Search “RAG”

Xreal Aura has officially launched in four countries, starting at $1,099

On October 28, 2026, Google and XREAL released the XREAL AURA, the first wired XR glasses powered by Android XR, starting at $1,099. According to the Google Blog, the product is available for order starting today in the United States, Canada, and South Korea, and goes on sale in Japan on November 2. The glasses weigh less than 95 grams, use transparent lenses and a 70-degree field of view to project apps into the user's field of vision; heavy computing is handled by a portable computing puck connected via cable, which features the debut of the Qualcomm Snapdragon Reality Elite platform. Users can open multiple apps at once and pair them with a Bluetooth keyboard and mouse, or connect a laptop screen as a window via USB-C wired mirroring, and Gemini can provide assistance with content in the field of view and on the screen. Testing Catalog reported the same day that the product is aimed at users aged 18 and over, with a launch price starting at $1,099 within the year.

heise online launches a hands-on workshop on AI coding assistants

heise online launches the iX workshop "Programming More Efficiently with AI Assistants," using GitHub Copilot as an example to guide developers through prompt techniques, Spec-Driven Development and Agentic Coding, and to distinguish these from Vibe Coding. The course also covers the architecture, features and pricing of Cursor, Claude Code, OpenAI Codex and Kilocode, and explains how MCP and RAG connect to external tools and your own data. The workshop takes place online on December 15–16, 2026, and is led by Rainer Stropek.

Kakao Open-Sources Two Korean-Optimized Embedding Models

On October 29, Kakao open-sourced two Korean-optimized embedding models on Hugging Face: Kanana-2-3b-embedding (3 billion parameters) and Kanana-2-1.3b-embedding (1.3 billion parameters), targeting personalized AI agents and RAG scenarios. Kakao said that in internal evaluations, the two models outperformed llama-nemotron-embed-1b-v2 and Qwen3-Embedding-4B of comparable scale in Korean retrieval performance, with comparable English performance and higher inference efficiency, while memory usage and inference speed improved by more than tenfold compared with the previous-generation Kanana embedding models. The models adopt MRL, allowing developers to adjust the embedding vector size, and are released under the Kanana Open License for commercial use. There are currently no further developments.

Mastra launches Span Queries

On October 28, 2026, Mastra launched Span Queries, which can filter and group individual spans across all traces by conditions such as time range, type, name, status, error, and duration, to help locate common failures in coding agents. This feature is available in Mastra platform, Studio, CLI, Client SDK, and observability endpoints. Each query can combine up to 100 conditions, return up to 1,000 spans per page, group by up to 2 dimensions, and cover a time range of up to 365 days; the CLI requires mastra@1.36.0 or later, and the SDK requires @mastra/client-js@1.57.0 or later. Self-hosted projects can also use it when storage.observability uses DuckDB, PostgreSQL, or ClickHouse. There are currently no further developments.

Chai Point says auditing with Claude Code cut its monthly AWS bill by 58.2%

Dharmendra Raghuvanshi of Chai Point said the company's monthly AWS bill dropped from $10,877 to $4,550, a 58.2% reduction. According to Analytics India Magazine, about 80% of the savings came from an Agentic Cost Audit performed by a senior engineer using Claude Code: the audit examined production and QA cloud accounts in read-only mode, identifying idle and orphaned resources, over-provisioning and misconfigurations, and ranked them by savings amount, implementation cost and risk. The remaining roughly 19% came from switching AWS reseller to Isaga for a 5% discount, and from Savings Plans reducing committed spending by about 15%. The report said the platform still supports more than 8,000 connected brewing devices across over 170 stores.

View story:Dharmendra Raghuvanshi said Chai Point's monthly AWS bill fell 58.2%

Anthropic donates Agent Skills to the Agentic AI Foundation

Anthropic announced that it will donate Agent Skills to the Agentic AI Foundation (AAIF). According to its first-party information, MCP had previously also been donated to the same foundation; since December 2025, more than 70 agent platforms have adopted the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code. Subsequent reports stated that AAIF, under the Linux Foundation, announced on October 22, 2026 that it had accepted four projects: in addition to Anthropic's Agent Skills, these include OpenAI's Open Responses, Hugging Face's OpenEnv, and Alibaba's OpenSandbox; Agent Skills is a universal format that allows different agents to reuse business knowledge and workflows, and Anthropic made it public as an open standard in December 2025. Reports also stated that the donation includes the name, logo, the GitHub organization account agentskills, and the agentskills.io domain; going forward, a technical operations committee composed of core maintainers from multiple organizations will decide the development direction, with Anthropic's David Soria Parra and Mahesh Murag serving as lead maintainers; the number of projects under AAIF has grown from three at its founding to ten.

