A well-liked AI orchestration framework Llama Index introduced a recent Agent Document Workflow (ADW) architecture that the company says goes beyond search-assisted generation (RAG) processes and increases agent productivity.
As orchestration structures proceed to enhance, this method may offer organizations the opportunity to extend agent decision-making capabilities.
LlamaIndex says ADW can help agents manage “complex workflows beyond simple extraction or matching.”
Some agent structures rely on RAG systems that provide agents with the information they should perform tasks. However, this method does not allow agents to make decisions based on this information.
LlamaIndex provided some real-world examples of ADW working well. For example, when reviewing contracts, analysts must extract key information, relate regulatory requirements, discover potential risks, and generate recommendations. AI agents deployed in this workflow would ideally follow the same pattern and make decisions based on the documents they read to review the contract and knowledge from other documents.
“ADW addresses these challenges by treating documents as part of broader business processes,” LlamaIndex said in: blog entry. “An ADW system can maintain state across stages, apply business rules, coordinate various components, and take action based on document content – not just analyzing it.”
LlamaIndex has previously stated that RAG, while an essential technique, stays primitive, especially for enterprises in search of more robust decision-making capabilities using AI.
Understanding the decision-making context
LlamaIndex has developed reference architectures that mix LlamaCloud’s analytics capabilities with agents. “It builds systems that can understand context, maintain state, and control multi-step processes.”
To do this, each workflow has a document that acts as a coordinator. It can direct agents to make use of LlamaParse to extract information from data, maintain the document’s context and process state, and then retrieve reference material from one other knowledge base. From this point, agents can start generating recommendations for the contract review use case or other actionable decisions for various use cases.
“By maintaining state throughout the process, agents can support complex, multi-step workflows that go beyond simple extraction or matching,” the company said. “This approach allows them to build deep context around the documents being processed while coordinating the operation of various system components.”
Different agent structures
Agent orchestration is an emerging field, and many organizations are still exploring how agents – or multiple agents – work for them. Coordinating agents and AI applications may grow to be a broader topic this yr as agents move from single systems to multi-agent ecosystems.
AI agents are an extension of the RAG offer, i.e. the ability to look for information based on the company’s knowledge.
But as more enterprises begin to deploy AI agents, they need them to also perform many of the tasks that employees perform. In more complicated cases, “vanilla” RAG is not going to be enough. One advanced approach that enterprises are considering is agent-based RAG, which expands agents’ knowledge base. Before they get the result, models can determine whether or not they need to search out more information, what tool to make use of to get it, and whether the context they simply retrieved is relevant.