Tell Indian citizens which government schemes they're owed
Entitled — (adj.) having a legal right to something India's welfare schemes are not charity. Task: Entitled — (adj.) having a legal right to something India's welfare schemes are not charity. You are entitled to them This agent tells you exactly to what. An AI agent that tells Indian citizens which government welfare schemes they qualify for — in plain language, with citations — built on Sanity structured content for the DEV Sanity Challenge (Path One). India runs 4,700+ welfare schemes worth ₹1.5 lakh crore a year. Much of it goes unclaimed because eligibility rules are scattered, written in legalese, and contradict each other across central and state sources. Entitled models those rules as structured content so an agent can reason over them instead of keyword-searching PDFs. Repo layout; tools: custom-built or unnamed agent. Human role: The original post does not say how a person stayed involved.; limitations: The dataset is limited to 125 schemes (118 Central, 7 State), with only 10 having detailed structured rules; the rest rely on summary data. The agent uses a session token that expires, requiring manual rotation. Benefit calculations mix cash, insurance, and one-time subsidies, potentially overstating annual totals. The system is read-only for the agent, requiring human curation in Sanity Studio for updates..
Tools
custom-built or unnamed agent
Published on Agent Work Atlas:
Overview
Entitled — (adj.) having a legal right to something India's welfare schemes are not charity.
Workflow
Entitled — (adj.) having a legal right to something India's welfare schemes are not charity. You are entitled to them This agent tells you exactly to what. An AI agent that tells Indian citizens which government welfare schemes they qualify for — in plain language, with citations — built on Sanity structured content for the DEV Sanity Challenge (Path One). India runs 4,700+ welfare schemes worth ₹1.5 lakh crore a year. Much of it goes unclaimed because eligibility rules are scattered, written in legalese, and contradict each other across central and state sources. Entitled models those rules as structured content so an agent can reason over them instead of keyword-searching PDFs. Repo layout
Reported result
The source describes a functional prototype built for the DEV Sanity Challenge. It successfully handles complex eligibility logic, such as disqualifying government employees from farmer schemes via structured exclusion rules. However, no measured business outcomes, user adoption metrics, or production performance data are reported. The system currently covers 125 schemes, with only 10 having fully hand-structured eligibility rules.
Human role
The original post does not say how a person stayed involved.
Limitations
The dataset is limited to 125 schemes (118 Central, 7 State), with only 10 having detailed structured rules; the rest rely on summary data. The agent uses a session token that expires, requiring manual rotation. Benefit calculations mix cash, insurance, and one-time subsidies, potentially overstating annual totals. The system is read-only for the agent, requiring human curation in Sanity Studio for updates.
Try it
Build a welfare eligibility assistant for [Target Region] using [CMS/Database Name] for structured rules. 1. Define schemas for 'Scheme', 'EligibilityRule' (with 'isExclusion' flag), and 'Source'. 2. Populate with [Number] sample schemes, ensuring at least 3 have complex exclusion logic. 3. Create an agent prompt that extracts user attributes (age, income, occupation) and queries the database using [Query Language, e.g., GROQ/SQL]. 4. Implement a post-processing step to attach official application URLs from the database, not the LLM. 5. Test with a sample user profile: '[User Description]'. Verify the agent correctly identifies exclusions. 6. Require human review of all generated eligibility verdicts before finalizing the logic. Output: A JSON response with verdict, reason, and source links. Measure success by checking if the agent correctly applies exclusion rules in 10/10 test cases.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.