change, the abstraction "leaks" or breaks. * Sudden shifts in scaling (traffic surges), regulation (GDPR updates), or security (zero-day vulnerabilities) expose the limitations of AI-delegated work, requiring senior intervention. * Poorly managed AI delegation can lead to "abstraction debt," where the cost of fixing a broken AI-generated system exceeds the cost of having written it manually from the start. To thrive in this environment, developers should embrace AI not as a replacement, but as a layer of abstraction. Success requires mastering the ability to define clear boundaries for AI—delegating routine CRUD operations and boilerplate while retaining human control over architecture, security, and complex business logic.
line LY Corporation’s engineering team developed an AI assistant for their private cloud platform, Flava, by prioritizing "context engineering" over traditional prompt engineering. To manage a complex environment of 260 APIs and hundreds of technical documents, they implemented a strategy of progressive disclosure to ensure the LLM receives only the most relevant information for any given query. This approach allows the assistant to move beyond simple RAG-based document summarization to perform active diagnostics and resource management based on real-time API data. ### Performance Limitations of Long Contexts * Research indicates that LLM performance can drop by 13.9% to 85% as context length increases, even if the model technically supports a large token window. * The phenomenon of "context rot" occurs when low-quality or irrelevant information is mixed into the input, causing the model to generate confident but incorrect answers. * Because LLMs are stateless, maintaining conversation history and processing dense JSON responses from multiple APIs quickly exhausts context windows and degrades reasoning quality. ### Progressive Disclosure and Tool Selection * The system avoids loading all 260+ API definitions at once; instead, it analyzes the user's intent to select only the necessary tools, such as loading only Redis-related APIs when a user asks about a cluster. * Specific product usage hints, such as the distinction between private and CDN settings for Object Storage, are injected only when those specific services are invoked. * This phased approach significantly reduces token consumption and prevents the model from being overwhelmed by irrelevant technical specifications. ### Response Guidelines and the "Mock Tool Message" Strategy * The team distinguished between "System Prompts" (global rules) and "Response Guidelines" (situational instructions), such as directing users to a console UI before suggesting CLI commands. * Injecting specific guidelines into the system prompt often caused "instruction conflict," where the LLM might hallucinate information to satisfy a guideline while ignoring core requirements like using search tools. * To resolve these conflicts, the team utilized "ToolMessages" to inject guidelines; by formatting instructions as if they were results from a tool execution, the LLM treats the information as factual context rather than a command that might override the system prompt. To build a robust enterprise LLM service, developers should focus on dynamic context management rather than static prompt optimization. Treating operational guidelines as external data via mock tool messages, rather than system instructions, provides a scalable way to reduce hallucinations and maintain high performance across hundreds of integrated services.
google Google Research in 2025 has shifted toward an accelerated "Magic Cycle" that rapidly translates foundational breakthroughs into real-world applications across science, society, and consumer products. By prioritizing model efficiency, factuality, and agentic capabilities, the organization is moving beyond static text generation toward interactive, multi-modal systems that solve complex global challenges. This evolution is underpinned by a commitment to responsible AI development, ensuring that new technologies like quantum computing and generative UI are both safe and culturally inclusive. ## Enhancing Model Efficiency and Factuality * Google introduced new efficiency-focused techniques like block verification (an evolution of speculative decoding) and the LAVA scheduling algorithm, which optimizes resource allocation in large cloud data centers. * The Gemini 3 model achieved state-of-the-art results on factuality benchmarks, including SimpleQA Verified and the newly released FACTS benchmark suite, by emphasizing grounded world knowledge. * Research into Retrieval Augmented Generation (RAG) led to the development of the LLM Re-Ranker in Vertex AI, which helps models determine if they possess sufficient context to provide accurate answers. * The Gemma open model expanded to support over 140 languages, supported by the TUNA taxonomy and the Amplify initiative to improve socio-cultural intelligence and data representation. ## Interactive Experiences through Generative UI * A novel implementation of generative UI allows Gemini 3 to dynamically create visual interfaces, web pages, and tools in response to user prompts rather than providing static text. * This technology is powered by specialized models like "Gemini 3-interactive," which are trained to output structured code and design elements. * These capabilities have been integrated into AI Mode within Google Search, allowing for more immersive and customizable user journeys. ## Advanced Architectures and Agentic AI * Google is exploring hybrid model architectures, such as Jamba-style models that combine State Space Models (SSMs) with traditional attention mechanisms to handle long contexts more efficiently. * The development of agentic AI focuses on models that can reason, plan, and use tools, exemplified by Project Astra, a prototype for a universal AI agent. * Specialized models like Gemini 3-code have been optimized to act as autonomous collaborators for software developers, assisting in complex coding tasks and system design. ## AI for Science and Planetary Health * In biology, research teams utilized AI to map human heart and brain structures and employed RoseTTAFold-Diffusion to design new proteins for therapeutic use. * The NeuralGCM model has revolutionized Earth sciences by combining traditional physics with machine learning for faster, more accurate weather and climate forecasting. * Environmental initiatives include the FireSat satellite constellation for global wildfire detection and the expansion of AI-driven flood forecasting and contrail mitigation. ## Quantum Computing and Responsible AI * Google achieved significant milestones in quantum error correction, developing low-overhead codes that bring the industry closer to a reliable, large-scale quantum computer. * Security and safety remain central, with the expansion of SynthID—a watermarking tool for AI-generated text, audio, and video—to help users identify synthetic content. * The team continues to refine the Secure AI Framework (SAIF) to defend against emerging threats while promoting the safe deployment of generative media models like Veo and Imagen. To maximize the impact of these advancements, organizations should focus on integrating agentic workflows and RAG-based architectures to ensure their AI implementations are both factual and capable of performing multi-step tasks. Developers can leverage the Gemma open models to build culturally aware applications that scale across diverse global markets.
