FISMA, FedRAMP, and state AI transparency laws extend to AI agents handling benefit eligibility, FOIA requests, and procurement. AutoPIL enforces classification-level access controls and produces the audit record that oversight bodies require.
10 policies across citizen services, records management, and procurement compliance — enforcing Privacy Act inter-agency data boundaries, blocking FOIA agents from classified records, and isolating procurement financials from citizen case data.
policies: # Benefits eligibility agent — applicant records and program criteria; blocked from law enforcement and classified data - name: benefits_eligibility_agent_policy agent_role: benefits_eligibility_agent allowed_sources: - applicant_records - program_eligibility_criteria - income_verification_data - benefits_history denied_sources: - law_enforcement_records - classified_data - interagency_intel allowed_tasks: - eligibility_determination - benefit_calculation - status_notification denied_tasks: - law_enforcement_query - procurement_action max_sensitivity: high
Point policy_path at your industry directory. AutoPIL loads every
YAML file recursively — roles, sensitivity rules, and process groups wired up
automatically from the directory structure. No additional config needed.
Policies are hot-reloaded at runtime. Extend or override any pre-built policy via the REST API without redeploying your agents or restarting services.
from autopil import ContextGuard # Point at your industry — only those policies load guard = ContextGuard( policy_path="policies/public_sector/", audit_db="autopil.db", ) # policies/public_sector/ — loads recursively # Switch verticals by changing the path — nothing else changes.
Pre-built policies for public sector are included in every AutoPIL trial. Extend or override any rule via the REST API without redeploying.