Code for America and Anthropic Develop AI Tools for Public Benefits Caseworkers

May 8, 2026
Code for America has partnered with Anthropic to design and deploy Claude-based tools that assist government caseworkers in administering public benefits programs, starting with the Supplemental Nutrition Assistance Program (SNAP).
Code for America and Anthropic Develop AI Tools for Public Benefits Caseworkers

Code for America has partnered with Anthropic to create AI tools that help government caseworkers manage public benefits more efficiently, announced in a press release. The collaboration focuses on building and testing applications powered by Anthropic's Claude models to assist with the administration of programs such as the Supplemental Nutrition Assistance Program (SNAP).

The first project under this partnership is the SNAP Policy Navigator, a Claude integration that provides caseworkers with accurate and current information across federal, state, and county policies. The tool uses the Model Context Protocol (MCP), an open standard developed by Anthropic, to securely connect AI systems with verified data sources.

Through the SNAP Policy Navigator, caseworkers can quickly access policy guidance and case-specific answers, improving the accuracy and speed of benefit delivery. The system is designed to handle complex policy scenarios while maintaining compliance with official regulations.

Following the initial pilot, both organizations plan to expand these tools for wider use across states and counties. The goal is to develop a reusable suite of Claude integrations to support tasks such as eligibility review, document analysis, and communication drafting for public benefits administration.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Enterprise AI Brief, AI Policy Brief or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

AI Policy Brief

Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.