google Google Research, in partnership with several pan-African machine learning communities, recently concluded the Africa-wide Data Science for Health Ideathon to address regional medical challenges. By providing access to specialized open-source health models and technical mentorship, the initiative empowered local researchers to develop tailored solutions for issues ranging from maternal health to oncology. The event demonstrated that localized innovation, supported by high-performance AI foundations, can effectively bridge healthcare gaps in resource-constrained environments. ## Collaborative Framework and Objectives * The Ideathon was launched at the 2025 Deep Learning Indaba in Kigali, Rwanda, in collaboration with SisonkeBiotik, Ro’ya, and DS-I Africa. * The primary goal was to foster capacity building within the African AI community, moving beyond theoretical research toward the execution of practical healthcare tools. * Participants received hands-on training on Google’s specialized health models and were supported with Google Cloud Vertex AI compute credits and mentorship from global experts. * Submissions were evaluated based on their innovation, technical feasibility, and contextual relevance to African health systems. ## Technical Foundations and Google Health Models * Developers focused on a suite of open health AI models, including MedGemma for clinical reasoning, TxGemma for therapeutics, and MedSigLIP for medical vision-language tasks. * The competition utilized a two-phase journey: an initial "Idea Development" stage where teams defined clinical problems and outlined AI approaches, followed by a "Prototype & Pitch" phase. * Technical implementations frequently involved advanced techniques such as Retrieval-Augmented Generation (RAG) to ensure alignment with local medical protocols and WHO guidelines. * Fine-tuning methods, specifically Low-Rank Adaptation (LoRA), were utilized by teams to specialize large-scale models like MedGemma-27B-IT for niche datasets. ## Innovative Solutions for Regional Health * **Dawa Health:** This first-place winner developed an AI-powered cervical cancer screening tool that uses MedSigLIP to identify abnormalities in colposcopy images uploaded via WhatsApp, combined with Gemini RAG for clinical guidance. * **Solver (CerviScreen AI):** This team built a web application for automated cervical-cytology screening by fine-tuning MedGemma-27B-IT on the CRIC dataset to assist cytopathologists with annotated images. * **Mkunga:** A maternal health call center that adapts MedGemma and Gemini to provide advice in Swahili using Speech-to-Text (STT) and Text-to-Speech (TTS) technologies. * **HexAI (DermaDetect):** Recognized for the best proof-of-concept, this offline-first mobile app allows community health workers to triage skin conditions using on-device versions of MedSigLIP, specifically designed for low-connectivity areas. The success of the Ideathon underscores the importance of "local solutions for local priorities." By making sophisticated models like MedGemma and MedSigLIP openly available, the technical barrier to entry is lowered, allowing African developers to build high-impact, culturally and linguistically relevant medical tools. For organizations looking to implement AI in global health, this model of providing foundational tools and cloud resources to local experts remains a highly effective strategy for sustainable innovation.
