AWS AI In Practice #2

We are delighted to welcome Phil Basford, Senior Director at Cognizant UK&I Consulting and Ashraful Alam, AWS Cloud Technical Lead at Legal and General.

Insurers deal with billions of messy, multi-format documents that used to take hours or days to process. Phil's talk shows how Intelligent Document Processing (IDP) on AWS - using Bedrock, Textract, Comprehend, and custom SageMaker models - automates extraction, classification, and validation end-to-end. Expect real-world architecture, pre-processing/post-processing patterns, and outcomes: 90%+ accuracy and >500x faster turnaround across £500M+ of business.

Ashraful will show you how to supercharge Amazon Q in the terminal with MCPs - 49 servers, live AWS checks, and Playwright for browser automations, custom rules for killing hallucinations. FSI-grade guardrails (prod protection, cost, audits) at £0 extra - a verification-first, agentic platform you own.

Programme
18:00: Arrival, registration
18:15: TALKS START
20:00: Networking with food and a drink provided by the generosity of our sponsors.

Talk 1
Using AI to help process documents in Insurance with Phil Basford

The insurance industry has billions of historical documents; with hundreds of thousands more being generated every day. The documents, in varying formats are used both internally and with other insurers to agree terms, assess risk and create accurate quotes. Historically each document can take a few hours or even days to manually process and needs to be loaded into each company’s systems. AI is helping several companies to reduce this processing time to minutes by automating the process using Intelligent Document Processing (IDP), saving time, increasing the accuracy, and readying the data for further analysis - giving valuable insights back to the business. IDP uses the latest AI services; Amazon’s Bedrock, Textract to extract text, Amazon Comprehend to classify and detect entries in the documents and custom models with labelled grown truth in SageMaker. This architecture will look at these services alongside the pre-processing, processing, and post processing challenges and showcase how to jointly leverage these services for the best success.

Using IDP, one customer achieved an accuracy of 90%+ and a more than 500x reduction in processing time across over £500 million worth of business

Talk 2:
How to Put Amazon Q or Any Agentic Coding on Steroids with MCPs with Ashraful Alam

Amazon Q is powerful out of the box, but in the terminal it becomes a superpower. In this talk, I share how I turned Amazon Q CLI into a fully-fledged, verification‑first AI platform using the Model Context Protocol (MCP) all without adding $0 extra cost. I’ll walk through how I built 49 MCP servers to remove hallucinations, browser automation with Playwright, and live AWS verification that eliminates hallucinations in practice. You’ll see Financial Services Institution grade guardrails (production protection, cost controls, and full audit trails) that makes Q feel native to a builder’s workflow, secure and reliable. You’ll leave with a blueprint to extend Amazon Q/ any agentic coding beyond chat into a trusted, terminal‑first, agentic platform you own and can evolve infinitely.

Remember to follow us @AWSUserGroupUK and on LinkedIn for the latest updates and you can find videos of our past meetups on YouTube.