What it is
This page introduces Agentic Document Workflows (ADW), a new architecture that enhances document processing and knowledge work automation by combining various elements such as retrieval and agentic orchestration….
Gabriel’s notes
a new architecture for applying agents on top of your documents: Agentic Document Workflows (ADW). This architecture combines document processing, retrieval, structured outputs, and agentic orchestration to enable end-to-end knowledge work automation. It is a step beyond both traditional Intelligent Document Processing (IDP) and RAG paradigms, which are focused on small, isolated steps of extraction and question-answering respectively, and helps to fulfill the promise of agents in dramatically increasing knowledge productivity.
Good fit if you want to:
- automate repetitive workflows and connect apps without custom code.
Pricing snapshot (auto-enriched): Free tier available with 10K credits; usage-based pricing with pay-as-you-go credits; pricing includes per user limits on lower plans and volume discounts on enterprise plans.
Work-use / compliance snapshot (auto-enriched): LlamaIndex is suitable for workplace use with secure data handling, 48-hour cached data retention, and offers enterprise features such as SSO integration; it maintains a strong compliance posture including SOC2 and HIPAA, and aligns with GDPR requirements.
Alternatives (auto-enriched): Alternative: Google Document AI | Comparison: Google Document AI specializes in document understanding and extraction, while LlamaIndex’s Agentic Document Workflows offer advanced agentic orchestration and multi-step workflow automation for complex knowledge work.
Reading tip: skim headings first, then focus on the sections that match your current project or question.
Note: pricing and policy details can change—verify on the official site before making decisions.