The model proposes. The system governs.
Policy-Based Agentic Systems (PBAS) — A framework for building agentic AI applications where the LLM generates plans but a deterministic policy engine governs execution.
Comprehensive guides and references for the DAF framework
Complete programmatic API documentation for all DAF components, classes, and methods.
Read Documentation →Eight core design principles behind DAF and how they influence the framework architecture.
Read Documentation →Step-by-step guide to extending DAF, implementing custom tools, agents, and policies.
Read Documentation →Get up and running with DAF in 2 minutes with mock examples and boilerplates.
View Quick Start →Understand the organization of the DAF repository and locate key components.
View Structure →Ready-to-run templates for common use cases: contract review, report generation, compliance, and more.
Explore Boilerplates →No LLM calls in policy evaluation. Either the plan conforms to your PolicyMatrix or it doesn't.
LLM handles cognition (planning), policy engine handles governance, execution runs in scoped context.
Write governance rules in YAML. Change policies without modifying code.
When plans violate policies, the system provides context for re-planning without manual intervention.
Develop and test with mock LLM clients. No API key required. Seamless switch to production.
Seven production-grade templates: contract review, report generation, support triage, and more.
Tests (Unit, Adversarial, Integration)
Production Boilerplates
Python Codebase
Open Source License
Clone the repository and run your first governed agentic loop in minutes.