Urgent.News

What's breaking now, across thousands of outlets.

AI

Sweep thousands of leases for compliance using Amazon Quick and the Adjudicated Query pattern

The Adjudicated Query pattern pairs the Amazon Quick chat agent with a bounded MCP server over a deterministic rules engine to deliver provably complete, defensible compliance answers. This post walks through the reference architecture and a deployable AWS CDK sample, using lease compliance as the running example.

Lease compliance for a 50,000-lease portfolio becomes impractical when state laws change frequently. Traditional software approaches produce unverifiable numbers and lack defensibility in case of audits. The Adjudicated Query pattern leverages generative AI in Amazon Quick and a deterministic rules engine to give business users conversational access while ensuring complete and defensible compliance sweeps.

The pattern separates the conversational surface from the rules engine, providing proven completeness receipts and drillable full result sets for accountability.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at aws.amazon.com →

More in AI

Dots get up in Muse’s business

OpenAI's answer to Muse arrived this week, and it looks a whole lot like Muse dressed up in a suit and tie. Dots is a business-first product - for now, at least - costing a minimum of $100 per month.

Add secure Web Search to Claude Desktop with Amazon Bedrock AgentCore

Claude Desktop on Amazon Bedrock is limited to the model's knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore…

  • Claude Desktop gains secure web search via Amazon Bedrock AgentCore.
  • Amazon Bedrock AgentCore's Gateway connects Claude Desktop to MCP-compatible web search.
  • Authentication secured with JWT and managed through AWS IAM Identity Center.

Fine-tune a search agent with multi-turn RL on Amazon SageMaker AI

Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost.

  • Amazon SageMaker AI enables fine-tuning LLMs for multi-turn search agents.
  • Multi-turn reinforcement learning (MTRL) optimizes agent performance across full trajectories.
  • Qwen3.6-27B model trained on FRAMES and BRIGHT datasets for enterprise search.

More from Friday 2 October →