IskayPet builds enterprise knowledge assistant based on Amazon Bedrock

IskayPet has built an enterprise knowledge assistant based on Amazon Bedrock Managed Knowledge Bases, covering retail operations, veterinary care, HR onboarding, and procurement scenarios, supporting four languages and three countries, with no need to self-manage RAG infrastructure. The assistant directly ingests existing documents through the native SharePoint connector, combining hybrid search of semantic and BM25 keyword search, managed reranking, and document-level permission control, and returns answers with source citations. The entire solution, from store front end to AWS architecture deployment, was completed by Kiro with Claude Haiku 4.5. There are currently no subsequent development facts.

Sarvam AI introduces a knowledge fabric architecture for enterprise agents

On October 21, 2026, Sarvam AI introduced a knowledge fabric architecture built for enterprise agents. The architecture consists of two layers, a knowledge tree and a domain ontology, compiling documents once into a structured layer that agents can navigate, query, and cite. According to its published results, on the Harvey LAB benchmark, answers using GLM 5.3 met 84.2% of expert grading criteria, higher than agentic RAG's 55.1%, with average task cost dropping from $0.64 to $0.28; on Sierra's tau-knowledge banking benchmark, it achieved accuracy comparable to the baseline using 64% fewer tokens. The knowledge tree is already used in the Sarvam cowork product, while the ontology is built domain by domain and enterprise client by enterprise client.

MemTensor Open-Sources Native Memory Architecture Model MemT-1.0

On October 22, 2026, MemTensor open-sourced its native memory architecture model MemT-1.0, offering two size tiers, 36B Nano and 288B Flash, and released a 66-page technical report. According to representative reports, the model places a Native Memory Block in parallel alongside the standard Transformer Block, enabling token-level dynamic state updates through erase, write, and forget gates, and expands memory capacity via a Mixture-of-Storage mechanism. Data cited in the reports states that with 256K of history, VRAM drops from 5.06 GiB to 40 MiB, and first-token latency remains at 104–112 ms between 512 and 256K. There are currently no subsequent developments.

Microsoft releases multiple new cloud sovereignty tools

On October 21, 2026, Microsoft announced multiple new digital sovereignty features for its cloud services at the Frontier Tour in Paris. Microsoft CEO Satya Nadella and cloud business head Douglas Phillips jointly unveiled a modular cloud sovereignty solution that lets enterprises decide for each computing task the degree of control, transparency, and local execution. A new Sovereign Control Panel aggregates Azure sovereignty signals and will gradually roll out Data Guardian and the Production Touch Ledger, which records remote operations by Microsoft engineers. Azure Managed HSM external key management is now generally available, and on the Azure Local side, DocumentDB, Blob Storage, GitHub Enterprise Local, and Foundry Local have been added. The German Informatics Society (GI) and others criticized such solutions as merely surface-level add-on controls, with the underlying software stack still controlled by U.S. vendors. There have been no further developments so far.

Gergely Orosz argues that continuously learning new tools is part of professional competence

On October 19, 2026, The Pragmatic Engineer author Gergely Orosz put forward the view that continuously learning new tools is itself part of professional competence. This statement came in response to a plea for help from a South Korean middleware engineer—the engineer's manager, influenced by the GenAI boom, had set "AI token usage" as a KPI and repeatedly pressured him for making little use of AI. Orosz believes the manager is using a clumsy approach to push him to adapt to change, and says that being "excellent" and "refusing to learn new things" are not mutually exclusive, and that refusing to adapt is still unprofessional. He offers two paths: accept that AI changes the way work is done, or honestly bear the cost of refusal, namely that the companies willing to hire you will keep shrinking. Currently this view is reported by a single source, with no subsequent developments yet.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.