North Yorkshire reports faster social-care data retrieval

AI system

System: Microsoft Azure AI proof of concept for semantic search and automatically generated eco-maps in Liquidlogic LCS records
Model: Not assessed
Release: Not assessed
Application developer: North Yorkshire Council using Microsoft Azure AI
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: The project uses existing Liquidlogic case-management material, including notes, forms, and images. It was supported by the Department for Education’s Data and Digital Solutions Fund and evaluated as a proof of concept.
Human oversight: Not assessed
Relation to AI: The proof of concept uses AI to search structured and unstructured case information and generate relationship maps. The reported 90% reduction concerns selected test tasks, not established production-wide savings or improved safeguarding outcomes.
AI contribution: The proof of concept uses AI to search structured and unstructured case information and generate relationship maps. The reported 90% reduction concerns selected test tasks, not established production-wide savings or improved safeguarding outcomes.

Outcome identifiers: Not assessed
Benefit: North Yorkshire reports 90% less time and cost for some data-retrieval tasks in its Azure AI proof of concept, plus relationship-mapping tools.
Category: Improved Knowledge Discovery
Status: Reported and intended benefits
Beneficiary groups: Organizations. People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Participants: Developer: North Yorkshire Council using Microsoft Azure AI. Operator: North Yorkshire Council.
Jurisdictions: Benefit: United Kingdom.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: The conditions needed to reproduce the benefit are unspecified.
Replication attempts: Not assessed
Later findings: Not assessed
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: Organizations. People.
Depth: Organizations: 1. People: 1.
Reasons: Organizations: Selected retrieval tasks reportedly cost less and take less time in testing. Savings across deployed services are unmeasured. People: Faster retrieval and automatic relationship maps reduce effort on the tested tasks. Improved child safety is not established.
Observed or intended: Reported and intended benefits
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Kind: Not assessed
Related entries: Not assessed
Field: Children’s social-care information management.
Purpose: Improve retrieval and interpretation of children’s social-care records, including relationships among people and cases.
Dates: Source published: 3 February 2025. Updated: 22 October 2026.
Stage: Not assessed
Version: SHA-256: 47b679204a3b…