Swindon Borough Council makes public information accessible with an Easy Read generative AI tool built on Amazon Bedrock
Swindon Borough Council · United Kingdom
Swindon Borough Council, a local authority in England, built an Easy Read solution using Amazon Bedrock to make council documents accessible to residents with learning disabilities, low literacy or cognitive impairment. The generative AI summarizes and simplifies complex text and generates matching images, presenting simplified text alongside images on the page. The council tested the tool on a complex tenancy agreement over 50 pages long and, working with a group of Experts by Experience of a Learning Disability, refined the format based on their feedback. Combined with the council's existing Translate solution, content can be produced in 75 languages. Manually adapting a five-page document into Easy Read format previously cost around £500 and took two weeks; the council can now create an accessible multi-page document for 7-10 pence per page. The council plans to make the tool open source for other councils to use.
Overview
Swindon Borough Council, a local authority in England, built an Easy Read solution using Amazon Bedrock to make council documents accessible to residents with learning disabilities, low literacy or cognitive impairment. The generative AI summarizes and simplifies complex text and generates matching images, presenting simplified text alongside images on the page. The council tested the tool on a complex tenancy agreement over 50 pages long and, working with a group of Experts by Experience of a Learning Disability, refined the format based on their feedback. Combined with the council's existing Translate solution, content can be produced in 75 languages. Manually adapting a five-page document into Easy Read format previously cost around £500 and took two weeks; the council can now create an accessible multi-page document for 7-10 pence per page. The council plans to make the tool open source for other councils to use.
This entry has 12 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Not all citizens have the same ability to identify and digest information that's important to them, so councils have to invest in alternative Easy Read versions of documents. It can typically cost £120 to adapt content manually for a single page with five lines and five images, and an average five-page document would take two weeks to adapt and cost £500 — unsustainable in terms of demand on council resources.
The solution
Swindon Borough Council built an Easy Read solution using Amazon Bedrock, a fully managed service that lets teams build and scale generative AI applications, to summarize and simplify complex text and generate matching images, presenting simplified text on the right side of a page and images on the left. The council tested the tool on a complex tenancy agreement more than 50 pages long, sending early samples to Adult Social Care before moving into a deeper engineering phase. Working with a group called Experts by Experience of a Learning Disability, the council refined the format based on their feedback — learning that images are important, text size needs to be bigger than usual, the space between text needs to be wider, and jargon and ambiguous terms must be avoided. The council combined the tool with its existing Translate solution to make content available in 75 languages.
Reported business value
It can typically cost £120 to adapt content manually for a single page with five lines and five images, and an average five-page document would take two weeks to adapt and cost £500 — unsustainable given council resource pressures. The council can now create an accessible multi-page document for 7-10 pence per page. The council plans to make the tool open source, along with its prompts and parameters, for other councils and public/third-sector organizations to use.
Sources
Open any source and check the claim yourself — that is the point of the register.
Other government & public sector entries in the register.
Estonia rolls out Bürokratt, an AI-guided virtual assistant network for public services
Bürokratt is a network of chatbots deployed on Estonian public sector institutions' websites, letting people obtain information from institutions and use public and information services via virtual assistants. It is a state-created, AI-based digital assistant that helps institutions deliver modern, efficient, around-the-clock customer service using large language models.
Austrian Academy of Sciences unlocks Ancient Greek with Mistral
The Austrian Academy of Sciences (OeAW), together with its Austrian Archaeological Institute, partnered with Mistral and services partner Reply to build Apollo, described as the first advanced large language model for Ancient Greek. Apollo is trained on a specialized corpus of 600 million words of historical Greek text plus tens of thousands of published inscriptions and papyri, helping researchers reconstruct damaged texts and identify thematic connections across collections. The OeAW reports Apollo turns work that once took years into hours, addressing over one million unread Greek papyri worldwide, with future phases planned for semantic search and handwritten inscription decipherment.
MITRE's Federal AI Sandbox accelerates government AI research with NVIDIA DGX SuperPOD
Nonprofit MITRE built the Federal AI Sandbox, powered by NVIDIA DGX SuperPOD, to give federal sponsors an affordable, centralized space to test and deploy AI and machine learning across domains such as weather forecasting, cybersecurity, and public benefits administration. The DGX SuperPOD delivers a 300-fold performance increase over MITRE's previous AI computing capabilities and supports thousands of researchers; MITRE is using it with NVIDIA Omniverse and NVIDIA Earth-2 to develop 1-kilometer precision weather forecasts with NOAA and the National Weather Service, plus a foundational model for cybersecurity threat analysis across 190 nations.
Israel's Meteorological Service Predicts the Weather Using NVIDIA Earth-2
The Israel Meteorological Service integrated an AI weather model called F3, powered by NVIDIA Earth-2 and NVIDIA PhysicsNeMo (including the CorrDiff neural network), into its forecasting system to achieve hyperlocal 2.5-kilometer resolution precipitation forecasts. F3 achieved 90 percent lower computational costs compared to running a classic non-AI numerical weather prediction model on a CPU cluster, delivering forecasts in minutes rather than hours, and saved 20-30 percent of the Tel Aviv-Yafo Municipality's preparedness budget for things like urban flood safety. CorrDiff was trained to emulate IMS's regional high-resolution ICON model using low-resolution ECMWF IFS input, enabling four high-resolution forecasts per day. Partners including the Israeli Police, the National Fire and Rescue Authority, the Ministry of Transportation and the National Road Company have adopted the forecasts, and IMS used F3 to issue a high-resolution flood map during a January storm that dropped 150 millimeters of rain in six hours.
Was this helpful?
Your feedback helps us improve our use case database