kakao Kakao has developed Kanana-v-embedding, a specialized multimodal embedding model designed to bridge the gap between Korean text and visual data within a unified semantic space. By leveraging a Vision-Language Model (VLM) framework, the model enables seamless search and recommendation across various combinations of text and images, offering a significant performance boost over existing English-centric models like CLIP. This development provides a robust technical foundation for enhancing Kakao’s services, including RAG-based systems and localized content discovery. ### Unified Multimodal Meaning Space * The model maps text and images into a single vector space where semantic similarity is measured via cosine similarity. * Unlike traditional CLIP models that use independent encoders, this architecture treats text and images as a single sequence, allowing for "text + image" combined queries. * It supports four primary interaction modes: Text-to-Text, Text-to-Image, Image-to-Image, and (Text+Image)-to-(Text+Image). ### VLM-Based Architecture and Instruction Tuning * The system utilizes a VLM consisting of an LLM and an image encoder, extracting embeddings from the final hidden state of the [EOS] token. * It employs instruction-based query embedding, where specific prompts (e.g., "Find an image matching this caption") guide the model to generate embeddings tailored to the specific task, such as retrieval or classification. * The model is optimized for the Korean language and cultural context, addressing the limitations of previous models that struggled with non-English data. ### Advanced Training for Scalability and Precision * **Gradient Caching:** To overcome GPU memory limitations, this technique allows the model to train with effectively large batch sizes, which is critical for the InfoNCE loss used in contrastive learning. * **Matryoshka Representation Learning (MRL):** The model supports flexible embedding sizes ranging from 64 to 2,048 dimensions. This allows services to choose between low-latency (smaller dimensions) or high-precision (larger dimensions) without retraining. * **Hard Negative Mining:** The training process incorporates "hard negatives"—items that are similar but incorrect—to sharpen the model’s ability to distinguish between subtle differences in data. ### Performance Benchmarks and Efficiency * Kanana-v-embedding significantly outperforms CLIP and VLM2Vec on the KoEmbed benchmark, particularly in Korean Text-to-Image and Image-to-Text retrieval tasks. * In the M-BEIR (Multimodal Benchmark for Retrieval), the model demonstrated superior performance in multimodal document retrieval and image-to-text tasks compared to established open-source models. * Evaluation of MRL showed that the model retains high accuracy even when dimensions are reduced to 256 or 512, providing a 4x to 8x improvement in storage and search efficiency with minimal loss in quality. For organizations looking to implement multimodal RAG or advanced recommendation systems in Korean-language environments, Kanana-v-embedding offers a highly adaptable solution. Its ability to balance computational cost and retrieval quality through Matryoshka learning makes it particularly suitable for large-scale production environments where latency is a primary concern.
aws Amazon S3 Vectors has reached general availability, establishing the first cloud object storage service with native support for storing and querying vector data. This serverless solution allows organizations to reduce total ownership costs by up to 90% compared to specialized vector database solutions while providing the performance required for production-grade AI applications. By integrating vector capabilities directly into S3, AWS enables a simplified architecture for retrieval-augmented generation (RAG), semantic search, and multi-agent workflows. ### Massive Scale and Index Consolidation The move to general availability introduces a significant increase in data capacity, allowing users to manage massive datasets without complex infrastructure workarounds. * **Increased Index Limits:** Each index can now store and search across up to 2 billion vectors, representing a 40x increase from the 50 million limit during the preview phase. * **Bucket Capacity:** A single vector bucket can now scale to house up to 20 trillion vectors. * **Simplified Architecture:** The increased scale per index removes the need for developers to shard data across multiple indexes or implement custom query federation logic. ### Performance and Latency Optimizations The service has been tuned to meet the low-latency requirements of interactive applications like conversational AI and real-time inference. * **Query Response Times:** Frequent queries now achieve latencies of approximately 100ms or less, while infrequent queries consistently return results in under one second. * **Enhanced Retrieval:** Users can now retrieve up to 100 search results per query (increased from 30), providing broader context for RAG applications. * **Write Throughput:** The system supports up to 1,000 PUT transactions per second for streaming single-vector updates, ensuring new data is immediately searchable. ### Serverless Efficiency and Ecosystem Integration S3 Vectors functions as a fully serverless offering, eliminating the need to provision or manage underlying instances while paying only for active storage and queries. * **Amazon Bedrock Integration:** It is now generally available as a vector storage engine for Bedrock Knowledge Bases, facilitating the building of RAG applications. * **OpenSearch Support:** Integration with Amazon OpenSearch allows users to utilize S3 Vectors for storage while leveraging OpenSearch for advanced analytics and search features. * **Expanded Footprint:** The service is now available in 14 AWS Regions, up from five during the preview period. With its massive scale and 90% cost reduction, S3 Vectors is a primary candidate for organizations looking to move AI prototypes into production. Developers should consider migrating high-volume vector workloads to S3 Vectors to benefit from the serverless operational model and the native integration with the broader AWS AI stack.
dropbox How Dash uses context engineering for smarter AI When we first built Dash, it looked like most enterprise search systems: a traditional RAG pipeline that combined semantic and keyword search across indexed documents. It worked well for retrieving information and generating conci…