The DPI-AI Framework is designed to be implemented — not just read. Use these tools to design your service, walk through the 9-step implementation journey, and watch a practical demonstration of a farmer requesting government support via WhatsApp.
translate(), identity_verify(), audit_log(). Each does one thing and is reusable across services.Amina is a smallholder farmer in Kisumu, Kenya. She sends a voice message on WhatsApp to apply for the Ministry of Agriculture's support benefit. Watch how AI Blocks, DPI Workflows, and DPI systems combine to deliver the service — with full governance at every step.
Select a use case to walk through all 9 implementation steps — from identifying scope to fine-tuning in operation — with sector-specific guidance at each stage.
Two complementary tools for designing and specifying DPI-AI services. Each opens as a dedicated full-page tool.
Free-form workflow builder. Pick any of 14 AI Blocks — foundational language primitives and sector-specific DPG connectors (MOSIP, OpenSPP, Mojaloop, W3C VC) — arrange them in execution order, generate a YAML spec, and simulate the workflow step by step.
Guided 6-step wizard to design a complete DPI-AI service. Choose from 30 use cases across 12 sectors, configure channels and the AI model (Cloud API, Self-Hosted, or SLM), map the citizen journey, select AI Blocks, and export a Code or OpenFn No-Code workflow spec with a governance risk checklist.