×
AI Streamlines Child Support Case Management in Texas
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

AI-powered search revolutionizes child support case management in Texas: The Texas Office of the Attorney General (OAG) has developed an innovative AI-driven search tool to streamline research processes for child support field case workers, significantly reducing time spent on policy and legal research.

The challenge and solution: Child support field case workers faced a major pain point in time-consuming research, prompting the OAG to develop a single knowledge base and robust AI search tool for the Child Support Division.

  • The project aimed to create a search engine that would return accurate answers or a clear “no answer” response.
  • Built on the Microsoft Azure Cosmos DB platform, the system incorporates nonconfidential documents and data within a secure “ring fence solution.”
  • The process included creating a comprehensive glossary of acronyms, enabling saved searches and citations, and ensuring mobile-friendly access.

Key features and safeguards: The AI-powered search tool prioritizes data security and accuracy while leveraging advanced technologies to enhance efficiency.

  • The OAG maintains full ownership and control of all data, preventing unauthorized access or manipulation.
  • The system uses retrieval augmented generation (RAG) for ease of implementation, with source data remaining securely within OAG systems.
  • Azure logging services are employed for system monitoring and management.
  • The tool is designed to prevent “hallucination” or incorrect responses, even when faced with repetitive or nonsensical queries.

Initial results and potential impact: Early adoption of the search tool has demonstrated significant time savings and productivity improvements for child support case workers.

  • Approximately 40 employees have reported saving about one hour per week using the new search tool.
  • With over 2,200 employees in the Child Support Division, the potential time savings could translate to thousands of hours annually.
  • The tool allows case workers to dedicate more time to direct casework and serving Texas constituents.

Scale and complexity of child support operations: The AI-powered search tool addresses the challenges posed by the vast scope of child support cases in Texas.

  • The child support system manages nearly 15 million members and 1.5 million active cases at any given time.
  • Annual payment distributions exceed $4.5 billion.
  • Cases can span from birth to 18 years and beyond, with some lasting over 40 years due to ongoing obligations.

Considerations for implementing augmented search: The OAG team shared key factors to consider when developing similar AI-powered search solutions.

  • Identify necessary documentation and ensure quality control.
  • Define and model data appropriately.
  • Establish clear data policies.
  • Utilize analytics to understand system usage.
  • Determine the frequency of documentation updates.

Broader implications and future potential: The success of this AI-powered search tool opens up new possibilities for innovation and efficiency in government operations.

  • The project serves as a catalyst for imagining further applications of AI and data-driven solutions.
  • It highlights the critical importance of data quality, including tagging, classification, cleansing, and accuracy in modernization efforts.
  • The tool’s success demonstrates the potential for replication in other agencies, showcasing the “art of the possible” in government technology innovation.
AI-Powered Search Drives Intelligent Texas Child Support Tool

Recent News

7 ways to optimize your business for ChatGPT recommendations

Companies must adapt their digital strategy with specific expertise, consistent information across platforms, and authoritative content to appear in AI-powered recommendation results.

Robin Williams’ daughter Zelda slams OpenAI’s Ghibli-style images amid artistic and ethical concerns

Robin Williams' daughter condemns OpenAI's AI-generated Ghibli-style images, highlighting both environmental costs and the contradiction with Miyazaki's well-documented opposition to artificial intelligence in creative work.

AI search tools provide wrong answers up to 60% of the time despite growing adoption

Independent testing reveals AI search tools frequently provide incorrect information, with error rates ranging from 37% to 94% across major platforms despite their growing popularity as Google alternatives.