1. Understand the basic concepts of agentic document workflow, which consists of RAG, agents, and event-driven workflows.
2. Build a series of LlamaIndex’s workflows that increase in complexity and involve branching, looping logic, and concurrent executions.
3. Set up the agent’s RAG capability by parsing the source document, loading the extracted information into a vector store, and building a query engine on top of the store.
4. Implement workflow steps that enable the agent to parse the form to be filled, turn the parsed information into simple questions, and use the questions to query the RAG pipeline.
5. Incorporate human-in-the-loop into the workflow and ask the agent to re-answer when necessary to produce more accurate form responses.
6. Add multimodal capability to the agent, allowing it to process spoken feedback.