Enterprise teams default to fine-tuning by accident, not conscious architectural choice
“most corporate teams make this decision by accident”
rag
29 tracked signals on rag.
Azure Content Understanding adds GPT-5 series support and agentic document reasoning in dual API release
“In internal evaluations, this reduced average inference token usage by up to 28 percent for GPT-4.1 and GPT-5.2, while also improving average accuracy by up to 3 percent.”
Bridgewater's AI analyst PAT compresses expert research hours into minutes, live across hundreds of investors.
“PAT is not a prototype today. It was actually deployed internally several months ago. And we now have hundreds of investors using it every single day, which is leading to a pretty incredible flywheel of improvement.”
A local code-indexing search layer cut AI coding input tokens by 94%, saving ~61% of total cost.
“It's like ordering a pizza and paying for extra nine pizzas you don't eat every time.”
AWS adds knowledge access, observability, and governance capabilities to Amazon Bedrock AgentCore for production agents.
“A capable model is only the starting point. What makes an agent perform in production is access to everything it needs to do the full job: the right knowledge, the resources to act, and the feedback loops to keep improving.”
Microsoft's Foundry IQ connects AI agents to enterprise knowledge via agentic retrieval.
“Foundry IQ is the thing you use to connect agents to knowledge.”
LLM coding agents are ~6 months out of date due to training cutoff lag
Amazon Bedrock Managed Knowledge Base now supports multi-tenant agentic retrieval with per-user data isolation.
Agent failures stem from static retrieval that never learns from eval and observability signals.
“We made wrong answers appear faster and cheaper, but we forgot to make retrieval learn.”
Open-source tool Docling extracts structure from unstructured enterprise documents to power RAG and agent systems.
“unstructured data is becoming this new context layer for AI”
SQL Server 2025 adds native vector search enabling semantic, meaning-based queries beyond keyword matching.
“But vector search is completely different uh in the sense uh that it really is a search for meaning.”
AI agents move data retrieval from single-turn RAG to multi-step tool use, but agent-generated SQL often fails retrieval.
“why 90% accuracy in text to SQL is 100% useless”
RAG isn't dead; hybrid tool-rich retrieval is becoming the default for serious agentic search.
“rag is dead, how hybrid tool tool rich retrieval is becoming a default for serious agentic search.”
Apple introduces SpotlightSearchTool, letting on-device LLMs search app content via Core Spotlight for grounded responses.
“today, we're introducing SpotlightSearchTool. It's a tool that adopts the tool protocol, to let a language model directly search your app's content in Core Spotlight for contextual response generation.”
Databricks updated Agent Bricks Knowledge Assistant for 3x faster, higher-quality search via parallel test-time scaling.
“Today we're announcing a major update that makes Agent Bricks Knowledge Assistant both faster and higher quality.”
Azure SQL Hyperscale adds native vector search and agentic RAG patterns in T-SQL
“Hyperscale provides all the AI capabilities for today's developer, including things like vector searching or REST APIs built into the SQL Server engine.”
Databricks Genie Agents can now ground on both structured data and documents with governance intact.
Guardoc Health achieves 46% fewer documentation errors using Amazon Nova models on Bedrock.
Two AI educators built an 'AI research OS' to turn 10,000+ scattered notes into a queryable personal research memory.
“I spent 18 months turning my second brain into my living research memory.”
Azure SQL Database lets developers build vectors on operational data and ground LLMs like OpenAI and Anthropic via Microsoft Foundry.
“You can you can essentially talk to LLMs with the with the truth that you have in your operational data.”
Azure SQL Database lets developers build vector search on operational data and ground LLMs like OpenAI and Anthropic via Microsoft Foundry.
“you can essentially talk to LLMs with the truth that you have in your operational data”
Azure Managed Redis offers semantic caching and vector storage to power faster AI and RAG apps at internet scale.
“Azure managed Reddus is also able to power your rag scenarios and you can also use it as a light lightweight vector data store as well.”
Azure SQL Database Hyperscale adds RAG, vector indexing, and semantic search without requiring new SQL skills.
“Microsoft SQL has really been innovating over the past couple years, including modern capabilities that help you build applications, integrate with analytics and AI, take advantage of rag, vector indexing, advantage of rag, vector indexing, semantic search, all of this while continuing to work with the same SQL foundation that you already know.”
AWS Bedrock Data Automation enables context-aware intelligent document processing beyond traditional OCR.
AWS demonstrates building an equipment repair assistant using Bedrock AgentCore, Nova 2 Lite, and Strands Agents SDK.
Elastic's agent builder can turn a traditional e-commerce search into a conversational AI agent on Azure without rebuilding the app.
“a model without the right context, without the right data is just a very expensive autocomplete”
Amazon Quick Research is an agentic LLM workflow that integrates biomedical databases into cited, versioned research reports.
Azure free tiers and serverless offerings enable viable apps under $25/month
“you're not just optimizing your architecture, but you're really building an economical, sustainable and scalable solution”
Azure free tiers and serverless offerings enable viable AI apps under $25/month
“You really don't want to sort of trouble your model with all kinds of questions and expensive queries.”