This AWS tutorial shows how to build an AI agent system with Amazon Bedrock AgentCore that automatically turns quarterly reports, compliance documents and market analyses into client PowerPoint presentations; in internal testing the whole process took under 90 seconds.
ShipStation Global's engineering team built Deckhand, an AI IT help desk agent running on Slack atop Amazon Bedrock AgentCore. In its first three months it answered 97.5% of channel messages, with its positive feedback rate rising from 82% in April to 96% in June.
Orca Security partnered with AWS to build Discovery AI on Amazon Bedrock, converting natural language questions into Sonar queries covering 900+ cloud models and 18 operators tracked by Sonar.
Postman and AWS detail the production architecture of its Agent Mode, an AI-native capability covering API testing, documentation, discovery, and implementation, serving 40 million developers.
Why it matters: The piece explains Postman's concrete practices in production—controlling tool scale, using schema reads instead of piling up tools, and treating context as the bottleneck—all transferable to other agent engineering.
Amazon Bedrock launched a public beta of OpenAI-powered Managed Agents and added new models including GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Luna, Claude Opus 5.5 and Kimi K3.
AWS has introduced real-time ACL enforcement for Amazon Quick and Amazon Bedrock Knowledge Bases, verifying permissions directly against authoritative data sources such as Google Drive and SharePoint at query time.
Cornerstone OnDemand built the multi-agent system Orion AI on Amazon Bedrock and Strands Agents, cutting database incident diagnosis time from 45 minutes to 10 minutes, a 78% reduction, reducing manual database lifecycle steps from more than 10 to a single interaction, and cutting median redundant alerts by 65%.
Qlik Answers, built on Amazon Bedrock, has been generally available since February 2026 and provides sourced, verifiable natural-language question answering to more than 40,000 customers worldwide, while its Discovery Agent has surfaced over 100,000 anomalous results.
AWS demonstrated on Amazon Bedrock Managed Knowledge Bases with LangChain a comparison of standard versus agentic retrieval: for a multi-part question containing six intents, single vector retrieval at 5 results covered only 4 sub-intents, while agentic retrieval used a planning loop to break the query into sub-queries, evaluate evidence and iterate.
This AWS tutorial shows how to build a voice travel concierge for an airline app using Amazon Bedrock AgentCore, Amazon Nova 2.5 Sonic, and Amazon Bedrock Knowledge Bases, supporting seat changes, meal preference updates, policy questions, and handoffs to human agents.
Amazon SageMaker AI introduced multi-turn reinforcement learning (MTRL) fine-tuning, enabling Qwen3.6-27B to be trained into a search agent that autonomously calls BM25 lexical retrieval and vector search tools.
Ai2 open-sourced AstaBrief 8B, a Qwen3-8B-based model, along with its training data. It generates cited reports in one pass from a research question and retrieved literature snippets, and is already live in Asta's Generate a report feature as the Fast mode alongside the Claude-powered Thinking mode.
AWS published a tutorial on its Machine Learning Blog demonstrating how to use Amazon Bedrock Knowledge Bases to index insurance claims documents in Amazon S3, using the AgenticRetrieveStream API to enable natural language questions, multi-turn conversations, metadata filtering, and cited answers.
The AWS Machine Learning Blog published a tutorial on a platform architecture that converts contract PDFs into structured data, using Claude Sonnet 4.6 on Amazon Bedrock AgentCore for extraction and Claude Haiku 4.5 for independent verification, with Amazon Textract arbitrating signature disagreements.
A Hugging Face team has proposed ProvenanceGuard, a source-aware factuality verification layer for MCP agents, which checks after generation whether the sources supporting each claim match the sources the answer states or implies, identifying cross-source confusion.
The GitHub Podcast breaks down five common AI hot takes one by one. Key conclusions: AI-generated code still needs review scaled to risk; Skills and MCP solve different problems, with MCP providing a standard for tool and data access while Skills package team workflows and best practices in Markdown, making them complementary; RAG is not dead—retrieval brings models closer to answers and can coexist with agents, MCP, and Skills in the same workflow.
Google Research's Retrieve-for-Train framework uses offline RL to discover reward-aligned query fan-out and distills it into supervision signals, bypassing LLM token-by-token chain-of-thought inference latency.
H Company released NeoMME, a multilingual multimodal encoder in 260M and 800M sizes. A single bidirectional Transformer processes both text tokens and 32×32 image patches, trained from scratch with a masked discrete diffusion objective, with no reliance on a pretrained vision tower or a causal language model. Both versions are open-sourced under Apache 2.0.
Sentence Transformers v6.0 adds the MultiVectorEncoder model type, and this tutorial demonstrates how to train and finetune ColBERT-style multi-vector retrieval models.
Why it matters: The author backs every training choice with measured data, teaching a multi-vector model domain finetuning method reproducible on a single GPU.
Hugging Face explains how it built a hybrid search engine for Papers with Code using Inference Endpoints, Jobs, and Storage Buckets.
Mistral released Agentic Search, a multi-step retrieval layer that lets models search, navigate, read, and verify information in complex documents, available through the Mistral Search Toolkit and via Libraries in Studio and Vibe, lifting FinanceBench accuracy from 26.7% to 86%.
Why it matters: Official benchmarks give concrete gains on FinanceBench and OfficeQA Pro plus tool design details, so readers can assess its fit for enterprise document retrieval workflows.
Hugging Face announced on its official blog that Sentence Transformers v6.0 adds a fourth model type, MultiVectorEncoder, supporting ColBERT-style late interaction retrieval; any PyLate and Stanford-NLP ColBERT checkpoint can be loaded directly, and colpali-engine models can also be used for visual document retrieval.
Why it matters: Official tutorials cover the full pipeline of loading, scoring, indexing, and compression, so readers can use them to decide whether multi-vector retrieval is worth adopting in their own search stack.
Mistral released the OCR 4 document parsing model, which beyond text extraction returns bounding boxes, typed block classification and per-word confidence scores, supports 170 languages across 10 language groups, and can be fully self-hosted via a single container.
Why it matters: Sourced from Mistral officially, it covers OCR 4's structured output, multilingual support and self-hosting options, and also discloses benchmark scoring limitations, serving as a selection reference.
Google has launched Cross-Corpus Retrieval, powered by Agentic RAG, on the Gemini Enterprise Agent Platform, now available in public preview.
Mistral AI released the public preview of Search Toolkit, an open-source framework for building production-grade search pipelines for AI applications, unifying ingestion, retrieval and evaluation in a single shared-interface framework.
Why it matters: The original details modules, evaluation metrics and enterprise case studies, helping readers judge whether it can replace their existing retrieval infrastructure.
Mistral AI has released Codestral Embed, its first code-specific embedding model, claiming it outperforms Voyage Code 3, Cohere Embed v4.0, and OpenAI's large embedding model on real-world code retrieval.
Mistral AI has launched Le Chat Enterprise, an enterprise-grade AI assistant powered by its new Mistral Medium 3 model, with features rolling out over the next two weeks.
Mistral explains how to evaluate RAG systems using “LLM As A Judge”: a judge LLM scores the answers of a generator LLM on numeric, binary, or qualitative scales.
Mistral released its optical character recognition API, Mistral OCR, which accepts image and PDF inputs and extracts text and images in order, and can work with RAG systems to process slides, complex PDFs, and other multimodal documents.
Why it matters: The official release includes internal benchmark comparisons, pricing, and self-deployment options, letting readers evaluate its usefulness for multimodal document understanding and RAG pipelines.